OpenGL: Fix inverted conditional for counter flush from #4471 (#4560)

Fixes OpenGL.

.editorconfig

@@ -89,6 +89,7 @@ csharp_style_conditional_delegate_call = true:suggestion
 # Modifier preferences
 csharp_prefer_static_local_function = true:suggestion
 csharp_preferred_modifier_order = public,private,protected,internal,static,extern,new,virtual,abstract,sealed,override,readonly,unsafe,volatile,async:silent
+csharp_style_prefer_readonly_struct = true
 
 # Code-block preferences
 csharp_prefer_braces = true:silent

.gitattributes

@@ -1,63 +1,4 @@
 ###############################################################################
 # Set default behavior to automatically normalize line endings.
 ###############################################################################
-* text=auto
-
-###############################################################################
-# Set default behavior for command prompt diff.
-#
-# This is need for earlier builds of msysgit that does not have it on by
-# default for csharp files.
-# Note: This is only used by command line
-###############################################################################
-#*.cs     diff=csharp
-
-###############################################################################
-# Set the merge driver for project and solution files
-#
-# Merging from the command prompt will add diff markers to the files if there
-# are conflicts (Merging from VS is not affected by the settings below, in VS
-# the diff markers are never inserted). Diff markers may cause the following 
-# file extensions to fail to load in VS. An alternative would be to treat
-# these files as binary and thus will always conflict and require user
-# intervention with every merge. To do so, just uncomment the entries below
-###############################################################################
-#*.sln       merge=binary
-#*.csproj    merge=binary
-#*.vbproj    merge=binary
-#*.vcxproj   merge=binary
-#*.vcproj    merge=binary
-#*.dbproj    merge=binary
-#*.fsproj    merge=binary
-#*.lsproj    merge=binary
-#*.wixproj   merge=binary
-#*.modelproj merge=binary
-#*.sqlproj   merge=binary
-#*.wwaproj   merge=binary
-
-###############################################################################
-# behavior for image files
-#
-# image files are treated as binary by default.
-###############################################################################
-#*.jpg   binary
-#*.png   binary
-#*.gif   binary
-
-###############################################################################
-# diff behavior for common document formats
-# 
-# Convert binary document formats to text before diffing them. This feature
-# is only available from the command line. Turn it on by uncommenting the 
-# entries below.
-###############################################################################
-#*.doc   diff=astextplain
-#*.DOC   diff=astextplain
-#*.docx  diff=astextplain
-#*.DOCX  diff=astextplain
-#*.dot   diff=astextplain
-#*.DOT   diff=astextplain
-#*.pdf   diff=astextplain
-#*.PDF   diff=astextplain
-#*.rtf   diff=astextplain
-#*.RTF   diff=astextplain
+* text=auto eol=lf

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,43 +0,0 @@
----
-name: Bug Report
-about: Something doesn't work correctly in Ryujinx.
-#assignees:
----
-
-## Bug Report
-
-[ If any section does not apply, replace its contents with "N/A". ]</br>
-[ Lines between [ ] (square brackets) should be removed before posting. ]
-
-### What's the issue you encountered?
-
-[ Describe the issue in detail and what you were doing beforehand. ]</br>
-[ Did you make any changes related to Ryujinx itself? ]</br>
-[ If so, make sure to include details relating to what exactly you changed. ]
-
-### How can the issue be reproduced?
-
-[ Include a detailed step by step process for recreating your issue. ]
-
-### Log file
-
-[ Logs files can be found under ``Logs`` folder in Ryujinx program folder. ]</br>
-[ If you don't include a crash report in instances of crash related issues, we will ask you one to provide one. ]
-
-### Environment?
-
-- Ryujinx version: 1.0.X</br>
-[ Replace X's with the Ryujinx version at time of crash. ]
-- Game version: X.X.X</br>
-[ Replace X's with the game version at time of crash. ]
-- System Specs:
-  - OS: *(e.g. Windows 10)*
-  - CPU: *(e.g. i7-6700)*
-  - GPU: *(e.g. NVIDIA RTX 2070)*
-  - RAM: *(e.g. 16GB)*
-- Applied Mods : [ Yes (Which ones) / No ]
-
-### Additional context?
-
-Additional info about your environment:</br>
-[ Any other information relevant to your issue. ]

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,86 @@
+name: Bug Report
+description: File a bug report
+title: "[Bug]"
+labels: bug
+body:
+  - type: textarea
+    id: issue
+    attributes:
+      label: Description of the issue
+      description: What's the issue you encountered?
+    validations:
+      required: true
+  - type: textarea
+    id: repro
+    attributes:
+      label: Reproduction steps
+      description: How can the issue be reproduced?
+      placeholder: Describe each step as precisely as possible
+    validations:
+      required: true
+  - type: textarea
+    id: log
+    attributes:
+      label: Log file
+      description: A log file will help our developers to better diagnose and fix the issue.
+      placeholder: Logs files can be found under "Logs" folder in Ryujinx program folder. You can drag and drop the log on to the text area
+    validations:
+      required: true
+  - type: input
+    id: os
+    attributes:
+      label: OS
+      placeholder: "e.g. Windows 10"
+    validations:
+      required: true
+  - type: input
+    id: ryujinx-version
+    attributes:
+      label: Ryujinx version
+      placeholder: "e.g. 1.0.470"
+    validations:
+      required: true
+  - type: input
+    id: game-version
+    attributes:
+      label: Game version
+      placeholder: "e.g. 1.1.1"
+    validations:
+      required: false
+  - type: input
+    id: cpu
+    attributes:
+      label: CPU
+      placeholder: "e.g. i7-6700"
+    validations:
+      required: false
+  - type: input
+    id: gpu
+    attributes:
+      label: GPU
+      placeholder: "e.g. NVIDIA RTX 2070"
+    validations:
+      required: false
+  - type: input
+    id: ram
+    attributes:
+      label: RAM
+      placeholder: "e.g. 16GB"
+    validations:
+      required: false
+  - type: textarea
+    id: mods
+    attributes:
+      label: List of applied mods
+      placeholder: You can list applied mods here.
+    validations:
+      required: false
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional context?
+      description: |
+        - Additional info about your environment:
+        - Any other information relevant to your issue.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,34 +0,0 @@
----
-name: Feature Request
-about: Suggest a new feature for Ryujinx.
-#assignees:
----
-
-## Feature Request
-
-[ If any section does not apply, replace its contents with "N/A". ]</br>
-[ If you do not have the information needed for a section, replace its contents with "Unknown". ]</br>
-[ Lines between [ ] (square brackets) are to be removed before posting. ]</br>
-
-[ Please search for existing [feature requests](https://github.com/Ryujinx/Ryujinx/issues) before you make your own request. ]</br>
-[ Duplicate requests will be marked as such and you will be referred to the original request. ]
-
-### What feature are you suggesting?
-#### Overview:
-- [ Include the basic, high-level concepts for this feature here. ]
-
-#### Smaller Details: 
-- [ These may include specific methods of implementation etc. ]
-
-#### Nature of Request:  
-[ Remove all that do not apply to your request. ]
-- Addition
-  - [ Ex: Addition of certain original features or features from other community projects. ]
-  - [ If you are suggesting porting features or including features from other projects, include what license they are distributed under and what, if any libraries those project use. ]
-- Change
-- Removal
-  - [Ex: Removal of certain features or implementation due to a specific issue/bug or because of low quality code, etc.]
-
-### Why would this feature be useful?
-[ If this is a feature for an end-user, how does it benefit the end-user? ]</br>
-[ If this feature is for developers, what does it add to Ryujinx that did not already exist? ]

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,30 @@
+name: Feature Request
+description: Suggest a new feature for Ryujinx.
+title: "[Feature Request]"
+body:
+  - type: textarea
+    id: overview
+    attributes:
+      label: Overview
+      description: Include the basic, high-level concepts for this feature here.
+    validations:
+      required: true
+  - type: textarea
+    id: details
+    attributes:
+      label: Smaller details
+      description: These may include specific methods of implementation etc.
+    validations:
+      required: true
+  - type: textarea
+    id: request
+    attributes:
+      label: Nature of request
+    validations:
+      required: true
+  - type: textarea
+    id: feature
+    attributes:
+      label: Why would this feature be useful?
+    validations:
+      required: true

.github/ISSUE_TEMPLATE/missing_cpu_instruction.md

@@ -1,34 +0,0 @@
----
-name: Missing CPU Instruction
-about: CPU Instruction is missing in Ryujinx.
-#assignees:
----
-
-## Missing CPU Instruction
-
-[ If any section does not apply, replace its contents with "N/A". ]</br>
-[ If you do not have the information needed for a section, replace its contents with "Unknown". ]</br>
-[ Lines between [ ] (square brackets) are to be removed before posting. ]
-
-[ Please search for existing [missing CPU instruction](https://github.com/Ryujinx/Ryujinx/issues) before you make your own issue. ]</br>
-[ See the following [issue](https://github.com/Ryujinx/Ryujinx/issues/1405) as an example ]</br>
-[ Duplicate issue will be marked as such and you will be referred to the original request. ]
-
-### What CPU instruction is missing?
-
-Requires the *INSTRUCTION* instruction.</br>
-[ Replace *INSTRUCTION* by the instruction name, e.g. VADDL.U16 ]
-
-```
-*
-```
-[ Add the undefined instruction error message in the above code block ]
-
-### Instruction name
-```
-*
-```
-[ Include the name from [armconverter.com](https://armconverter.com/?disasm) or [shell-storm.org](http://shell-storm.org/online/Online-Assembler-and-Disassembler/?arch=arm64&endianness=big&dis_with_raw=True&dis_with_ins=True) in the above code block ]
-
-### Required by: 
-[ Add our (games list database)[https://github.com/Ryujinx/Ryujinx-Games-List/issues] links of games who require this instruction ]

.github/ISSUE_TEMPLATE/missing_cpu_instruction.yml

@@ -0,0 +1,26 @@
+name: Missing CPU Instruction
+description: CPU Instruction is missing in Ryujinx.
+title: "[CPU]"
+labels: [cpu, not-implemented]
+body:
+  - type: textarea
+    id: instruction
+    attributes:
+      label: CPU instruction
+      description: What CPU instruction is missing?
+    validations:
+      required: true
+  - type: textarea
+    id: name
+    attributes:
+      label: Instruction name
+      description: Include the name from [armconverter.com](https://armconverter.com/?disasm) or [shell-storm.org](http://shell-storm.org/online/Online-Assembler-and-Disassembler/?arch=arm64&endianness=big&dis_with_raw=True&dis_with_ins=True) in the above code block
+    validations:
+      required: true
+  - type: textarea
+    id: required
+    attributes:
+      label: Required by
+      description: Add links to the [compatibility list page(s)](https://github.com/Ryujinx/Ryujinx-Games-List/issues) of the game(s) that require this instruction.
+    validations:
+      required: true

.github/ISSUE_TEMPLATE/missing_service_call.md

@@ -1,35 +0,0 @@
----
-name: Missing Service Call
-about: Service call is missing in Ryujinx.
-#assignees:
----
-
-## Missing Service Call
-
-[ If any section does not apply, replace its contents with "N/A". ]</br>
-[ If you do not have the information needed for a section, replace its contents with "Unknown". ]</br>
-[ Lines between [ ] (square brackets) are to be removed before posting. ]
-
-[ Please search for existing [missing service call](https://github.com/Ryujinx/Ryujinx/issues) before you make your own issue. ]</br>
-[ See the following [issue](https://github.com/Ryujinx/Ryujinx/issues/1431) as an example ]</br>
-[ Duplicate issue will be marked as such and you will be referred to the original request. ]
-
-### What service call is missing?
-
-*SERVICE* *INTERFACE*: *NUMBER* (*NAME*) is not implemented.</br>
-[ Replace *SERVICE* by the service name, e.g. appletAE ]</br>
-[ Replace *INTERFACE* by the interface name, e.g. IAllSystemAppletProxiesService ]</br>
-[ Replace *NUMBER* by the call number, e.g. 100 ]</br>
-[ Replace *NAME* by the call name, e.g. OpenSystemAppletProxy ]</br>
-[ e.g. appletAE IAllSystemAppletProxiesService: 100 (OpenSystemAppletProxy) ]
-
-[ Add related links to the specific call from [Switchbrew](https://switchbrew.org/w/index.php?title=Services_API) and/or [SwIPC](https://reswitched.github.io/SwIPC/) ]
-
-### Service description
-```
-*
-```
-[ Include the description/explanation from [Switchbrew](https://switchbrew.org/w/index.php?title=Services_API) and/or [SwIPC](https://reswitched.github.io/SwIPC/) in the above code block ]
-
-### Required by: 
-[ Add our (games list database)[https://github.com/Ryujinx/Ryujinx-Games-List/issues] links of games who require this call ]

.github/ISSUE_TEMPLATE/missing_service_call.yml

@@ -0,0 +1,25 @@
+name: Missing Service Call
+description: Service call is missing in Ryujinx.
+labels: not-implemented
+body:
+  - type: textarea
+    id: instruction
+    attributes:
+      label: Service call
+      description: What service call is missing?
+    validations:
+      required: true
+  - type: textarea
+    id: name
+    attributes:
+      label: Service description
+      description: Include the description/explanation from [Switchbrew](https://switchbrew.org/w/index.php?title=Services_API) and/or [SwIPC](https://reswitched.github.io/SwIPC/) in the above code block
+    validations:
+      required: true
+  - type: textarea
+    id: required
+    attributes:
+      label: Required by
+      description:  Add links to the [compatibility list page(s)](https://github.com/Ryujinx/Ryujinx-Games-List/issues) of the game(s) that require this service.
+    validations:
+      required: true

.github/dependabot.yml

@@ -0,0 +1,24 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: weekly
+    labels:
+      - "infra"
+    reviewers:
+      - marysaka
+    commit-message:
+      prefix: "ci"
+
+  - package-ecosystem: nuget
+    directory: /
+    open-pull-requests-limit: 5
+    schedule:
+      interval: daily
+    labels:
+      - "infra"
+    reviewers:
+      - marysaka
+    commit-message:
+      prefix: nuget

.github/workflows/build.yml

@@ -48,44 +48,41 @@ jobs:
       DOTNET_CLI_TELEMETRY_OPTOUT: 1
       RYUJINX_BASE_VERSION: "1.1.0"
     steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-dotnet@v1
+      - uses: actions/checkout@v3
+      - uses: actions/setup-dotnet@v3
         with:
-          dotnet-version: 6.0.x
-      - name: Ensure NuGet Source
-        uses: fabriciomurta/ensure-nuget-source@v1
+          dotnet-version: 7.0.x
       - name: Get git short hash
         id: git_short_hash
-        run: echo "::set-output name=result::$(git rev-parse --short "${{ github.sha }}")"
-      - name: Clear
-        run: dotnet clean && dotnet nuget locals all --clear
+        run: echo "result=$(git rev-parse --short "${{ github.sha }}")" >> $GITHUB_OUTPUT
+        shell: bash
       - name: Build
-        run: dotnet build -c "${{ matrix.configuration }}" /p:Version="${{ env.RYUJINX_BASE_VERSION }}" /p:SourceRevisionId="${{ steps.git_short_hash.outputs.result }}" /p:ExtraDefineConstants=DISABLE_UPDATER
+        run: dotnet build -c "${{ matrix.configuration }}" -p:Version="${{ env.RYUJINX_BASE_VERSION }}" -p:SourceRevisionId="${{ steps.git_short_hash.outputs.result }}" -p:ExtraDefineConstants=DISABLE_UPDATER
       - name: Test
-        run: dotnet test -c "${{ matrix.configuration }}"
+        run: dotnet test --no-build -c "${{ matrix.configuration }}"
       - name: Publish Ryujinx
-        run: dotnet publish -c "${{ matrix.configuration }}" -r "${{ matrix.DOTNET_RUNTIME_IDENTIFIER }}" -o ./publish /p:Version="${{ env.RYUJINX_BASE_VERSION }}" /p:DebugType=embedded /p:SourceRevisionId="${{ steps.git_short_hash.outputs.result }}" /p:ExtraDefineConstants=DISABLE_UPDATER Ryujinx --self-contained
+        run: dotnet publish -c "${{ matrix.configuration }}" -r "${{ matrix.DOTNET_RUNTIME_IDENTIFIER }}" -o ./publish -p:Version="${{ env.RYUJINX_BASE_VERSION }}" -p:DebugType=embedded -p:SourceRevisionId="${{ steps.git_short_hash.outputs.result }}" -p:ExtraDefineConstants=DISABLE_UPDATER Ryujinx --self-contained true
         if: github.event_name == 'pull_request'
       - name: Publish Ryujinx.Headless.SDL2
-        run: dotnet publish -c "${{ matrix.configuration }}" -r "${{ matrix.DOTNET_RUNTIME_IDENTIFIER }}" -o ./publish_sdl2_headless /p:Version="${{ env.RYUJINX_BASE_VERSION }}" /p:DebugType=embedded /p:SourceRevisionId="${{ steps.git_short_hash.outputs.result }}" /p:ExtraDefineConstants=DISABLE_UPDATER Ryujinx.Headless.SDL2 --self-contained
+        run: dotnet publish -c "${{ matrix.configuration }}" -r "${{ matrix.DOTNET_RUNTIME_IDENTIFIER }}" -o ./publish_sdl2_headless -p:Version="${{ env.RYUJINX_BASE_VERSION }}" -p:DebugType=embedded -p:SourceRevisionId="${{ steps.git_short_hash.outputs.result }}" -p:ExtraDefineConstants=DISABLE_UPDATER Ryujinx.Headless.SDL2 --self-contained true
         if: github.event_name == 'pull_request'
       - name: Publish Ryujinx.Ava
-        run: dotnet publish -c "${{ matrix.configuration }}" -r "${{ matrix.DOTNET_RUNTIME_IDENTIFIER }}" -o ./publish_ava /p:Version="1.0.0" /p:DebugType=embedded /p:SourceRevisionId="${{ steps.git_short_hash.outputs.result }}" /p:ExtraDefineConstants=DISABLE_UPDATER Ryujinx.Ava
+        run: dotnet publish -c "${{ matrix.configuration }}" -r "${{ matrix.DOTNET_RUNTIME_IDENTIFIER }}" -o ./publish_ava -p:Version="${{ env.RYUJINX_BASE_VERSION }}" -p:DebugType=embedded -p:SourceRevisionId="${{ steps.git_short_hash.outputs.result }}" -p:ExtraDefineConstants=DISABLE_UPDATER Ryujinx.Ava --self-contained true
         if: github.event_name == 'pull_request'
       - name: Upload Ryujinx artifact
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: ryujinx-${{ matrix.configuration }}-${{ env.RYUJINX_BASE_VERSION }}+${{ steps.git_short_hash.outputs.result }}-${{ matrix.RELEASE_ZIP_OS_NAME }}
           path: publish
         if: github.event_name == 'pull_request'
       - name: Upload Ryujinx.Headless.SDL2 artifact
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: sdl2-ryujinx-headless-${{ matrix.configuration }}-${{ env.RYUJINX_BASE_VERSION }}+${{ steps.git_short_hash.outputs.result }}-${{ matrix.RELEASE_ZIP_OS_NAME }}
           path: publish_sdl2_headless
         if: github.event_name == 'pull_request'
       - name: Upload Ryujinx.Ava artifact
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: ava-ryujinx-${{ matrix.configuration }}-${{ env.RYUJINX_BASE_VERSION }}+${{ steps.git_short_hash.outputs.result }}-${{ matrix.RELEASE_ZIP_OS_NAME }}
           path: publish_ava

.github/workflows/flatpak.yml

@@ -0,0 +1,171 @@
+name: Flatpak release job
+
+on:
+  workflow_call:
+    inputs:
+      ryujinx_version:
+        required: true
+        type: string
+
+
+concurrency: flatpak-release
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+
+    env:
+      NUGET_PACKAGES: ${{ github.workspace }}/.nuget/packages
+      GIT_COMMITTER_NAME: "RyujinxBot"
+      GIT_COMMITTER_EMAIL: "61127645+RyujinxBot@users.noreply.github.com"
+      RYUJINX_PROJECT_FILE: "Ryujinx/Ryujinx.csproj"
+      NUGET_SOURCES_DESTDIR: "nuget-sources"
+      RYUJINX_VERSION: "${{ inputs.ryujinx_version }}"
+
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          path: Ryujinx
+
+      - uses: actions/setup-dotnet@v3
+        with:
+          global-json-file: Ryujinx/global.json
+
+      - name: Get version info
+        id: version_info
+        working-directory: Ryujinx
+        run: |
+          echo "git_hash=$(git rev-parse HEAD)" >> $GITHUB_OUTPUT
+
+      - uses: actions/checkout@v3
+        with:
+          repository: flathub/org.ryujinx.Ryujinx
+          token: ${{ secrets.RYUJINX_BOT_PAT }}
+          submodules: recursive
+          path: flathub
+
+      - name: Install dependencies
+        run: python -m pip install PyYAML lxml
+
+      - name: Restore Nuget packages
+        run: dotnet restore Ryujinx/${{ env.RYUJINX_PROJECT_FILE }}
+
+      - name: Generate nuget_sources.json
+        shell: python
+        run: |
+          from pathlib import Path
+          import base64
+          import binascii
+          import json
+          import os
+
+          sources = []
+
+          for path in Path(os.environ['NUGET_PACKAGES']).glob('**/*.nupkg.sha512'):
+            name = path.parent.parent.name
+            version = path.parent.name
+            filename = '{}.{}.nupkg'.format(name, version)
+            url = 'https://api.nuget.org/v3-flatcontainer/{}/{}/{}'.format(name, version, filename)
+
+            with path.open() as fp:
+                sha512 = binascii.hexlify(base64.b64decode(fp.read())).decode('ascii')
+
+            sources.append({
+                'type': 'file',
+                'url': url,
+                'sha512': sha512,
+                'dest': os.environ['NUGET_SOURCES_DESTDIR'],
+                'dest-filename': filename,
+            })
+
+          with open('flathub/nuget_sources.json', 'w') as fp:
+            json.dump(sources, fp, indent=4)
+
+      - name: Update flatpak metadata
+        id: metadata
+        env:
+          RYUJINX_GIT_HASH: ${{ steps.version_info.outputs.git_hash }}
+        shell: python
+        run: |
+          import hashlib
+          import hmac
+          import json
+          import os
+          import yaml
+          from datetime import datetime
+          from lxml import etree
+          
+          
+          # Ensure we don't destroy multiline strings
+          def str_presenter(dumper, data):
+            if len(data.splitlines()) > 1:
+              return dumper.represent_scalar("tag:yaml.org,2002:str", data, style="|")
+            return dumper.represent_scalar("tag:yaml.org,2002:str", data)
+            
+            
+          yaml.representer.SafeRepresenter.add_representer(str, str_presenter)
+  
+          yaml_file = "flathub/org.ryujinx.Ryujinx.yml"
+          xml_file = "flathub/org.ryujinx.Ryujinx.appdata.xml"
+
+          with open(yaml_file, "r") as f:
+            data = yaml.safe_load(f)
+
+          for source in data["modules"][0]["sources"]:
+            if type(source) is str:
+              continue
+            if (
+              source["type"] == "git"
+              and source["url"] == "https://github.com/Ryujinx/Ryujinx.git"
+            ):
+              source["commit"] = os.environ['RYUJINX_GIT_HASH']
+
+          is_same_version = data["modules"][0]["build-options"]["env"]["RYUJINX_VERSION"] == os.environ['RYUJINX_VERSION']
+
+          with open(os.environ['GITHUB_OUTPUT'], "a") as gh_out:
+            if is_same_version:
+              gh_out.write(f"commit_message=Retry update to {os.environ['RYUJINX_VERSION']}")
+            else:
+              gh_out.write(f"commit_message=Update to {os.environ['RYUJINX_VERSION']}")
+
+          if not is_same_version:
+            data["modules"][0]["build-options"]["env"]["RYUJINX_VERSION"] = os.environ['RYUJINX_VERSION']
+
+            with open(yaml_file, "w") as f:
+                yaml.safe_dump(data, f, sort_keys=False)
+
+            parser = etree.XMLParser(remove_blank_text=True)
+            tree = etree.parse(xml_file, parser)
+
+            root = tree.getroot()
+
+            releases = root.find("releases")
+
+            element = etree.Element("release")
+            element.set("version", os.environ['RYUJINX_VERSION'])
+            element.set("date", datetime.now().date().isoformat())
+            releases.insert(0, element)
+
+            # Ensure 4 spaces
+            etree.indent(root, space="    ")
+
+            with open(xml_file, "wb") as f:
+              f.write(
+                etree.tostring(
+                  tree,
+                  pretty_print=True,
+                  encoding="UTF-8",
+                  doctype='<?xml version="1.0" encoding="UTF-8"?>',
+                )
+              )
+
+      - name: Push flatpak update
+        working-directory: flathub
+        env:
+          COMMIT_MESSAGE: ${{ steps.metadata.outputs.commit_message }}
+        run: |
+          git config user.name "${{ env.GIT_COMMITTER_NAME }}"
+          git config user.email "${{ env.GIT_COMMITTER_EMAIL }}"
+          git add .
+          git commit -m "$COMMIT_MESSAGE"
+          git push origin master

.github/workflows/nightly_pr_comment.yml

@@ -8,7 +8,7 @@ jobs:
     if: github.event.workflow_run.event == 'pull_request' && github.event.workflow_run.conclusion == 'success'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/github-script@v3
+      - uses: actions/github-script@v6
         with:
           script: |
             const {owner, repo} = context.repo;
@@ -16,7 +16,7 @@ jobs:
             const pull_head_sha = '${{github.event.workflow_run.head_sha}}';
 
             const issue_number = await (async () => {
-              const pulls = await github.pulls.list({owner, repo});
+              const pulls = await github.rest.pulls.list({owner, repo});
               for await (const {data} of github.paginate.iterator(pulls)) {
                 for (const pull of data) {
                   if (pull.head.sha === pull_head_sha) {
@@ -31,7 +31,7 @@ jobs:
               return core.error(`No matching pull request found`);
             }
 
-            const {data: {artifacts}} = await github.actions.listWorkflowRunArtifacts({owner, repo, run_id});
+            const {data: {artifacts}} = await github.rest.actions.listWorkflowRunArtifacts({owner, repo, run_id});
             if (!artifacts.length) {
               return core.error(`No artifacts found`);
             }
@@ -57,12 +57,12 @@ jobs:
             body += hidden_headless_artifacts;
             body += hidden_debug_artifacts;
 
-            const {data: comments} = await github.issues.listComments({repo, owner, issue_number});
+            const {data: comments} = await github.rest.issues.listComments({repo, owner, issue_number});
             const existing_comment = comments.find((c) => c.user.login === 'github-actions[bot]');
             if (existing_comment) {
               core.info(`Updating comment ${existing_comment.id}`);
-              await github.issues.updateComment({repo, owner, comment_id: existing_comment.id, body});
+              await github.rest.issues.updateComment({repo, owner, comment_id: existing_comment.id, body});
             } else {
               core.info(`Creating a comment`);
-              await github.issues.createComment({repo, owner, issue_number, body});
+              await github.rest.issues.createComment({repo, owner, issue_number, body});
             }

.github/workflows/release.yml

@@ -11,49 +11,45 @@ on:
       - '*.yml'
       - 'README.md'
 
+concurrency: release
+
+env:
+  POWERSHELL_TELEMETRY_OPTOUT: 1
+  DOTNET_CLI_TELEMETRY_OPTOUT: 1
+  RYUJINX_BASE_VERSION: "1.1"
+  RYUJINX_TARGET_RELEASE_CHANNEL_NAME: "master"
+  RYUJINX_TARGET_RELEASE_CHANNEL_OWNER: "Ryujinx"
+  RYUJINX_TARGET_RELEASE_CHANNEL_REPO: "release-channel-master"
 
 jobs:
   release:
     runs-on: windows-latest
-
-    env:
-      POWERSHELL_TELEMETRY_OPTOUT: 1
-      DOTNET_CLI_TELEMETRY_OPTOUT: 1
-      RYUJINX_BASE_VERSION: "1.1"
-      RYUJINX_TARGET_RELEASE_CHANNEL_NAME: "master"
-      RYUJINX_TARGET_RELEASE_CHANNEL_OWNER: "Ryujinx"
-      RYUJINX_TARGET_RELEASE_CHANNEL_REPO: "release-channel-master"
-
     steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-dotnet@v1
+      - uses: actions/checkout@v3
+      - uses: actions/setup-dotnet@v3
         with:
-          dotnet-version: 6.0.x
-      - name: Ensure NuGet Source
-        uses: fabriciomurta/ensure-nuget-source@v1
-      - name: Clear
-        run: dotnet clean && dotnet nuget locals all --clear
+          global-json-file: global.json
       - name: Get version info
         id: version_info
         run: |
-          echo "::set-output name=build_version::${{ env.RYUJINX_BASE_VERSION }}.${{ github.run_number }}"
-          echo "::set-output name=git_short_hash::$(git rev-parse --short "${{ github.sha }}")"
+          echo "build_version=${{ env.RYUJINX_BASE_VERSION }}.${{ github.run_number }}" >> $GITHUB_OUTPUT
+          echo "git_short_hash=$(git rev-parse --short "${{ github.sha }}")" >> $GITHUB_OUTPUT
         shell: bash
       - name: Configure for release
         run: |
-          sed -r --in-place 's/\%\%RYUJINX_BUILD_VERSION\%\%/${{ steps.version_info.outputs.build_version }}/g;' Ryujinx.Common/ReleaseInformations.cs
-          sed -r --in-place 's/\%\%RYUJINX_BUILD_GIT_HASH\%\%/${{ steps.version_info.outputs.git_short_hash }}/g;' Ryujinx.Common/ReleaseInformations.cs
-          sed -r --in-place 's/\%\%RYUJINX_TARGET_RELEASE_CHANNEL_NAME\%\%/${{ env.RYUJINX_TARGET_RELEASE_CHANNEL_NAME }}/g;' Ryujinx.Common/ReleaseInformations.cs
-          sed -r --in-place 's/\%\%RYUJINX_TARGET_RELEASE_CHANNEL_OWNER\%\%/${{ env.RYUJINX_TARGET_RELEASE_CHANNEL_OWNER }}/g;' Ryujinx.Common/ReleaseInformations.cs
-          sed -r --in-place 's/\%\%RYUJINX_TARGET_RELEASE_CHANNEL_REPO\%\%/${{ env.RYUJINX_TARGET_RELEASE_CHANNEL_REPO }}/g;' Ryujinx.Common/ReleaseInformations.cs
+          sed -r --in-place 's/\%\%RYUJINX_BUILD_VERSION\%\%/${{ steps.version_info.outputs.build_version }}/g;' Ryujinx.Common/ReleaseInformation.cs
+          sed -r --in-place 's/\%\%RYUJINX_BUILD_GIT_HASH\%\%/${{ steps.version_info.outputs.git_short_hash }}/g;' Ryujinx.Common/ReleaseInformation.cs
+          sed -r --in-place 's/\%\%RYUJINX_TARGET_RELEASE_CHANNEL_NAME\%\%/${{ env.RYUJINX_TARGET_RELEASE_CHANNEL_NAME }}/g;' Ryujinx.Common/ReleaseInformation.cs
+          sed -r --in-place 's/\%\%RYUJINX_TARGET_RELEASE_CHANNEL_OWNER\%\%/${{ env.RYUJINX_TARGET_RELEASE_CHANNEL_OWNER }}/g;' Ryujinx.Common/ReleaseInformation.cs
+          sed -r --in-place 's/\%\%RYUJINX_TARGET_RELEASE_CHANNEL_REPO\%\%/${{ env.RYUJINX_TARGET_RELEASE_CHANNEL_REPO }}/g;' Ryujinx.Common/ReleaseInformation.cs
         shell: bash
       - name: Create output dir
         run: "mkdir release_output"
       - name: Publish Windows
         run: |
-          dotnet publish -c Release -r win10-x64 -o ./publish_windows/publish /p:Version="${{ steps.version_info.outputs.build_version }}" /p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" /p:DebugType=embedded Ryujinx --self-contained
-          dotnet publish -c Release -r win10-x64 -o ./publish_windows_sdl2_headless/publish /p:Version="${{ steps.version_info.outputs.build_version }}" /p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" /p:DebugType=embedded Ryujinx.Headless.SDL2 --self-contained
-          dotnet publish -c Release -r win10-x64 -o ./publish_windows_ava/publish /p:Version="${{ steps.version_info.outputs.build_version }}" /p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" /p:DebugType=embedded Ryujinx.Ava --self-contained
+          dotnet publish -c Release -r win10-x64 -o ./publish_windows/publish -p:Version="${{ steps.version_info.outputs.build_version }}" -p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" -p:DebugType=embedded Ryujinx --self-contained true
+          dotnet publish -c Release -r win10-x64 -o ./publish_windows_sdl2_headless/publish -p:Version="${{ steps.version_info.outputs.build_version }}" -p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" -p:DebugType=embedded Ryujinx.Headless.SDL2 --self-contained true
+          dotnet publish -c Release -r win10-x64 -o ./publish_windows_ava/publish -p:Version="${{ steps.version_info.outputs.build_version }}" -p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" -p:DebugType=embedded Ryujinx.Ava --self-contained true
       - name: Packing Windows builds
         run: |
           pushd publish_windows
@@ -71,22 +67,34 @@ jobs:
 
       - name: Publish Linux
         run: |
-          dotnet publish -c Release -r linux-x64 -o ./publish_linux/publish /p:Version="${{ steps.version_info.outputs.build_version }}" /p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" /p:DebugType=embedded Ryujinx --self-contained
-          dotnet publish -c Release -r linux-x64 -o ./publish_linux_sdl2_headless/publish /p:Version="${{ steps.version_info.outputs.build_version }}" /p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" /p:DebugType=embedded Ryujinx.Headless.SDL2 --self-contained
-          dotnet publish -c Release -r linux-x64 -o ./publish_linux_ava/publish /p:Version="${{ steps.version_info.outputs.build_version }}" /p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" /p:DebugType=embedded Ryujinx.Ava --self-contained
+          dotnet publish -c Release -r linux-x64 -o ./publish_linux/publish -p:Version="${{ steps.version_info.outputs.build_version }}" -p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" -p:DebugType=embedded Ryujinx --self-contained true
+          dotnet publish -c Release -r linux-x64 -o ./publish_linux_sdl2_headless/publish -p:Version="${{ steps.version_info.outputs.build_version }}" -p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" -p:DebugType=embedded Ryujinx.Headless.SDL2 --self-contained true
+          dotnet publish -c Release -r linux-x64 -o ./publish_linux_ava/publish -p:Version="${{ steps.version_info.outputs.build_version }}" -p:SourceRevisionId="${{ steps.version_info.outputs.git_short_hash }}" -p:DebugType=embedded Ryujinx.Ava --self-contained true
 
       - name: Packing Linux builds
         run: |
           pushd publish_linux
-          tar -czvf ../release_output/ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar.gz publish
+          tar --exclude "publish/Ryujinx" --exclude "publish/Ryujinx.sh" -cvf ../release_output/ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar publish
+          python3 ../distribution/misc/add_tar_exec.py ../release_output/ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar "publish/Ryujinx" "publish/Ryujinx"
+          python3 ../distribution/misc/add_tar_exec.py ../release_output/ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar "publish/Ryujinx.sh" "publish/Ryujinx.sh"
+          gzip -9 < ../release_output/ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar > ../release_output/ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar.gz
+          rm ../release_output/ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar
           popd
 
           pushd publish_linux_sdl2_headless
-          tar -czvf ../release_output/sdl2-ryujinx-headless-${{ steps.version_info.outputs.build_version }}-linux_x64.tar.gz publish
+          tar --exclude "publish/Ryujinx.Headless.SDL2" --exclude "publish/Ryujinx.sh" -cvf ../release_output/sdl2-ryujinx-headless-${{ steps.version_info.outputs.build_version }}-linux_x64.tar publish
+          python3 ../distribution/misc/add_tar_exec.py ../release_output/sdl2-ryujinx-headless-${{ steps.version_info.outputs.build_version }}-linux_x64.tar "publish/Ryujinx.Headless.SDL2" "publish/Ryujinx.Headless.SDL2"
+          python3 ../distribution/misc/add_tar_exec.py ../release_output/sdl2-ryujinx-headless-${{ steps.version_info.outputs.build_version }}-linux_x64.tar "publish/Ryujinx.sh" "publish/Ryujinx.sh"
+          gzip -9 < ../release_output/sdl2-ryujinx-headless-${{ steps.version_info.outputs.build_version }}-linux_x64.tar > ../release_output/sdl2-ryujinx-headless-${{ steps.version_info.outputs.build_version }}-linux_x64.tar.gz
+          rm ../release_output/sdl2-ryujinx-headless-${{ steps.version_info.outputs.build_version }}-linux_x64.tar
           popd
 
           pushd publish_linux_ava
-          tar -czvf ../release_output/test-ava-ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar.gz publish
+          tar --exclude "publish/Ryujinx.Ava" --exclude "publish/Ryujinx.sh" -cvf ../release_output/test-ava-ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar publish
+          python3 ../distribution/misc/add_tar_exec.py ../release_output/test-ava-ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar "publish/Ryujinx.Ava" "publish/Ryujinx.Ava"
+          python3 ../distribution/misc/add_tar_exec.py ../release_output/test-ava-ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar "publish/Ryujinx.sh" "publish/Ryujinx.sh"
+          gzip -9 < ../release_output/test-ava-ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar > ../release_output/test-ava-ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar.gz
+          rm ../release_output/test-ava-ryujinx-${{ steps.version_info.outputs.build_version }}-linux_x64.tar
           popd
         shell: bash
 
@@ -103,3 +111,10 @@ jobs:
           owner: ${{ env.RYUJINX_TARGET_RELEASE_CHANNEL_OWNER }}
           repo: ${{ env.RYUJINX_TARGET_RELEASE_CHANNEL_REPO }}
           token: ${{ secrets.RELEASE_TOKEN }}
+
+  flatpak_release:
+    uses: ./.github/workflows/flatpak.yml
+    needs: release
+    with:
+      ryujinx_version: "1.1.${{ github.run_number }}"
+    secrets: inherit

.gitignore

@@ -125,6 +125,9 @@ ClientBin/
 packages/*
 *.config
 
+# Include nuget.config
+!nuget.config
+
 # RIA/Silverlight projects
 Generated_Code/
 
@@ -167,3 +170,6 @@ launchSettings.json
 
 # NetCore Publishing Profiles
 PublishProfiles/
+
+# Glade backup files
+*.glade~

ARMeilleure/ARMeilleure.csproj

@@ -1,7 +1,7 @@
 <Project Sdk="Microsoft.NET.Sdk">
 
   <PropertyGroup>
-    <TargetFramework>net6.0</TargetFramework>
+    <TargetFramework>net7.0</TargetFramework>
     <AllowUnsafeBlocks>true</AllowUnsafeBlocks>
   </PropertyGroup>
 
@@ -9,4 +9,17 @@
     <ProjectReference Include="..\Ryujinx.Common\Ryujinx.Common.csproj" />
   </ItemGroup>
 
+  <ItemGroup>
+    <ContentWithTargetPath Include="Native\libs\libarmeilleure-jitsupport.dylib" Condition="'$(RuntimeIdentifier)' == '' OR '$(RuntimeIdentifier)' == 'osx-arm64'">
+      <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
+      <TargetPath>libarmeilleure-jitsupport.dylib</TargetPath>
+    </ContentWithTargetPath>
+  </ItemGroup>
+
+  <ItemGroup>
+    <AssemblyAttribute Include="System.Runtime.CompilerServices.InternalsVisibleTo">
+      <_Parameter1>Ryujinx.Tests</_Parameter1>
+    </AssemblyAttribute>
+  </ItemGroup>
+
 </Project>

ARMeilleure/CodeGen/Arm64/Arm64Optimizer.cs

@@ -0,0 +1,270 @@
+using ARMeilleure.CodeGen.Optimizations;
+using ARMeilleure.IntermediateRepresentation;
+using ARMeilleure.Translation;
+using System.Collections.Generic;
+using static ARMeilleure.IntermediateRepresentation.Operand.Factory;
+using static ARMeilleure.IntermediateRepresentation.Operation.Factory;
+
+namespace ARMeilleure.CodeGen.Arm64
+{
+    static class Arm64Optimizer
+    {
+        private const int MaxConstantUses = 10000;
+
+        public static void RunPass(ControlFlowGraph cfg)
+        {
+            var constants = new Dictionary<ulong, Operand>();
+
+            Operand GetConstantCopy(BasicBlock block, Operation operation, Operand source)
+            {
+                // If the constant has many uses, we also force a new constant mov to be added, in order
+                // to avoid overflow of the counts field (that is limited to 16 bits).
+                if (!constants.TryGetValue(source.Value, out var constant) || constant.UsesCount > MaxConstantUses)
+                {
+                    constant = Local(source.Type);
+
+                    Operation copyOp = Operation(Instruction.Copy, constant, source);
+
+                    block.Operations.AddBefore(operation, copyOp);
+
+                    constants[source.Value] = constant;
+                }
+
+                return constant;
+            }
+
+            for (BasicBlock block = cfg.Blocks.First; block != null; block = block.ListNext)
+            {
+                constants.Clear();
+
+                Operation nextNode;
+
+                for (Operation node = block.Operations.First; node != default; node = nextNode)
+                {
+                    nextNode = node.ListNext;
+
+                    // Insert copies for constants that can't fit on a 32-bit immediate.
+                    // Doing this early unblocks a few optimizations.
+                    if (node.Instruction == Instruction.Add)
+                    {
+                        Operand src1 = node.GetSource(0);
+                        Operand src2 = node.GetSource(1);
+
+                        if (src1.Kind == OperandKind.Constant && (src1.Relocatable || ConstTooLong(src1, OperandType.I32)))
+                        {
+                            node.SetSource(0, GetConstantCopy(block, node, src1));
+                        }
+
+                        if (src2.Kind == OperandKind.Constant && (src2.Relocatable || ConstTooLong(src2, OperandType.I32)))
+                        {
+                            node.SetSource(1, GetConstantCopy(block, node, src2));
+                        }
+                    }
+
+                    // Try to fold something like:
+                    //  lsl x1, x1, #2
+                    //  add x0, x0, x1
+                    //  ldr x0, [x0]
+                    //  add x2, x2, #16
+                    //  ldr x2, [x2]
+                    // Into:
+                    //  ldr x0, [x0, x1, lsl #2]
+                    //  ldr x2, [x2, #16]
+                    if (IsMemoryLoadOrStore(node.Instruction))
+                    {
+                        OperandType type;
+
+                        if (node.Destination != default)
+                        {
+                            type = node.Destination.Type;
+                        }
+                        else
+                        {
+                            type = node.GetSource(1).Type;
+                        }
+
+                        Operand memOp = GetMemoryOperandOrNull(node.GetSource(0), type);
+
+                        if (memOp != default)
+                        {
+                            node.SetSource(0, memOp);
+                        }
+                    }
+                }
+            }
+
+            Optimizer.RemoveUnusedNodes(cfg);
+        }
+
+        private static Operand GetMemoryOperandOrNull(Operand addr, OperandType type)
+        {
+            Operand baseOp = addr;
+
+            // First we check if the address is the result of a local X with immediate
+            // addition. If that is the case, then the baseOp is X, and the memory operand immediate
+            // becomes the addition immediate. Otherwise baseOp keeps being the address.
+            int imm = GetConstOp(ref baseOp, type);
+            if (imm != 0)
+            {
+                return MemoryOp(type, baseOp, default, Multiplier.x1, imm);
+            }
+
+            // Now we check if the baseOp is the result of a local Y with a local Z addition.
+            // If that is the case, we now set baseOp to Y and indexOp to Z. We further check
+            // if Z is the result of a left shift of local W by a value == 0 or == Log2(AccessSize),
+            // if that is the case, we set indexOp to W and adjust the scale value of the memory operand
+            // to match that of the left shift.
+            // There is one missed case, which is the address being a shift result, but this is
+            // probably not worth optimizing as it should never happen.
+            (Operand indexOp, Multiplier scale) = GetIndexOp(ref baseOp, type);
+
+            // If baseOp is still equal to address, then there's nothing that can be optimized.
+            if (baseOp == addr)
+            {
+                return default;
+            }
+
+            return MemoryOp(type, baseOp, indexOp, scale, 0);
+        }
+
+        private static int GetConstOp(ref Operand baseOp, OperandType accessType)
+        {
+            Operation operation = GetAsgOpWithInst(baseOp, Instruction.Add);
+
+            if (operation == default)
+            {
+                return 0;
+            }
+
+            Operand src1 = operation.GetSource(0);
+            Operand src2 = operation.GetSource(1);
+
+            Operand constOp;
+            Operand otherOp;
+
+            if (src1.Kind == OperandKind.Constant && src2.Kind == OperandKind.LocalVariable)
+            {
+                constOp = src1;
+                otherOp = src2;
+            }
+            else if (src1.Kind == OperandKind.LocalVariable && src2.Kind == OperandKind.Constant)
+            {
+                constOp = src2;
+                otherOp = src1;
+            }
+            else
+            {
+                return 0;
+            }
+
+            // If we have addition by a constant that we can't encode on the instruction,
+            // then we can't optimize it further.
+            if (ConstTooLong(constOp, accessType))
+            {
+                return 0;
+            }
+
+            baseOp = otherOp;
+
+            return constOp.AsInt32();
+        }
+
+        private static (Operand, Multiplier) GetIndexOp(ref Operand baseOp, OperandType accessType)
+        {
+            Operand indexOp = default;
+
+            Multiplier scale = Multiplier.x1;
+
+            Operation addOp = GetAsgOpWithInst(baseOp, Instruction.Add);
+
+            if (addOp == default)
+            {
+                return (indexOp, scale);
+            }
+
+            Operand src1 = addOp.GetSource(0);
+            Operand src2 = addOp.GetSource(1);
+
+            if (src1.Kind != OperandKind.LocalVariable || src2.Kind != OperandKind.LocalVariable)
+            {
+                return (indexOp, scale);
+            }
+
+            baseOp = src1;
+            indexOp = src2;
+
+            Operation shlOp = GetAsgOpWithInst(src1, Instruction.ShiftLeft);
+
+            bool indexOnSrc2 = false;
+
+            if (shlOp == default)
+            {
+                shlOp = GetAsgOpWithInst(src2, Instruction.ShiftLeft);
+
+                indexOnSrc2 = true;
+            }
+
+            if (shlOp != default)
+            {
+                Operand shSrc = shlOp.GetSource(0);
+                Operand shift = shlOp.GetSource(1);
+
+                int maxShift = Assembler.GetScaleForType(accessType);
+
+                if (shSrc.Kind == OperandKind.LocalVariable &&
+                    shift.Kind == OperandKind.Constant &&
+                    (shift.Value == 0 || shift.Value == (ulong)maxShift))
+                {
+                    scale = shift.Value switch
+                    {
+                        1 => Multiplier.x2,
+                        2 => Multiplier.x4,
+                        3 => Multiplier.x8,
+                        4 => Multiplier.x16,
+                        _ => Multiplier.x1
+                    };
+
+                    baseOp = indexOnSrc2 ? src1 : src2;
+                    indexOp = shSrc;
+                }
+            }
+
+            return (indexOp, scale);
+        }
+
+        private static Operation GetAsgOpWithInst(Operand op, Instruction inst)
+        {
+            // If we have multiple assignments, folding is not safe
+            // as the value may be different depending on the
+            // control flow path.
+            if (op.AssignmentsCount != 1)
+            {
+                return default;
+            }
+
+            Operation asgOp = op.Assignments[0];
+
+            if (asgOp.Instruction != inst)
+            {
+                return default;
+            }
+
+            return asgOp;
+        }
+
+        private static bool IsMemoryLoadOrStore(Instruction inst)
+        {
+            return inst == Instruction.Load || inst == Instruction.Store;
+        }
+
+        private static bool ConstTooLong(Operand constOp, OperandType accessType)
+        {
+            if ((uint)constOp.Value != constOp.Value)
+            {
+                return true;
+            }
+
+            return !CodeGenCommon.ConstFitsOnUImm12(constOp.AsInt32(), accessType);
+        }
+    }
+}

ARMeilleure/CodeGen/Arm64/ArmCondition.cs

@@ -0,0 +1,47 @@
+using ARMeilleure.IntermediateRepresentation;
+using System;
+
+namespace ARMeilleure.CodeGen.Arm64
+{
+    enum ArmCondition
+    {
+        Eq   = 0,
+        Ne   = 1,
+        GeUn = 2,
+        LtUn = 3,
+        Mi   = 4,
+        Pl   = 5,
+        Vs   = 6,
+        Vc   = 7,
+        GtUn = 8,
+        LeUn = 9,
+        Ge   = 10,
+        Lt   = 11,
+        Gt   = 12,
+        Le   = 13,
+        Al   = 14,
+        Nv   = 15
+    }
+
+    static class ComparisonArm64Extensions
+    {
+        public static ArmCondition ToArmCondition(this Comparison comp)
+        {
+            return comp switch
+            {
+                Comparison.Equal            => ArmCondition.Eq,
+                Comparison.NotEqual         => ArmCondition.Ne,
+                Comparison.Greater          => ArmCondition.Gt,
+                Comparison.LessOrEqual      => ArmCondition.Le,
+                Comparison.GreaterUI        => ArmCondition.GtUn,
+                Comparison.LessOrEqualUI    => ArmCondition.LeUn,
+                Comparison.GreaterOrEqual   => ArmCondition.Ge,
+                Comparison.Less             => ArmCondition.Lt,
+                Comparison.GreaterOrEqualUI => ArmCondition.GeUn,
+                Comparison.LessUI           => ArmCondition.LtUn,
+
+                _ => throw new ArgumentException(null, nameof(comp))
+            };
+        }
+    }
+}

ARMeilleure/CodeGen/Arm64/ArmExtensionType.cs

@@ -0,0 +1,14 @@
+namespace ARMeilleure.CodeGen.Arm64
+{
+    enum ArmExtensionType
+    {
+        Uxtb = 0,
+        Uxth = 1,
+        Uxtw = 2,
+        Uxtx = 3,
+        Sxtb = 4,
+        Sxth = 5,
+        Sxtw = 6,
+        Sxtx = 7
+    }
+}

ARMeilleure/CodeGen/Arm64/ArmShiftType.cs

@@ -0,0 +1,11 @@
+
+namespace ARMeilleure.CodeGen.Arm64
+{
+    enum ArmShiftType
+    {
+        Lsl = 0,
+        Lsr = 1,
+        Asr = 2,
+        Ror = 3
+    }
+}

ARMeilleure/CodeGen/Arm64/CallingConvention.cs

@@ -0,0 +1,96 @@
+using System;
+
+namespace ARMeilleure.CodeGen.Arm64
+{
+    static class CallingConvention
+    {
+        private const int RegistersMask = unchecked((int)0xffffffff);
+
+        // Some of those register have specific roles and can't be used as general purpose registers.
+        // X18 - Reserved for platform specific usage.
+        // X29 - Frame pointer.
+        // X30 - Return address.
+        // X31 - Not an actual register, in some cases maps to SP, and in others to ZR.
+        private const int ReservedRegsMask = (1 << CodeGenCommon.ReservedRegister) | (1 << 18) | (1 << 29) | (1 << 30) | (1 << 31);
+
+        public static int GetIntAvailableRegisters()
+        {
+            return RegistersMask & ~ReservedRegsMask;
+        }
+
+        public static int GetVecAvailableRegisters()
+        {
+            return RegistersMask;
+        }
+
+        public static int GetIntCallerSavedRegisters()
+        {
+            return (GetIntCalleeSavedRegisters() ^ RegistersMask) & ~ReservedRegsMask;
+        }
+
+        public static int GetFpCallerSavedRegisters()
+        {
+            return GetFpCalleeSavedRegisters() ^ RegistersMask;
+        }
+
+        public static int GetVecCallerSavedRegisters()
+        {
+            return GetVecCalleeSavedRegisters() ^ RegistersMask;
+        }
+
+        public static int GetIntCalleeSavedRegisters()
+        {
+            return 0x1ff80000; // X19 to X28
+        }
+
+        public static int GetFpCalleeSavedRegisters()
+        {
+            return 0xff00; // D8 to D15
+        }
+
+        public static int GetVecCalleeSavedRegisters()
+        {
+            return 0;
+        }
+
+        public static int GetArgumentsOnRegsCount()
+        {
+            return 8;
+        }
+
+        public static int GetIntArgumentRegister(int index)
+        {
+            if ((uint)index < (uint)GetArgumentsOnRegsCount())
+            {
+                return index;
+            }
+
+            throw new ArgumentOutOfRangeException(nameof(index));
+        }
+
+        public static int GetVecArgumentRegister(int index)
+        {
+            if ((uint)index < (uint)GetArgumentsOnRegsCount())
+            {
+                return index;
+            }
+
+            throw new ArgumentOutOfRangeException(nameof(index));
+        }
+
+        public static int GetIntReturnRegister()
+        {
+            return 0;
+        }
+
+        public static int GetIntReturnRegisterHigh()
+        {
+            return 1;
+        }
+
+        public static int GetVecReturnRegister()
+        {
+            return 0;
+        }
+    }
+}

ARMeilleure/CodeGen/Arm64/CodeGenCommon.cs

@@ -0,0 +1,91 @@
+using ARMeilleure.IntermediateRepresentation;
+using System.Numerics;
+
+namespace ARMeilleure.CodeGen.Arm64
+{
+    static class CodeGenCommon
+    {
+        public const int TcAddressRegister = 8;
+        public const int ReservedRegister = 17;
+
+        public static bool ConstFitsOnSImm7(int value, int scale)
+        {
+            return (((value >> scale) << 25) >> (25 - scale)) == value;
+        }
+
+        public static bool ConstFitsOnSImm9(int value)
+        {
+            return ((value << 23) >> 23) == value;
+        }
+
+        public static bool ConstFitsOnUImm12(int value)
+        {
+            return (value & 0xfff) == value;
+        }
+
+        public static bool ConstFitsOnUImm12(int value, OperandType type)
+        {
+            int scale = Assembler.GetScaleForType(type);
+            return (((value >> scale) & 0xfff) << scale) == value;
+        }
+
+        public static bool TryEncodeBitMask(Operand operand, out int immN, out int immS, out int immR)
+        {
+            return TryEncodeBitMask(operand.Type, operand.Value, out immN, out immS, out immR);
+        }
+
+        public static bool TryEncodeBitMask(OperandType type, ulong value, out int immN, out int immS, out int immR)
+        {
+            if (type == OperandType.I32)
+            {
+                value |= value << 32;
+            }
+
+            return TryEncodeBitMask(value, out immN, out immS, out immR);
+        }
+
+        public static bool TryEncodeBitMask(ulong value, out int immN, out int immS, out int immR)
+        {
+            // Some special values also can't be encoded:
+            // 0 can't be encoded because we need to subtract 1 from onesCount (which would became negative if 0).
+            // A value with all bits set can't be encoded because it is reserved according to the spec, because:
+            // Any value AND all ones will be equal itself, so it's effectively a no-op.
+            // Any value OR all ones will be equal all ones, so one can just use MOV.
+            // Any value XOR all ones will be equal its inverse, so one can just use MVN.
+            if (value == 0 || value == ulong.MaxValue)
+            {
+                immN = 0;
+                immS = 0;
+                immR = 0;
+
+                return false;
+            }
+
+            // Normalize value, rotating it such that the LSB is 1: Ensures we get a complete element that has not
+            // been cut-in-half across the word boundary.
+            int rotation = BitOperations.TrailingZeroCount(value & (value + 1));
+            ulong rotatedValue = ulong.RotateRight(value, rotation);
+
+            // Now that we have a complete element in the LSB with the LSB = 1, determine size and number of ones
+            // in element.
+            int elementSize = BitOperations.TrailingZeroCount(rotatedValue & (rotatedValue + 1));
+            int onesInElement = BitOperations.TrailingZeroCount(~rotatedValue);
+
+            // Check the value is repeating; also ensures element size is a power of two.
+            if (ulong.RotateRight(value, elementSize) != value)
+            {
+                immN = 0;
+                immS = 0;
+                immR = 0;
+
+                return false;
+            }
+
+            immN = (elementSize >> 6) & 1;
+            immS = (((~elementSize + 1) << 1) | (onesInElement - 1)) & 0x3f;
+            immR = (elementSize - rotation) & (elementSize - 1);
+
+            return true;
+        }
+    }
+}

ARMeilleure/CodeGen/Arm64/CodeGenContext.cs

@@ -0,0 +1,287 @@
+using ARMeilleure.CodeGen.Linking;
+using ARMeilleure.CodeGen.RegisterAllocators;
+using ARMeilleure.IntermediateRepresentation;
+using Ryujinx.Common.Memory;
+using System;
+using System.Collections.Generic;
+using System.IO;
+
+namespace ARMeilleure.CodeGen.Arm64
+{
+    class CodeGenContext
+    {
+        private const int BccInstLength = 4;
+        private const int CbnzInstLength = 4;
+        private const int LdrLitInstLength = 4;
+
+        private Stream _stream;
+
+        public int StreamOffset => (int)_stream.Length;
+
+        public AllocationResult AllocResult { get; }
+
+        public Assembler Assembler { get; }
+
+        public BasicBlock CurrBlock { get; private set; }
+
+        public bool HasCall { get; }
+
+        public int CallArgsRegionSize { get; }
+        public int FpLrSaveRegionSize { get; }
+
+        private readonly Dictionary<BasicBlock, long> _visitedBlocks;
+        private readonly Dictionary<BasicBlock, List<(ArmCondition Condition, long BranchPos)>> _pendingBranches;
+
+        private struct ConstantPoolEntry
+        {
+            public readonly int Offset;
+            public readonly Symbol Symbol;
+            public readonly List<(Operand, int)> LdrOffsets;
+
+            public ConstantPoolEntry(int offset, Symbol symbol)
+            {
+                Offset = offset;
+                Symbol = symbol;
+                LdrOffsets = new List<(Operand, int)>();
+            }
+        }
+
+        private readonly Dictionary<ulong, ConstantPoolEntry> _constantPool;
+
+        private bool _constantPoolWritten;
+        private long _constantPoolOffset;
+
+        private ArmCondition _jNearCondition;
+        private Operand _jNearValue;
+
+        private long _jNearPosition;
+
+        private readonly bool _relocatable;
+
+        public CodeGenContext(AllocationResult allocResult, int maxCallArgs, int blocksCount, bool relocatable)
+        {
+            _stream = MemoryStreamManager.Shared.GetStream();
+
+            AllocResult = allocResult;
+
+            Assembler = new Assembler(_stream);
+
+            bool hasCall = maxCallArgs >= 0;
+
+            HasCall = hasCall;
+
+            if (maxCallArgs < 0)
+            {
+                maxCallArgs = 0;
+            }
+
+            CallArgsRegionSize = maxCallArgs * 16;
+            FpLrSaveRegionSize = hasCall ? 16 : 0;
+
+            _visitedBlocks = new Dictionary<BasicBlock, long>();
+            _pendingBranches = new Dictionary<BasicBlock, List<(ArmCondition, long)>>();
+            _constantPool = new Dictionary<ulong, ConstantPoolEntry>();
+
+            _relocatable = relocatable;
+        }
+
+        public void EnterBlock(BasicBlock block)
+        {
+            CurrBlock = block;
+
+            long target = _stream.Position;
+
+            if (_pendingBranches.TryGetValue(block, out var list))
+            {
+                foreach (var tuple in list)
+                {
+                    _stream.Seek(tuple.BranchPos, SeekOrigin.Begin);
+                    WriteBranch(tuple.Condition, target);
+                }
+
+                _stream.Seek(target, SeekOrigin.Begin);
+                _pendingBranches.Remove(block);
+            }
+
+            _visitedBlocks.Add(block, target);
+        }
+
+        public void JumpTo(BasicBlock target)
+        {
+            JumpTo(ArmCondition.Al, target);
+        }
+
+        public void JumpTo(ArmCondition condition, BasicBlock target)
+        {
+            if (_visitedBlocks.TryGetValue(target, out long offset))
+            {
+                WriteBranch(condition, offset);
+            }
+            else
+            {
+                if (!_pendingBranches.TryGetValue(target, out var list))
+                {
+                    list = new List<(ArmCondition, long)>();
+                    _pendingBranches.Add(target, list);
+                }
+
+                list.Add((condition, _stream.Position));
+
+                _stream.Seek(BccInstLength, SeekOrigin.Current);
+            }
+        }
+
+        private void WriteBranch(ArmCondition condition, long to)
+        {
+            int imm = checked((int)(to - _stream.Position));
+
+            if (condition != ArmCondition.Al)
+            {
+                Assembler.B(condition, imm);
+            }
+            else
+            {
+                Assembler.B(imm);
+            }
+        }
+
+        public void JumpToNear(ArmCondition condition)
+        {
+            _jNearCondition = condition;
+            _jNearPosition = _stream.Position;
+
+            _stream.Seek(BccInstLength, SeekOrigin.Current);
+        }
+
+        public void JumpToNearIfNotZero(Operand value)
+        {
+            _jNearValue = value;
+            _jNearPosition = _stream.Position;
+
+            _stream.Seek(CbnzInstLength, SeekOrigin.Current);
+        }
+
+        public void JumpHere()
+        {
+            long currentPosition = _stream.Position;
+            long offset = currentPosition - _jNearPosition;
+
+            _stream.Seek(_jNearPosition, SeekOrigin.Begin);
+
+            if (_jNearValue != default)
+            {
+                Assembler.Cbnz(_jNearValue, checked((int)offset));
+                _jNearValue = default;
+            }
+            else
+            {
+                Assembler.B(_jNearCondition, checked((int)offset));
+            }
+
+            _stream.Seek(currentPosition, SeekOrigin.Begin);
+        }
+
+        public void ReserveRelocatableConstant(Operand rt, Symbol symbol, ulong value)
+        {
+            if (!_constantPool.TryGetValue(value, out ConstantPoolEntry cpe))
+            {
+                cpe = new ConstantPoolEntry(_constantPool.Count * sizeof(ulong), symbol);
+                _constantPool.Add(value, cpe);
+            }
+
+            cpe.LdrOffsets.Add((rt, (int)_stream.Position));
+            _stream.Seek(LdrLitInstLength, SeekOrigin.Current);
+        }
+
+        private long WriteConstantPool()
+        {
+            if (_constantPoolWritten)
+            {
+                return _constantPoolOffset;
+            }
+
+            long constantPoolBaseOffset = _stream.Position;
+
+            foreach (ulong value in _constantPool.Keys)
+            {
+                WriteUInt64(value);
+            }
+
+            foreach (ConstantPoolEntry cpe in _constantPool.Values)
+            {
+                foreach ((Operand rt, int ldrOffset) in cpe.LdrOffsets)
+                {
+                    _stream.Seek(ldrOffset, SeekOrigin.Begin);
+
+                    int absoluteOffset = checked((int)(constantPoolBaseOffset + cpe.Offset));
+                    int pcRelativeOffset = absoluteOffset - ldrOffset;
+
+                    Assembler.LdrLit(rt, pcRelativeOffset);
+                }
+            }
+
+            _stream.Seek(constantPoolBaseOffset + _constantPool.Count * sizeof(ulong), SeekOrigin.Begin);
+
+            _constantPoolOffset = constantPoolBaseOffset;
+            _constantPoolWritten = true;
+
+            return constantPoolBaseOffset;
+        }
+
+        public (byte[], RelocInfo) GetCode()
+        {
+            long constantPoolBaseOffset = WriteConstantPool();
+
+            byte[] code = new byte[_stream.Length];
+
+            long originalPosition = _stream.Position;
+
+            _stream.Seek(0, SeekOrigin.Begin);
+            _stream.Read(code, 0, code.Length);
+            _stream.Seek(originalPosition, SeekOrigin.Begin);
+
+            RelocInfo relocInfo;
+
+            if (_relocatable)
+            {
+                RelocEntry[] relocs = new RelocEntry[_constantPool.Count];
+
+                int index = 0;
+
+                foreach (ConstantPoolEntry cpe in _constantPool.Values)
+                {
+                    if (cpe.Symbol.Type != SymbolType.None)
+                    {
+                        int absoluteOffset = checked((int)(constantPoolBaseOffset + cpe.Offset));
+                        relocs[index++] = new RelocEntry(absoluteOffset, cpe.Symbol);
+                    }
+                }
+
+                if (index != relocs.Length)
+                {
+                    Array.Resize(ref relocs, index);
+                }
+
+                relocInfo = new RelocInfo(relocs);
+            }
+            else
+            {
+                relocInfo = new RelocInfo(Array.Empty<RelocEntry>());
+            }
+
+            return (code, relocInfo);
+        }
+
+        private void WriteUInt64(ulong value)
+        {
+            _stream.WriteByte((byte)(value >> 0));
+            _stream.WriteByte((byte)(value >> 8));
+            _stream.WriteByte((byte)(value >> 16));
+            _stream.WriteByte((byte)(value >> 24));
+            _stream.WriteByte((byte)(value >> 32));
+            _stream.WriteByte((byte)(value >> 40));
+            _stream.WriteByte((byte)(value >> 48));
+            _stream.WriteByte((byte)(value >> 56));
+        }
+    }
+}

ARMeilleure/CodeGen/Arm64/CodeGeneratorIntrinsic.cs

@@ -0,0 +1,662 @@
+using ARMeilleure.IntermediateRepresentation;
+using System;
+using System.Diagnostics;
+
+namespace ARMeilleure.CodeGen.Arm64
+{
+    static class CodeGeneratorIntrinsic
+    {
+        public static void GenerateOperation(CodeGenContext context, Operation operation)
+        {
+            Intrinsic intrin = operation.Intrinsic;
+
+            IntrinsicInfo info = IntrinsicTable.GetInfo(intrin & ~(Intrinsic.Arm64VTypeMask | Intrinsic.Arm64VSizeMask));
+
+            switch (info.Type)
+            {
+                case IntrinsicType.ScalarUnary:
+                    GenerateVectorUnary(
+                        context,
+                        0,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0));
+                    break;
+                case IntrinsicType.ScalarUnaryByElem:
+                    Debug.Assert(operation.GetSource(1).Kind == OperandKind.Constant);
+
+                    GenerateVectorUnaryByElem(
+                        context,
+                        0,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        (uint)operation.GetSource(1).AsInt32(),
+                        operation.Destination,
+                        operation.GetSource(0));
+                    break;
+                case IntrinsicType.ScalarBinary:
+                    GenerateVectorBinary(
+                        context,
+                        0,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        operation.GetSource(1));
+                    break;
+                case IntrinsicType.ScalarBinaryFPByElem:
+                    Debug.Assert(operation.GetSource(2).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryFPByElem(
+                        context,
+                        0,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        (uint)operation.GetSource(2).AsInt32(),
+                        operation.Destination,
+                        operation.GetSource(0),
+                        operation.GetSource(1));
+                    break;
+                case IntrinsicType.ScalarBinaryRd:
+                    GenerateVectorUnary(
+                        context,
+                        0,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(1));
+                    break;
+                case IntrinsicType.ScalarBinaryShl:
+                    Debug.Assert(operation.GetSource(1).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryShlImm(
+                        context,
+                        0,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        (uint)operation.GetSource(1).AsInt32());
+                    break;
+                case IntrinsicType.ScalarBinaryShr:
+                    Debug.Assert(operation.GetSource(1).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryShrImm(
+                        context,
+                        0,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        (uint)operation.GetSource(1).AsInt32());
+                    break;
+                case IntrinsicType.ScalarFPCompare:
+                    GenerateScalarFPCompare(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        operation.GetSource(1));
+                    break;
+                case IntrinsicType.ScalarFPConvFixed:
+                    Debug.Assert(operation.GetSource(1).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryShrImm(
+                        context,
+                        0,
+                        ((uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift) + 2u,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        (uint)operation.GetSource(1).AsInt32());
+                    break;
+                case IntrinsicType.ScalarFPConvFixedGpr:
+                    Debug.Assert(operation.GetSource(1).Kind == OperandKind.Constant);
+
+                    GenerateScalarFPConvGpr(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        (uint)operation.GetSource(1).AsInt32());
+                    break;
+                case IntrinsicType.ScalarFPConvGpr:
+                    GenerateScalarFPConvGpr(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0));
+                    break;
+                case IntrinsicType.ScalarTernary:
+                    GenerateScalarTernary(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(1),
+                        operation.GetSource(2),
+                        operation.GetSource(0));
+                    break;
+                case IntrinsicType.ScalarTernaryFPRdByElem:
+                    Debug.Assert(operation.GetSource(3).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryFPByElem(
+                        context,
+                        0,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        (uint)operation.GetSource(3).AsInt32(),
+                        operation.Destination,
+                        operation.GetSource(1),
+                        operation.GetSource(2));
+                    break;
+                case IntrinsicType.ScalarTernaryShlRd:
+                    Debug.Assert(operation.GetSource(2).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryShlImm(
+                        context,
+                        0,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(1),
+                        (uint)operation.GetSource(2).AsInt32());
+                    break;
+                case IntrinsicType.ScalarTernaryShrRd:
+                    Debug.Assert(operation.GetSource(2).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryShrImm(
+                        context,
+                        0,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(1),
+                        (uint)operation.GetSource(2).AsInt32());
+                    break;
+
+                case IntrinsicType.VectorUnary:
+                    GenerateVectorUnary(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0));
+                    break;
+                case IntrinsicType.VectorUnaryByElem:
+                    Debug.Assert(operation.GetSource(1).Kind == OperandKind.Constant);
+
+                    GenerateVectorUnaryByElem(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        (uint)operation.GetSource(1).AsInt32(),
+                        operation.Destination,
+                        operation.GetSource(0));
+                    break;
+                case IntrinsicType.VectorBinary:
+                    GenerateVectorBinary(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        operation.GetSource(1));
+                    break;
+                case IntrinsicType.VectorBinaryBitwise:
+                    GenerateVectorBinary(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        operation.GetSource(1));
+                    break;
+                case IntrinsicType.VectorBinaryByElem:
+                    Debug.Assert(operation.GetSource(2).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryByElem(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        (uint)operation.GetSource(2).AsInt32(),
+                        operation.Destination,
+                        operation.GetSource(0),
+                        operation.GetSource(1));
+                    break;
+                case IntrinsicType.VectorBinaryFPByElem:
+                    Debug.Assert(operation.GetSource(2).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryFPByElem(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        (uint)operation.GetSource(2).AsInt32(),
+                        operation.Destination,
+                        operation.GetSource(0),
+                        operation.GetSource(1));
+                    break;
+                case IntrinsicType.VectorBinaryRd:
+                    GenerateVectorUnary(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(1));
+                    break;
+                case IntrinsicType.VectorBinaryShl:
+                    Debug.Assert(operation.GetSource(1).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryShlImm(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        (uint)operation.GetSource(1).AsInt32());
+                    break;
+                case IntrinsicType.VectorBinaryShr:
+                    Debug.Assert(operation.GetSource(1).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryShrImm(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        (uint)operation.GetSource(1).AsInt32());
+                    break;
+                case IntrinsicType.VectorFPConvFixed:
+                    Debug.Assert(operation.GetSource(1).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryShrImm(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        ((uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift) + 2u,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(0),
+                        (uint)operation.GetSource(1).AsInt32());
+                    break;
+                case IntrinsicType.VectorInsertByElem:
+                    Debug.Assert(operation.GetSource(1).Kind == OperandKind.Constant);
+                    Debug.Assert(operation.GetSource(3).Kind == OperandKind.Constant);
+
+                    GenerateVectorInsertByElem(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        (uint)operation.GetSource(3).AsInt32(),
+                        (uint)operation.GetSource(1).AsInt32(),
+                        operation.Destination,
+                        operation.GetSource(2));
+                    break;
+                case IntrinsicType.VectorLookupTable:
+                    Debug.Assert((uint)(operation.SourcesCount - 2) <= 3);
+
+                    for (int i = 1; i < operation.SourcesCount - 1; i++)
+                    {
+                        Register currReg = operation.GetSource(i).GetRegister();
+                        Register prevReg = operation.GetSource(i - 1).GetRegister();
+
+                        Debug.Assert(prevReg.Index + 1 == currReg.Index && currReg.Type == RegisterType.Vector);
+                    }
+
+                    GenerateVectorBinary(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        info.Inst | ((uint)(operation.SourcesCount - 2) << 13),
+                        operation.Destination,
+                        operation.GetSource(0),
+                        operation.GetSource(operation.SourcesCount - 1));
+                    break;
+                case IntrinsicType.VectorTernaryFPRdByElem:
+                    Debug.Assert(operation.GetSource(3).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryFPByElem(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        (uint)operation.GetSource(3).AsInt32(),
+                        operation.Destination,
+                        operation.GetSource(1),
+                        operation.GetSource(2));
+                    break;
+                case IntrinsicType.VectorTernaryRd:
+                    GenerateVectorBinary(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(1),
+                        operation.GetSource(2));
+                    break;
+                case IntrinsicType.VectorTernaryRdBitwise:
+                    GenerateVectorBinary(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(1),
+                        operation.GetSource(2));
+                    break;
+                case IntrinsicType.VectorTernaryRdByElem:
+                    Debug.Assert(operation.GetSource(3).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryByElem(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        (uint)operation.GetSource(3).AsInt32(),
+                        operation.Destination,
+                        operation.GetSource(1),
+                        operation.GetSource(2));
+                    break;
+                case IntrinsicType.VectorTernaryShlRd:
+                    Debug.Assert(operation.GetSource(2).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryShlImm(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(1),
+                        (uint)operation.GetSource(2).AsInt32());
+                    break;
+                case IntrinsicType.VectorTernaryShrRd:
+                    Debug.Assert(operation.GetSource(2).Kind == OperandKind.Constant);
+
+                    GenerateVectorBinaryShrImm(
+                        context,
+                        (uint)(intrin & Intrinsic.Arm64VTypeMask) >> (int)Intrinsic.Arm64VTypeShift,
+                        (uint)(intrin & Intrinsic.Arm64VSizeMask) >> (int)Intrinsic.Arm64VSizeShift,
+                        info.Inst,
+                        operation.Destination,
+                        operation.GetSource(1),
+                        (uint)operation.GetSource(2).AsInt32());
+                    break;
+
+                case IntrinsicType.GetRegister:
+                    context.Assembler.WriteInstruction(info.Inst, operation.Destination);
+                    break;
+                case IntrinsicType.SetRegister:
+                    context.Assembler.WriteInstruction(info.Inst, operation.GetSource(0));
+                    break;
+
+                default:
+                    throw new NotImplementedException(info.Type.ToString());
+            }
+        }
+
+        private static void GenerateScalarFPCompare(
+            CodeGenContext context,
+            uint sz,
+            uint instruction,
+            Operand dest,
+            Operand rn,
+            Operand rm)
+        {
+            instruction |= (sz << 22);
+
+            if (rm.Kind == OperandKind.Constant && rm.Value == 0)
+            {
+                instruction |= 0b1000;
+                rm = rn;
+            }
+
+            context.Assembler.WriteInstructionRm16NoRet(instruction, rn, rm);
+            context.Assembler.Mrs(dest, 1, 3, 4, 2, 0);
+        }
+
+        private static void GenerateScalarFPConvGpr(
+            CodeGenContext context,
+            uint sz,
+            uint instruction,
+            Operand rd,
+            Operand rn)
+        {
+            instruction |= (sz << 22);
+
+            if (rd.Type.IsInteger())
+            {
+                context.Assembler.WriteInstructionAuto(instruction, rd, rn);
+            }
+            else
+            {
+                if (rn.Type == OperandType.I64)
+                {
+                    instruction |= Assembler.SfFlag;
+                }
+
+                context.Assembler.WriteInstruction(instruction, rd, rn);
+            }
+        }
+
+        private static void GenerateScalarFPConvGpr(
+            CodeGenContext context,
+            uint sz,
+            uint instruction,
+            Operand rd,
+            Operand rn,
+            uint fBits)
+        {
+            Debug.Assert(fBits <= 64);
+
+            instruction |= (sz << 22);
+            instruction |= (64 - fBits) << 10;
+
+            if (rd.Type.IsInteger())
+            {
+                Debug.Assert(rd.Type != OperandType.I32 || fBits <= 32);
+
+                context.Assembler.WriteInstructionAuto(instruction, rd, rn);
+            }
+            else
+            {
+                if (rn.Type == OperandType.I64)
+                {
+                    instruction |= Assembler.SfFlag;
+                }
+                else
+                {
+                    Debug.Assert(fBits <= 32);
+                }
+
+                context.Assembler.WriteInstruction(instruction, rd, rn);
+            }
+
+        }
+
+        private static void GenerateScalarTernary(
+            CodeGenContext context,
+            uint sz,
+            uint instruction,
+            Operand rd,
+            Operand rn,
+            Operand rm,
+            Operand ra)
+        {
+            instruction |= (sz << 22);
+
+            context.Assembler.WriteInstruction(instruction, rd, rn, rm, ra);
+        }
+
+        private static void GenerateVectorUnary(
+            CodeGenContext context,
+            uint q,
+            uint sz,
+            uint instruction,
+            Operand rd,
+            Operand rn)
+        {
+            instruction |= (q << 30) | (sz << 22);
+
+            context.Assembler.WriteInstruction(instruction, rd, rn);
+        }
+
+        private static void GenerateVectorUnaryByElem(
+            CodeGenContext context,
+            uint q,
+            uint sz,
+            uint instruction,
+            uint srcIndex,
+            Operand rd,
+            Operand rn)
+        {
+            uint imm5 = (srcIndex << ((int)sz + 1)) | (1u << (int)sz);
+
+            instruction |= (q << 30) | (imm5 << 16);
+
+            context.Assembler.WriteInstruction(instruction, rd, rn);
+        }
+
+        private static void GenerateVectorBinary(
+            CodeGenContext context,
+            uint q,
+            uint instruction,
+            Operand rd,
+            Operand rn,
+            Operand rm)
+        {
+            instruction |= (q << 30);
+
+            context.Assembler.WriteInstructionRm16(instruction, rd, rn, rm);
+        }
+
+        private static void GenerateVectorBinary(
+            CodeGenContext context,
+            uint q,
+            uint sz,
+            uint instruction,
+            Operand rd,
+            Operand rn,
+            Operand rm)
+        {
+            instruction |= (q << 30) | (sz << 22);
+
+            context.Assembler.WriteInstructionRm16(instruction, rd, rn, rm);
+        }
+
+        private static void GenerateVectorBinaryByElem(
+            CodeGenContext context,
+            uint q,
+            uint size,
+            uint instruction,
+            uint srcIndex,
+            Operand rd,
+            Operand rn,
+            Operand rm)
+        {
+            instruction |= (q << 30) | (size << 22);
+
+            if (size == 2)
+            {
+                instruction |= ((srcIndex & 1) << 21) | ((srcIndex & 2) << 10);
+            }
+            else
+            {
+                instruction |= ((srcIndex & 3) << 20) | ((srcIndex & 4) << 9);
+            }
+
+            context.Assembler.WriteInstructionRm16(instruction, rd, rn, rm);
+        }
+
+        private static void GenerateVectorBinaryFPByElem(
+            CodeGenContext context,
+            uint q,
+            uint sz,
+            uint instruction,
+            uint srcIndex,
+            Operand rd,
+            Operand rn,
+            Operand rm)
+        {
+            instruction |= (q << 30) | (sz << 22);
+
+            if (sz != 0)
+            {
+                instruction |= (srcIndex & 1) << 11;
+            }
+            else
+            {
+                instruction |= ((srcIndex & 1) << 21) | ((srcIndex & 2) << 10);
+            }
+
+            context.Assembler.WriteInstructionRm16(instruction, rd, rn, rm);
+        }
+
+        private static void GenerateVectorBinaryShlImm(
+            CodeGenContext context,
+            uint q,
+            uint sz,
+            uint instruction,
+            Operand rd,
+            Operand rn,
+            uint shift)
+        {
+            instruction |= (q << 30);
+
+            Debug.Assert(shift >= 0 && shift < (8u << (int)sz));
+
+            uint imm = (8u << (int)sz) | (shift & (0x3fu >> (int)(3 - sz)));
+
+            instruction |= (imm << 16);
+
+            context.Assembler.WriteInstruction(instruction, rd, rn);
+        }
+
+        private static void GenerateVectorBinaryShrImm(
+            CodeGenContext context,
+            uint q,
+            uint sz,
+            uint instruction,
+            Operand rd,
+            Operand rn,
+            uint shift)
+        {
+            instruction |= (q << 30);
+
+            Debug.Assert(shift > 0 && shift <= (8u << (int)sz));
+
+            uint imm = (8u << (int)sz) | ((8u << (int)sz) - shift);
+
+            instruction |= (imm << 16);
+
+            context.Assembler.WriteInstruction(instruction, rd, rn);
+        }
+
+        private static void GenerateVectorInsertByElem(
+            CodeGenContext context,
+            uint sz,
+            uint instruction,
+            uint srcIndex,
+            uint dstIndex,
+            Operand rd,
+            Operand rn)
+        {
+            uint imm4 = srcIndex << (int)sz;
+            uint imm5 = (dstIndex << ((int)sz + 1)) | (1u << (int)sz);
+
+            instruction |= imm4 << 11;
+            instruction |= imm5 << 16;
+
+            context.Assembler.WriteInstruction(instruction, rd, rn);
+        }
+    }
+}

ARMeilleure/CodeGen/Arm64/HardwareCapabilities.cs

@@ -0,0 +1,185 @@
+using System;
+using System.Linq;
+using System.Reflection;
+using System.Runtime.CompilerServices;
+using System.Runtime.InteropServices;
+using System.Runtime.Intrinsics.Arm;
+using System.Runtime.Versioning;
+
+namespace ARMeilleure.CodeGen.Arm64
+{
+    static partial class HardwareCapabilities
+    {
+        static HardwareCapabilities()
+        {
+            if (!ArmBase.Arm64.IsSupported)
+            {
+                return;
+            }
+
+            if (OperatingSystem.IsLinux())
+            {
+                LinuxFeatureInfoHwCap = (LinuxFeatureFlagsHwCap)getauxval(AT_HWCAP);
+                LinuxFeatureInfoHwCap2 = (LinuxFeatureFlagsHwCap2)getauxval(AT_HWCAP2);
+            }
+
+            if (OperatingSystem.IsMacOS())
+            {
+                for (int i = 0; i < _sysctlNames.Length; i++)
+                {
+                    if (CheckSysctlName(_sysctlNames[i]))
+                    {
+                        MacOsFeatureInfo |= (MacOsFeatureFlags)(1 << i);
+                    }
+                }
+            }
+        }
+
+#region Linux
+
+        private const ulong AT_HWCAP = 16;
+        private const ulong AT_HWCAP2 = 26;
+
+        [LibraryImport("libc", SetLastError = true)]
+        private static partial ulong getauxval(ulong type);
+
+        [Flags]
+        public enum LinuxFeatureFlagsHwCap : ulong
+        {
+            Fp        = 1 << 0,
+            Asimd     = 1 << 1,
+            Evtstrm   = 1 << 2,
+            Aes       = 1 << 3,
+            Pmull     = 1 << 4,
+            Sha1      = 1 << 5,
+            Sha2      = 1 << 6,
+            Crc32     = 1 << 7,
+            Atomics   = 1 << 8,
+            FpHp      = 1 << 9,
+            AsimdHp   = 1 << 10,
+            CpuId     = 1 << 11,
+            AsimdRdm  = 1 << 12,
+            Jscvt     = 1 << 13,
+            Fcma      = 1 << 14,
+            Lrcpc     = 1 << 15,
+            DcpOp     = 1 << 16,
+            Sha3      = 1 << 17,
+            Sm3       = 1 << 18,
+            Sm4       = 1 << 19,
+            AsimdDp   = 1 << 20,
+            Sha512    = 1 << 21,
+            Sve       = 1 << 22,
+            AsimdFhm  = 1 << 23,
+            Dit       = 1 << 24,
+            Uscat     = 1 << 25,
+            Ilrcpc    = 1 << 26,
+            FlagM     = 1 << 27,
+            Ssbs      = 1 << 28,
+            Sb        = 1 << 29,
+            Paca      = 1 << 30,
+            Pacg      = 1UL << 31
+        }
+
+        [Flags]
+        public enum LinuxFeatureFlagsHwCap2 : ulong
+        {
+            Dcpodp      = 1 << 0,
+            Sve2        = 1 << 1,
+            SveAes      = 1 << 2,
+            SvePmull    = 1 << 3,
+            SveBitperm  = 1 << 4,
+            SveSha3     = 1 << 5,
+            SveSm4      = 1 << 6,
+            FlagM2      = 1 << 7,
+            Frint       = 1 << 8,
+            SveI8mm     = 1 << 9,
+            SveF32mm    = 1 << 10,
+            SveF64mm    = 1 << 11,
+            SveBf16     = 1 << 12,
+            I8mm        = 1 << 13,
+            Bf16        = 1 << 14,
+            Dgh         = 1 << 15,
+            Rng         = 1 << 16,
+            Bti         = 1 << 17,
+            Mte         = 1 << 18,
+            Ecv         = 1 << 19,
+            Afp         = 1 << 20,
+            Rpres       = 1 << 21,
+            Mte3        = 1 << 22,
+            Sme         = 1 << 23,
+            Sme_i16i64  = 1 << 24,
+            Sme_f64f64  = 1 << 25,
+            Sme_i8i32   = 1 << 26,
+            Sme_f16f32  = 1 << 27,
+            Sme_b16f32  = 1 << 28,
+            Sme_f32f32  = 1 << 29,
+            Sme_fa64    = 1 << 30,
+            Wfxt        = 1UL << 31,
+            Ebf16       = 1UL << 32,
+            Sve_Ebf16   = 1UL << 33,
+            Cssc        = 1UL << 34,
+            Rprfm       = 1UL << 35,
+            Sve2p1      = 1UL << 36
+        }
+
+        public static LinuxFeatureFlagsHwCap LinuxFeatureInfoHwCap { get; } = 0;
+        public static LinuxFeatureFlagsHwCap2 LinuxFeatureInfoHwCap2 { get; } = 0;
+
+#endregion
+
+#region macOS
+
+        [LibraryImport("libSystem.dylib", SetLastError = true)]
+        private static unsafe partial int sysctlbyname([MarshalAs(UnmanagedType.LPStr)] string name, out int oldValue, ref ulong oldSize, IntPtr newValue, ulong newValueSize);
+
+        [SupportedOSPlatform("macos")]
+        private static bool CheckSysctlName(string name)
+        {
+            ulong size = sizeof(int);
+            if (sysctlbyname(name, out int val, ref size, IntPtr.Zero, 0) == 0 && size == sizeof(int))
+            {
+                return val != 0;
+            }
+            return false;
+        }
+
+        private static string[] _sysctlNames = new string[]
+        {
+            "hw.optional.floatingpoint",
+            "hw.optional.AdvSIMD",
+            "hw.optional.arm.FEAT_FP16",
+            "hw.optional.arm.FEAT_AES",
+            "hw.optional.arm.FEAT_PMULL",
+            "hw.optional.arm.FEAT_LSE",
+            "hw.optional.armv8_crc32",
+            "hw.optional.arm.FEAT_SHA1",
+            "hw.optional.arm.FEAT_SHA256"
+        };
+
+        [Flags]
+        public enum MacOsFeatureFlags
+        {
+            Fp      = 1 << 0,
+            AdvSimd = 1 << 1,
+            Fp16    = 1 << 2,
+            Aes     = 1 << 3,
+            Pmull   = 1 << 4,
+            Lse     = 1 << 5,
+            Crc32   = 1 << 6,
+            Sha1    = 1 << 7,
+            Sha256  = 1 << 8
+        }
+
+        public static MacOsFeatureFlags MacOsFeatureInfo { get; } = 0;
+
+#endregion
+
+        public static bool SupportsAdvSimd => LinuxFeatureInfoHwCap.HasFlag(LinuxFeatureFlagsHwCap.Asimd) || MacOsFeatureInfo.HasFlag(MacOsFeatureFlags.AdvSimd);
+        public static bool SupportsAes => LinuxFeatureInfoHwCap.HasFlag(LinuxFeatureFlagsHwCap.Aes) || MacOsFeatureInfo.HasFlag(MacOsFeatureFlags.Aes);
+        public static bool SupportsPmull => LinuxFeatureInfoHwCap.HasFlag(LinuxFeatureFlagsHwCap.Pmull) || MacOsFeatureInfo.HasFlag(MacOsFeatureFlags.Pmull);
+        public static bool SupportsLse => LinuxFeatureInfoHwCap.HasFlag(LinuxFeatureFlagsHwCap.Atomics) || MacOsFeatureInfo.HasFlag(MacOsFeatureFlags.Lse);
+        public static bool SupportsCrc32 => LinuxFeatureInfoHwCap.HasFlag(LinuxFeatureFlagsHwCap.Crc32) || MacOsFeatureInfo.HasFlag(MacOsFeatureFlags.Crc32);
+        public static bool SupportsSha1 => LinuxFeatureInfoHwCap.HasFlag(LinuxFeatureFlagsHwCap.Sha1) || MacOsFeatureInfo.HasFlag(MacOsFeatureFlags.Sha1);
+        public static bool SupportsSha256 => LinuxFeatureInfoHwCap.HasFlag(LinuxFeatureFlagsHwCap.Sha2) || MacOsFeatureInfo.HasFlag(MacOsFeatureFlags.Sha256);
+    }
+}

ARMeilleure/CodeGen/Arm64/IntrinsicInfo.cs

@@ -0,0 +1,14 @@
+namespace ARMeilleure.CodeGen.Arm64
+{
+    struct IntrinsicInfo
+    {
+        public uint          Inst { get; }
+        public IntrinsicType Type { get; }
+
+        public IntrinsicInfo(uint inst, IntrinsicType type)
+        {
+            Inst = inst;
+            Type = type;
+        }
+    }
+}

ARMeilleure/CodeGen/Arm64/IntrinsicTable.cs

@@ -0,0 +1,461 @@
+using ARMeilleure.Common;
+using ARMeilleure.IntermediateRepresentation;
+
+namespace ARMeilleure.CodeGen.Arm64
+{
+    static class IntrinsicTable
+    {
+        private static IntrinsicInfo[] _intrinTable;
+
+        static IntrinsicTable()
+        {
+            _intrinTable = new IntrinsicInfo[EnumUtils.GetCount(typeof(Intrinsic))];
+
+            Add(Intrinsic.Arm64AbsS,          new IntrinsicInfo(0x5e20b800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64AbsV,          new IntrinsicInfo(0x0e20b800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64AddhnV,        new IntrinsicInfo(0x0e204000u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64AddpS,         new IntrinsicInfo(0x5e31b800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64AddpV,         new IntrinsicInfo(0x0e20bc00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64AddvV,         new IntrinsicInfo(0x0e31b800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64AddS,          new IntrinsicInfo(0x5e208400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64AddV,          new IntrinsicInfo(0x0e208400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64AesdV,         new IntrinsicInfo(0x4e285800u, IntrinsicType.Vector128Unary));
+            Add(Intrinsic.Arm64AeseV,         new IntrinsicInfo(0x4e284800u, IntrinsicType.Vector128Unary));
+            Add(Intrinsic.Arm64AesimcV,       new IntrinsicInfo(0x4e287800u, IntrinsicType.Vector128Unary));
+            Add(Intrinsic.Arm64AesmcV,        new IntrinsicInfo(0x4e286800u, IntrinsicType.Vector128Unary));
+            Add(Intrinsic.Arm64AndV,          new IntrinsicInfo(0x0e201c00u, IntrinsicType.VectorBinaryBitwise));
+            Add(Intrinsic.Arm64BicVi,         new IntrinsicInfo(0x2f001400u, IntrinsicType.VectorBinaryBitwiseImm));
+            Add(Intrinsic.Arm64BicV,          new IntrinsicInfo(0x0e601c00u, IntrinsicType.VectorBinaryBitwise));
+            Add(Intrinsic.Arm64BifV,          new IntrinsicInfo(0x2ee01c00u, IntrinsicType.VectorTernaryRdBitwise));
+            Add(Intrinsic.Arm64BitV,          new IntrinsicInfo(0x2ea01c00u, IntrinsicType.VectorTernaryRdBitwise));
+            Add(Intrinsic.Arm64BslV,          new IntrinsicInfo(0x2e601c00u, IntrinsicType.VectorTernaryRdBitwise));
+            Add(Intrinsic.Arm64ClsV,          new IntrinsicInfo(0x0e204800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64ClzV,          new IntrinsicInfo(0x2e204800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64CmeqS,         new IntrinsicInfo(0x7e208c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64CmeqV,         new IntrinsicInfo(0x2e208c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64CmeqSz,        new IntrinsicInfo(0x5e209800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64CmeqVz,        new IntrinsicInfo(0x0e209800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64CmgeS,         new IntrinsicInfo(0x5e203c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64CmgeV,         new IntrinsicInfo(0x0e203c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64CmgeSz,        new IntrinsicInfo(0x7e208800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64CmgeVz,        new IntrinsicInfo(0x2e208800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64CmgtS,         new IntrinsicInfo(0x5e203400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64CmgtV,         new IntrinsicInfo(0x0e203400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64CmgtSz,        new IntrinsicInfo(0x5e208800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64CmgtVz,        new IntrinsicInfo(0x0e208800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64CmhiS,         new IntrinsicInfo(0x7e203400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64CmhiV,         new IntrinsicInfo(0x2e203400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64CmhsS,         new IntrinsicInfo(0x7e203c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64CmhsV,         new IntrinsicInfo(0x2e203c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64CmleSz,        new IntrinsicInfo(0x7e209800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64CmleVz,        new IntrinsicInfo(0x2e209800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64CmltSz,        new IntrinsicInfo(0x5e20a800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64CmltVz,        new IntrinsicInfo(0x0e20a800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64CmtstS,        new IntrinsicInfo(0x5e208c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64CmtstV,        new IntrinsicInfo(0x0e208c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64CntV,          new IntrinsicInfo(0x0e205800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64DupSe,         new IntrinsicInfo(0x5e000400u, IntrinsicType.ScalarUnaryByElem));
+            Add(Intrinsic.Arm64DupVe,         new IntrinsicInfo(0x0e000400u, IntrinsicType.VectorUnaryByElem));
+            Add(Intrinsic.Arm64DupGp,         new IntrinsicInfo(0x0e000c00u, IntrinsicType.VectorUnaryByElem));
+            Add(Intrinsic.Arm64EorV,          new IntrinsicInfo(0x2e201c00u, IntrinsicType.VectorBinaryBitwise));
+            Add(Intrinsic.Arm64ExtV,          new IntrinsicInfo(0x2e000000u, IntrinsicType.VectorExt));
+            Add(Intrinsic.Arm64FabdS,         new IntrinsicInfo(0x7ea0d400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FabdV,         new IntrinsicInfo(0x2ea0d400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FabsV,         new IntrinsicInfo(0x0ea0f800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FabsS,         new IntrinsicInfo(0x1e20c000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FacgeS,        new IntrinsicInfo(0x7e20ec00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FacgeV,        new IntrinsicInfo(0x2e20ec00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FacgtS,        new IntrinsicInfo(0x7ea0ec00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FacgtV,        new IntrinsicInfo(0x2ea0ec00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FaddpS,        new IntrinsicInfo(0x7e30d800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FaddpV,        new IntrinsicInfo(0x2e20d400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FaddV,         new IntrinsicInfo(0x0e20d400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FaddS,         new IntrinsicInfo(0x1e202800u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FccmpeS,       new IntrinsicInfo(0x1e200410u, IntrinsicType.ScalarFPCompareCond));
+            Add(Intrinsic.Arm64FccmpS,        new IntrinsicInfo(0x1e200400u, IntrinsicType.ScalarFPCompareCond));
+            Add(Intrinsic.Arm64FcmeqS,        new IntrinsicInfo(0x5e20e400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FcmeqV,        new IntrinsicInfo(0x0e20e400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FcmeqSz,       new IntrinsicInfo(0x5ea0d800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcmeqVz,       new IntrinsicInfo(0x0ea0d800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcmgeS,        new IntrinsicInfo(0x7e20e400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FcmgeV,        new IntrinsicInfo(0x2e20e400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FcmgeSz,       new IntrinsicInfo(0x7ea0c800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcmgeVz,       new IntrinsicInfo(0x2ea0c800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcmgtS,        new IntrinsicInfo(0x7ea0e400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FcmgtV,        new IntrinsicInfo(0x2ea0e400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FcmgtSz,       new IntrinsicInfo(0x5ea0c800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcmgtVz,       new IntrinsicInfo(0x0ea0c800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcmleSz,       new IntrinsicInfo(0x7ea0d800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcmleVz,       new IntrinsicInfo(0x2ea0d800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcmltSz,       new IntrinsicInfo(0x5ea0e800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcmltVz,       new IntrinsicInfo(0x0ea0e800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcmpeS,        new IntrinsicInfo(0x1e202010u, IntrinsicType.ScalarFPCompare));
+            Add(Intrinsic.Arm64FcmpS,         new IntrinsicInfo(0x1e202000u, IntrinsicType.ScalarFPCompare));
+            Add(Intrinsic.Arm64FcselS,        new IntrinsicInfo(0x1e200c00u, IntrinsicType.ScalarFcsel));
+            Add(Intrinsic.Arm64FcvtasS,       new IntrinsicInfo(0x5e21c800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtasV,       new IntrinsicInfo(0x0e21c800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtasGp,      new IntrinsicInfo(0x1e240000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FcvtauS,       new IntrinsicInfo(0x7e21c800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtauV,       new IntrinsicInfo(0x2e21c800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtauGp,      new IntrinsicInfo(0x1e250000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FcvtlV,        new IntrinsicInfo(0x0e217800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtmsS,       new IntrinsicInfo(0x5e21b800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtmsV,       new IntrinsicInfo(0x0e21b800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtmsGp,      new IntrinsicInfo(0x1e300000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FcvtmuS,       new IntrinsicInfo(0x7e21b800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtmuV,       new IntrinsicInfo(0x2e21b800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtmuGp,      new IntrinsicInfo(0x1e310000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FcvtnsS,       new IntrinsicInfo(0x5e21a800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtnsV,       new IntrinsicInfo(0x0e21a800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtnsGp,      new IntrinsicInfo(0x1e200000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FcvtnuS,       new IntrinsicInfo(0x7e21a800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtnuV,       new IntrinsicInfo(0x2e21a800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtnuGp,      new IntrinsicInfo(0x1e210000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FcvtnV,        new IntrinsicInfo(0x0e216800u, IntrinsicType.VectorBinaryRd));
+            Add(Intrinsic.Arm64FcvtpsS,       new IntrinsicInfo(0x5ea1a800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtpsV,       new IntrinsicInfo(0x0ea1a800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtpsGp,      new IntrinsicInfo(0x1e280000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FcvtpuS,       new IntrinsicInfo(0x7ea1a800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtpuV,       new IntrinsicInfo(0x2ea1a800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtpuGp,      new IntrinsicInfo(0x1e290000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FcvtxnS,       new IntrinsicInfo(0x7e216800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtxnV,       new IntrinsicInfo(0x2e216800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtzsSFixed,  new IntrinsicInfo(0x5f00fc00u, IntrinsicType.ScalarFPConvFixed));
+            Add(Intrinsic.Arm64FcvtzsVFixed,  new IntrinsicInfo(0x0f00fc00u, IntrinsicType.VectorFPConvFixed));
+            Add(Intrinsic.Arm64FcvtzsS,       new IntrinsicInfo(0x5ea1b800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtzsV,       new IntrinsicInfo(0x0ea1b800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtzsGpFixed, new IntrinsicInfo(0x1e180000u, IntrinsicType.ScalarFPConvFixedGpr));
+            Add(Intrinsic.Arm64FcvtzsGp,      new IntrinsicInfo(0x1e380000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FcvtzuSFixed,  new IntrinsicInfo(0x7f00fc00u, IntrinsicType.ScalarFPConvFixed));
+            Add(Intrinsic.Arm64FcvtzuVFixed,  new IntrinsicInfo(0x2f00fc00u, IntrinsicType.VectorFPConvFixed));
+            Add(Intrinsic.Arm64FcvtzuS,       new IntrinsicInfo(0x7ea1b800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FcvtzuV,       new IntrinsicInfo(0x2ea1b800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FcvtzuGpFixed, new IntrinsicInfo(0x1e190000u, IntrinsicType.ScalarFPConvFixedGpr));
+            Add(Intrinsic.Arm64FcvtzuGp,      new IntrinsicInfo(0x1e390000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FcvtS,         new IntrinsicInfo(0x1e224000u, IntrinsicType.ScalarFPConv));
+            Add(Intrinsic.Arm64FdivV,         new IntrinsicInfo(0x2e20fc00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FdivS,         new IntrinsicInfo(0x1e201800u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FmaddS,        new IntrinsicInfo(0x1f000000u, IntrinsicType.ScalarTernary));
+            Add(Intrinsic.Arm64FmaxnmpS,      new IntrinsicInfo(0x7e30c800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FmaxnmpV,      new IntrinsicInfo(0x2e20c400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FmaxnmvV,      new IntrinsicInfo(0x2e30c800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FmaxnmV,       new IntrinsicInfo(0x0e20c400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FmaxnmS,       new IntrinsicInfo(0x1e206800u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FmaxpS,        new IntrinsicInfo(0x7e30f800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FmaxpV,        new IntrinsicInfo(0x2e20f400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FmaxvV,        new IntrinsicInfo(0x2e30f800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FmaxV,         new IntrinsicInfo(0x0e20f400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FmaxS,         new IntrinsicInfo(0x1e204800u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FminnmpS,      new IntrinsicInfo(0x7eb0c800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FminnmpV,      new IntrinsicInfo(0x2ea0c400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FminnmvV,      new IntrinsicInfo(0x2eb0c800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FminnmV,       new IntrinsicInfo(0x0ea0c400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FminnmS,       new IntrinsicInfo(0x1e207800u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FminpS,        new IntrinsicInfo(0x7eb0f800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FminpV,        new IntrinsicInfo(0x2ea0f400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FminvV,        new IntrinsicInfo(0x2eb0f800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FminV,         new IntrinsicInfo(0x0ea0f400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FminS,         new IntrinsicInfo(0x1e205800u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FmlaSe,        new IntrinsicInfo(0x5f801000u, IntrinsicType.ScalarTernaryFPRdByElem));
+            Add(Intrinsic.Arm64FmlaVe,        new IntrinsicInfo(0x0f801000u, IntrinsicType.VectorTernaryFPRdByElem));
+            Add(Intrinsic.Arm64FmlaV,         new IntrinsicInfo(0x0e20cc00u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64FmlsSe,        new IntrinsicInfo(0x5f805000u, IntrinsicType.ScalarTernaryFPRdByElem));
+            Add(Intrinsic.Arm64FmlsVe,        new IntrinsicInfo(0x0f805000u, IntrinsicType.VectorTernaryFPRdByElem));
+            Add(Intrinsic.Arm64FmlsV,         new IntrinsicInfo(0x0ea0cc00u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64FmovVi,        new IntrinsicInfo(0x0f00f400u, IntrinsicType.VectorFmovi));
+            Add(Intrinsic.Arm64FmovS,         new IntrinsicInfo(0x1e204000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FmovGp,        new IntrinsicInfo(0x1e260000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64FmovSi,        new IntrinsicInfo(0x1e201000u, IntrinsicType.ScalarFmovi));
+            Add(Intrinsic.Arm64FmsubS,        new IntrinsicInfo(0x1f008000u, IntrinsicType.ScalarTernary));
+            Add(Intrinsic.Arm64FmulxSe,       new IntrinsicInfo(0x7f809000u, IntrinsicType.ScalarBinaryFPByElem));
+            Add(Intrinsic.Arm64FmulxVe,       new IntrinsicInfo(0x2f809000u, IntrinsicType.VectorBinaryFPByElem));
+            Add(Intrinsic.Arm64FmulxS,        new IntrinsicInfo(0x5e20dc00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FmulxV,        new IntrinsicInfo(0x0e20dc00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FmulSe,        new IntrinsicInfo(0x5f809000u, IntrinsicType.ScalarBinaryFPByElem));
+            Add(Intrinsic.Arm64FmulVe,        new IntrinsicInfo(0x0f809000u, IntrinsicType.VectorBinaryFPByElem));
+            Add(Intrinsic.Arm64FmulV,         new IntrinsicInfo(0x2e20dc00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FmulS,         new IntrinsicInfo(0x1e200800u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FnegV,         new IntrinsicInfo(0x2ea0f800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FnegS,         new IntrinsicInfo(0x1e214000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FnmaddS,       new IntrinsicInfo(0x1f200000u, IntrinsicType.ScalarTernary));
+            Add(Intrinsic.Arm64FnmsubS,       new IntrinsicInfo(0x1f208000u, IntrinsicType.ScalarTernary));
+            Add(Intrinsic.Arm64FnmulS,        new IntrinsicInfo(0x1e208800u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FrecpeS,       new IntrinsicInfo(0x5ea1d800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FrecpeV,       new IntrinsicInfo(0x0ea1d800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FrecpsS,       new IntrinsicInfo(0x5e20fc00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FrecpsV,       new IntrinsicInfo(0x0e20fc00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FrecpxS,       new IntrinsicInfo(0x5ea1f800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FrintaV,       new IntrinsicInfo(0x2e218800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FrintaS,       new IntrinsicInfo(0x1e264000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FrintiV,       new IntrinsicInfo(0x2ea19800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FrintiS,       new IntrinsicInfo(0x1e27c000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FrintmV,       new IntrinsicInfo(0x0e219800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FrintmS,       new IntrinsicInfo(0x1e254000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FrintnV,       new IntrinsicInfo(0x0e218800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FrintnS,       new IntrinsicInfo(0x1e244000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FrintpV,       new IntrinsicInfo(0x0ea18800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FrintpS,       new IntrinsicInfo(0x1e24c000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FrintxV,       new IntrinsicInfo(0x2e219800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FrintxS,       new IntrinsicInfo(0x1e274000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FrintzV,       new IntrinsicInfo(0x0ea19800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FrintzS,       new IntrinsicInfo(0x1e25c000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FrsqrteS,      new IntrinsicInfo(0x7ea1d800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FrsqrteV,      new IntrinsicInfo(0x2ea1d800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FrsqrtsS,      new IntrinsicInfo(0x5ea0fc00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64FrsqrtsV,      new IntrinsicInfo(0x0ea0fc00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FsqrtV,        new IntrinsicInfo(0x2ea1f800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64FsqrtS,        new IntrinsicInfo(0x1e21c000u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64FsubV,         new IntrinsicInfo(0x0ea0d400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64FsubS,         new IntrinsicInfo(0x1e203800u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64InsVe,         new IntrinsicInfo(0x6e000400u, IntrinsicType.VectorInsertByElem));
+            Add(Intrinsic.Arm64InsGp,         new IntrinsicInfo(0x4e001c00u, IntrinsicType.ScalarUnaryByElem));
+            Add(Intrinsic.Arm64Ld1rV,         new IntrinsicInfo(0x0d40c000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64Ld1Vms,        new IntrinsicInfo(0x0c402000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64Ld1Vss,        new IntrinsicInfo(0x0d400000u, IntrinsicType.VectorLdStSs));
+            Add(Intrinsic.Arm64Ld2rV,         new IntrinsicInfo(0x0d60c000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64Ld2Vms,        new IntrinsicInfo(0x0c408000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64Ld2Vss,        new IntrinsicInfo(0x0d600000u, IntrinsicType.VectorLdStSs));
+            Add(Intrinsic.Arm64Ld3rV,         new IntrinsicInfo(0x0d40e000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64Ld3Vms,        new IntrinsicInfo(0x0c404000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64Ld3Vss,        new IntrinsicInfo(0x0d402000u, IntrinsicType.VectorLdStSs));
+            Add(Intrinsic.Arm64Ld4rV,         new IntrinsicInfo(0x0d60e000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64Ld4Vms,        new IntrinsicInfo(0x0c400000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64Ld4Vss,        new IntrinsicInfo(0x0d602000u, IntrinsicType.VectorLdStSs));
+            Add(Intrinsic.Arm64MlaVe,         new IntrinsicInfo(0x2f000000u, IntrinsicType.VectorTernaryRdByElem));
+            Add(Intrinsic.Arm64MlaV,          new IntrinsicInfo(0x0e209400u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64MlsVe,         new IntrinsicInfo(0x2f004000u, IntrinsicType.VectorTernaryRdByElem));
+            Add(Intrinsic.Arm64MlsV,          new IntrinsicInfo(0x2e209400u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64MoviV,         new IntrinsicInfo(0x0f000400u, IntrinsicType.VectorMovi));
+            Add(Intrinsic.Arm64MrsFpsr,       new IntrinsicInfo(0xd53b4420u, IntrinsicType.GetRegister));
+            Add(Intrinsic.Arm64MsrFpsr,       new IntrinsicInfo(0xd51b4420u, IntrinsicType.SetRegister));
+            Add(Intrinsic.Arm64MulVe,         new IntrinsicInfo(0x0f008000u, IntrinsicType.VectorBinaryByElem));
+            Add(Intrinsic.Arm64MulV,          new IntrinsicInfo(0x0e209c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64MvniV,         new IntrinsicInfo(0x2f000400u, IntrinsicType.VectorMvni));
+            Add(Intrinsic.Arm64NegS,          new IntrinsicInfo(0x7e20b800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64NegV,          new IntrinsicInfo(0x2e20b800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64NotV,          new IntrinsicInfo(0x2e205800u, IntrinsicType.VectorUnaryBitwise));
+            Add(Intrinsic.Arm64OrnV,          new IntrinsicInfo(0x0ee01c00u, IntrinsicType.VectorBinaryBitwise));
+            Add(Intrinsic.Arm64OrrVi,         new IntrinsicInfo(0x0f001400u, IntrinsicType.VectorBinaryBitwiseImm));
+            Add(Intrinsic.Arm64OrrV,          new IntrinsicInfo(0x0ea01c00u, IntrinsicType.VectorBinaryBitwise));
+            Add(Intrinsic.Arm64PmullV,        new IntrinsicInfo(0x0e20e000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64PmulV,         new IntrinsicInfo(0x2e209c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64RaddhnV,       new IntrinsicInfo(0x2e204000u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64RbitV,         new IntrinsicInfo(0x2e605800u, IntrinsicType.VectorUnaryBitwise));
+            Add(Intrinsic.Arm64Rev16V,        new IntrinsicInfo(0x0e201800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64Rev32V,        new IntrinsicInfo(0x2e200800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64Rev64V,        new IntrinsicInfo(0x0e200800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64RshrnV,        new IntrinsicInfo(0x0f008c00u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64RsubhnV,       new IntrinsicInfo(0x2e206000u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64SabalV,        new IntrinsicInfo(0x0e205000u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64SabaV,         new IntrinsicInfo(0x0e207c00u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64SabdlV,        new IntrinsicInfo(0x0e207000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SabdV,         new IntrinsicInfo(0x0e207400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SadalpV,       new IntrinsicInfo(0x0e206800u, IntrinsicType.VectorBinaryRd));
+            Add(Intrinsic.Arm64SaddlpV,       new IntrinsicInfo(0x0e202800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64SaddlvV,       new IntrinsicInfo(0x0e303800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64SaddlV,        new IntrinsicInfo(0x0e200000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SaddwV,        new IntrinsicInfo(0x0e201000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64ScvtfSFixed,   new IntrinsicInfo(0x5f00e400u, IntrinsicType.ScalarFPConvFixed));
+            Add(Intrinsic.Arm64ScvtfVFixed,   new IntrinsicInfo(0x0f00e400u, IntrinsicType.VectorFPConvFixed));
+            Add(Intrinsic.Arm64ScvtfS,        new IntrinsicInfo(0x5e21d800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64ScvtfV,        new IntrinsicInfo(0x0e21d800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64ScvtfGpFixed,  new IntrinsicInfo(0x1e020000u, IntrinsicType.ScalarFPConvFixedGpr));
+            Add(Intrinsic.Arm64ScvtfGp,       new IntrinsicInfo(0x1e220000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64Sha1cV,        new IntrinsicInfo(0x5e000000u, IntrinsicType.Vector128Binary));
+            Add(Intrinsic.Arm64Sha1hV,        new IntrinsicInfo(0x5e280800u, IntrinsicType.Vector128Unary));
+            Add(Intrinsic.Arm64Sha1mV,        new IntrinsicInfo(0x5e002000u, IntrinsicType.Vector128Binary));
+            Add(Intrinsic.Arm64Sha1pV,        new IntrinsicInfo(0x5e001000u, IntrinsicType.Vector128Binary));
+            Add(Intrinsic.Arm64Sha1su0V,      new IntrinsicInfo(0x5e003000u, IntrinsicType.Vector128Binary));
+            Add(Intrinsic.Arm64Sha1su1V,      new IntrinsicInfo(0x5e281800u, IntrinsicType.Vector128Unary));
+            Add(Intrinsic.Arm64Sha256h2V,     new IntrinsicInfo(0x5e005000u, IntrinsicType.Vector128Binary));
+            Add(Intrinsic.Arm64Sha256hV,      new IntrinsicInfo(0x5e004000u, IntrinsicType.Vector128Binary));
+            Add(Intrinsic.Arm64Sha256su0V,    new IntrinsicInfo(0x5e282800u, IntrinsicType.Vector128Unary));
+            Add(Intrinsic.Arm64Sha256su1V,    new IntrinsicInfo(0x5e006000u, IntrinsicType.Vector128Binary));
+            Add(Intrinsic.Arm64ShaddV,        new IntrinsicInfo(0x0e200400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64ShllV,         new IntrinsicInfo(0x2e213800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64ShlS,          new IntrinsicInfo(0x5f005400u, IntrinsicType.ScalarBinaryShl));
+            Add(Intrinsic.Arm64ShlV,          new IntrinsicInfo(0x0f005400u, IntrinsicType.VectorBinaryShl));
+            Add(Intrinsic.Arm64ShrnV,         new IntrinsicInfo(0x0f008400u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64ShsubV,        new IntrinsicInfo(0x0e202400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SliS,          new IntrinsicInfo(0x7f005400u, IntrinsicType.ScalarTernaryShlRd));
+            Add(Intrinsic.Arm64SliV,          new IntrinsicInfo(0x2f005400u, IntrinsicType.VectorTernaryShlRd));
+            Add(Intrinsic.Arm64SmaxpV,        new IntrinsicInfo(0x0e20a400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SmaxvV,        new IntrinsicInfo(0x0e30a800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64SmaxV,         new IntrinsicInfo(0x0e206400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SminpV,        new IntrinsicInfo(0x0e20ac00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SminvV,        new IntrinsicInfo(0x0e31a800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64SminV,         new IntrinsicInfo(0x0e206c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SmlalVe,       new IntrinsicInfo(0x0f002000u, IntrinsicType.VectorTernaryRdByElem));
+            Add(Intrinsic.Arm64SmlalV,        new IntrinsicInfo(0x0e208000u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64SmlslVe,       new IntrinsicInfo(0x0f006000u, IntrinsicType.VectorTernaryRdByElem));
+            Add(Intrinsic.Arm64SmlslV,        new IntrinsicInfo(0x0e20a000u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64SmovV,         new IntrinsicInfo(0x0e002c00u, IntrinsicType.VectorUnaryByElem));
+            Add(Intrinsic.Arm64SmullVe,       new IntrinsicInfo(0x0f00a000u, IntrinsicType.VectorBinaryByElem));
+            Add(Intrinsic.Arm64SmullV,        new IntrinsicInfo(0x0e20c000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SqabsS,        new IntrinsicInfo(0x5e207800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64SqabsV,        new IntrinsicInfo(0x0e207800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64SqaddS,        new IntrinsicInfo(0x5e200c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SqaddV,        new IntrinsicInfo(0x0e200c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SqdmlalSe,     new IntrinsicInfo(0x5f003000u, IntrinsicType.ScalarBinaryByElem));
+            Add(Intrinsic.Arm64SqdmlalVe,     new IntrinsicInfo(0x0f003000u, IntrinsicType.VectorBinaryByElem));
+            Add(Intrinsic.Arm64SqdmlalS,      new IntrinsicInfo(0x5e209000u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SqdmlalV,      new IntrinsicInfo(0x0e209000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SqdmlslSe,     new IntrinsicInfo(0x5f007000u, IntrinsicType.ScalarBinaryByElem));
+            Add(Intrinsic.Arm64SqdmlslVe,     new IntrinsicInfo(0x0f007000u, IntrinsicType.VectorBinaryByElem));
+            Add(Intrinsic.Arm64SqdmlslS,      new IntrinsicInfo(0x5e20b000u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SqdmlslV,      new IntrinsicInfo(0x0e20b000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SqdmulhSe,     new IntrinsicInfo(0x5f00c000u, IntrinsicType.ScalarBinaryByElem));
+            Add(Intrinsic.Arm64SqdmulhVe,     new IntrinsicInfo(0x0f00c000u, IntrinsicType.VectorBinaryByElem));
+            Add(Intrinsic.Arm64SqdmulhS,      new IntrinsicInfo(0x5e20b400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SqdmulhV,      new IntrinsicInfo(0x0e20b400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SqdmullSe,     new IntrinsicInfo(0x5f00b000u, IntrinsicType.ScalarBinaryByElem));
+            Add(Intrinsic.Arm64SqdmullVe,     new IntrinsicInfo(0x0f00b000u, IntrinsicType.VectorBinaryByElem));
+            Add(Intrinsic.Arm64SqdmullS,      new IntrinsicInfo(0x5e20d000u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SqdmullV,      new IntrinsicInfo(0x0e20d000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SqnegS,        new IntrinsicInfo(0x7e207800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64SqnegV,        new IntrinsicInfo(0x2e207800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64SqrdmulhSe,    new IntrinsicInfo(0x5f00d000u, IntrinsicType.ScalarBinaryByElem));
+            Add(Intrinsic.Arm64SqrdmulhVe,    new IntrinsicInfo(0x0f00d000u, IntrinsicType.VectorBinaryByElem));
+            Add(Intrinsic.Arm64SqrdmulhS,     new IntrinsicInfo(0x7e20b400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SqrdmulhV,     new IntrinsicInfo(0x2e20b400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SqrshlS,       new IntrinsicInfo(0x5e205c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SqrshlV,       new IntrinsicInfo(0x0e205c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SqrshrnS,      new IntrinsicInfo(0x5f009c00u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64SqrshrnV,      new IntrinsicInfo(0x0f009c00u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64SqrshrunS,     new IntrinsicInfo(0x7f008c00u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64SqrshrunV,     new IntrinsicInfo(0x2f008c00u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64SqshluS,       new IntrinsicInfo(0x7f006400u, IntrinsicType.ScalarBinaryShl));
+            Add(Intrinsic.Arm64SqshluV,       new IntrinsicInfo(0x2f006400u, IntrinsicType.VectorBinaryShl));
+            Add(Intrinsic.Arm64SqshlSi,       new IntrinsicInfo(0x5f007400u, IntrinsicType.ScalarBinaryShl));
+            Add(Intrinsic.Arm64SqshlVi,       new IntrinsicInfo(0x0f007400u, IntrinsicType.VectorBinaryShl));
+            Add(Intrinsic.Arm64SqshlS,        new IntrinsicInfo(0x5e204c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SqshlV,        new IntrinsicInfo(0x0e204c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SqshrnS,       new IntrinsicInfo(0x5f009400u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64SqshrnV,       new IntrinsicInfo(0x0f009400u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64SqshrunS,      new IntrinsicInfo(0x7f008400u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64SqshrunV,      new IntrinsicInfo(0x2f008400u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64SqsubS,        new IntrinsicInfo(0x5e202c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SqsubV,        new IntrinsicInfo(0x0e202c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SqxtnS,        new IntrinsicInfo(0x5e214800u, IntrinsicType.ScalarBinaryRd));
+            Add(Intrinsic.Arm64SqxtnV,        new IntrinsicInfo(0x0e214800u, IntrinsicType.VectorBinaryRd));
+            Add(Intrinsic.Arm64SqxtunS,       new IntrinsicInfo(0x7e212800u, IntrinsicType.ScalarBinaryRd));
+            Add(Intrinsic.Arm64SqxtunV,       new IntrinsicInfo(0x2e212800u, IntrinsicType.VectorBinaryRd));
+            Add(Intrinsic.Arm64SrhaddV,       new IntrinsicInfo(0x0e201400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SriS,          new IntrinsicInfo(0x7f004400u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64SriV,          new IntrinsicInfo(0x2f004400u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64SrshlS,        new IntrinsicInfo(0x5e205400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SrshlV,        new IntrinsicInfo(0x0e205400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SrshrS,        new IntrinsicInfo(0x5f002400u, IntrinsicType.ScalarBinaryShr));
+            Add(Intrinsic.Arm64SrshrV,        new IntrinsicInfo(0x0f002400u, IntrinsicType.VectorBinaryShr));
+            Add(Intrinsic.Arm64SrsraS,        new IntrinsicInfo(0x5f003400u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64SrsraV,        new IntrinsicInfo(0x0f003400u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64SshllV,        new IntrinsicInfo(0x0f00a400u, IntrinsicType.VectorBinaryShl));
+            Add(Intrinsic.Arm64SshlS,         new IntrinsicInfo(0x5e204400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SshlV,         new IntrinsicInfo(0x0e204400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SshrS,         new IntrinsicInfo(0x5f000400u, IntrinsicType.ScalarBinaryShr));
+            Add(Intrinsic.Arm64SshrV,         new IntrinsicInfo(0x0f000400u, IntrinsicType.VectorBinaryShr));
+            Add(Intrinsic.Arm64SsraS,         new IntrinsicInfo(0x5f001400u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64SsraV,         new IntrinsicInfo(0x0f001400u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64SsublV,        new IntrinsicInfo(0x0e202000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SsubwV,        new IntrinsicInfo(0x0e203000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64St1Vms,        new IntrinsicInfo(0x0c002000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64St1Vss,        new IntrinsicInfo(0x0d000000u, IntrinsicType.VectorLdStSs));
+            Add(Intrinsic.Arm64St2Vms,        new IntrinsicInfo(0x0c008000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64St2Vss,        new IntrinsicInfo(0x0d200000u, IntrinsicType.VectorLdStSs));
+            Add(Intrinsic.Arm64St3Vms,        new IntrinsicInfo(0x0c004000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64St3Vss,        new IntrinsicInfo(0x0d002000u, IntrinsicType.VectorLdStSs));
+            Add(Intrinsic.Arm64St4Vms,        new IntrinsicInfo(0x0c000000u, IntrinsicType.VectorLdSt));
+            Add(Intrinsic.Arm64St4Vss,        new IntrinsicInfo(0x0d202000u, IntrinsicType.VectorLdStSs));
+            Add(Intrinsic.Arm64SubhnV,        new IntrinsicInfo(0x0e206000u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64SubS,          new IntrinsicInfo(0x7e208400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64SubV,          new IntrinsicInfo(0x2e208400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64SuqaddS,       new IntrinsicInfo(0x5e203800u, IntrinsicType.ScalarBinaryRd));
+            Add(Intrinsic.Arm64SuqaddV,       new IntrinsicInfo(0x0e203800u, IntrinsicType.VectorBinaryRd));
+            Add(Intrinsic.Arm64TblV,          new IntrinsicInfo(0x0e000000u, IntrinsicType.VectorLookupTable));
+            Add(Intrinsic.Arm64TbxV,          new IntrinsicInfo(0x0e001000u, IntrinsicType.VectorLookupTable));
+            Add(Intrinsic.Arm64Trn1V,         new IntrinsicInfo(0x0e002800u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64Trn2V,         new IntrinsicInfo(0x0e006800u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UabalV,        new IntrinsicInfo(0x2e205000u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64UabaV,         new IntrinsicInfo(0x2e207c00u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64UabdlV,        new IntrinsicInfo(0x2e207000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UabdV,         new IntrinsicInfo(0x2e207400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UadalpV,       new IntrinsicInfo(0x2e206800u, IntrinsicType.VectorBinaryRd));
+            Add(Intrinsic.Arm64UaddlpV,       new IntrinsicInfo(0x2e202800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64UaddlvV,       new IntrinsicInfo(0x2e303800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64UaddlV,        new IntrinsicInfo(0x2e200000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UaddwV,        new IntrinsicInfo(0x2e201000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UcvtfSFixed,   new IntrinsicInfo(0x7f00e400u, IntrinsicType.ScalarFPConvFixed));
+            Add(Intrinsic.Arm64UcvtfVFixed,   new IntrinsicInfo(0x2f00e400u, IntrinsicType.VectorFPConvFixed));
+            Add(Intrinsic.Arm64UcvtfS,        new IntrinsicInfo(0x7e21d800u, IntrinsicType.ScalarUnary));
+            Add(Intrinsic.Arm64UcvtfV,        new IntrinsicInfo(0x2e21d800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64UcvtfGpFixed,  new IntrinsicInfo(0x1e030000u, IntrinsicType.ScalarFPConvFixedGpr));
+            Add(Intrinsic.Arm64UcvtfGp,       new IntrinsicInfo(0x1e230000u, IntrinsicType.ScalarFPConvGpr));
+            Add(Intrinsic.Arm64UhaddV,        new IntrinsicInfo(0x2e200400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UhsubV,        new IntrinsicInfo(0x2e202400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UmaxpV,        new IntrinsicInfo(0x2e20a400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UmaxvV,        new IntrinsicInfo(0x2e30a800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64UmaxV,         new IntrinsicInfo(0x2e206400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UminpV,        new IntrinsicInfo(0x2e20ac00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UminvV,        new IntrinsicInfo(0x2e31a800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64UminV,         new IntrinsicInfo(0x2e206c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UmlalVe,       new IntrinsicInfo(0x2f002000u, IntrinsicType.VectorTernaryRdByElem));
+            Add(Intrinsic.Arm64UmlalV,        new IntrinsicInfo(0x2e208000u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64UmlslVe,       new IntrinsicInfo(0x2f006000u, IntrinsicType.VectorTernaryRdByElem));
+            Add(Intrinsic.Arm64UmlslV,        new IntrinsicInfo(0x2e20a000u, IntrinsicType.VectorTernaryRd));
+            Add(Intrinsic.Arm64UmovV,         new IntrinsicInfo(0x0e003c00u, IntrinsicType.VectorUnaryByElem));
+            Add(Intrinsic.Arm64UmullVe,       new IntrinsicInfo(0x2f00a000u, IntrinsicType.VectorBinaryByElem));
+            Add(Intrinsic.Arm64UmullV,        new IntrinsicInfo(0x2e20c000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UqaddS,        new IntrinsicInfo(0x7e200c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64UqaddV,        new IntrinsicInfo(0x2e200c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UqrshlS,       new IntrinsicInfo(0x7e205c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64UqrshlV,       new IntrinsicInfo(0x2e205c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UqrshrnS,      new IntrinsicInfo(0x7f009c00u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64UqrshrnV,      new IntrinsicInfo(0x2f009c00u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64UqshlSi,       new IntrinsicInfo(0x7f007400u, IntrinsicType.ScalarBinaryShl));
+            Add(Intrinsic.Arm64UqshlVi,       new IntrinsicInfo(0x2f007400u, IntrinsicType.VectorBinaryShl));
+            Add(Intrinsic.Arm64UqshlS,        new IntrinsicInfo(0x7e204c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64UqshlV,        new IntrinsicInfo(0x2e204c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UqshrnS,       new IntrinsicInfo(0x7f009400u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64UqshrnV,       new IntrinsicInfo(0x2f009400u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64UqsubS,        new IntrinsicInfo(0x7e202c00u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64UqsubV,        new IntrinsicInfo(0x2e202c00u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UqxtnS,        new IntrinsicInfo(0x7e214800u, IntrinsicType.ScalarBinaryRd));
+            Add(Intrinsic.Arm64UqxtnV,        new IntrinsicInfo(0x2e214800u, IntrinsicType.VectorBinaryRd));
+            Add(Intrinsic.Arm64UrecpeV,       new IntrinsicInfo(0x0ea1c800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64UrhaddV,       new IntrinsicInfo(0x2e201400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UrshlS,        new IntrinsicInfo(0x7e205400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64UrshlV,        new IntrinsicInfo(0x2e205400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UrshrS,        new IntrinsicInfo(0x7f002400u, IntrinsicType.ScalarBinaryShr));
+            Add(Intrinsic.Arm64UrshrV,        new IntrinsicInfo(0x2f002400u, IntrinsicType.VectorBinaryShr));
+            Add(Intrinsic.Arm64UrsqrteV,      new IntrinsicInfo(0x2ea1c800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64UrsraS,        new IntrinsicInfo(0x7f003400u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64UrsraV,        new IntrinsicInfo(0x2f003400u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64UshllV,        new IntrinsicInfo(0x2f00a400u, IntrinsicType.VectorBinaryShl));
+            Add(Intrinsic.Arm64UshlS,         new IntrinsicInfo(0x7e204400u, IntrinsicType.ScalarBinary));
+            Add(Intrinsic.Arm64UshlV,         new IntrinsicInfo(0x2e204400u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UshrS,         new IntrinsicInfo(0x7f000400u, IntrinsicType.ScalarBinaryShr));
+            Add(Intrinsic.Arm64UshrV,         new IntrinsicInfo(0x2f000400u, IntrinsicType.VectorBinaryShr));
+            Add(Intrinsic.Arm64UsqaddS,       new IntrinsicInfo(0x7e203800u, IntrinsicType.ScalarBinaryRd));
+            Add(Intrinsic.Arm64UsqaddV,       new IntrinsicInfo(0x2e203800u, IntrinsicType.VectorBinaryRd));
+            Add(Intrinsic.Arm64UsraS,         new IntrinsicInfo(0x7f001400u, IntrinsicType.ScalarTernaryShrRd));
+            Add(Intrinsic.Arm64UsraV,         new IntrinsicInfo(0x2f001400u, IntrinsicType.VectorTernaryShrRd));
+            Add(Intrinsic.Arm64UsublV,        new IntrinsicInfo(0x2e202000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64UsubwV,        new IntrinsicInfo(0x2e203000u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64Uzp1V,         new IntrinsicInfo(0x0e001800u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64Uzp2V,         new IntrinsicInfo(0x0e005800u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64XtnV,          new IntrinsicInfo(0x0e212800u, IntrinsicType.VectorUnary));
+            Add(Intrinsic.Arm64Zip1V,         new IntrinsicInfo(0x0e003800u, IntrinsicType.VectorBinary));
+            Add(Intrinsic.Arm64Zip2V,         new IntrinsicInfo(0x0e007800u, IntrinsicType.VectorBinary));
+        }
+
+        private static void Add(Intrinsic intrin, IntrinsicInfo info)
+        {
+            _intrinTable[(int)intrin] = info;
+        }
+
+        public static IntrinsicInfo GetInfo(Intrinsic intrin)
+        {
+            return _intrinTable[(int)intrin];
+        }
+    }
+}

ARMeilleure/CodeGen/Arm64/IntrinsicType.cs

@@ -0,0 +1,59 @@
+namespace ARMeilleure.CodeGen.Arm64
+{
+    enum IntrinsicType
+    {
+        ScalarUnary,
+        ScalarUnaryByElem,
+        ScalarBinary,
+        ScalarBinaryByElem,
+        ScalarBinaryFPByElem,
+        ScalarBinaryRd,
+        ScalarBinaryShl,
+        ScalarBinaryShr,
+        ScalarFcsel,
+        ScalarFmovi,
+        ScalarFPCompare,
+        ScalarFPCompareCond,
+        ScalarFPConv,
+        ScalarFPConvFixed,
+        ScalarFPConvFixedGpr,
+        ScalarFPConvGpr,
+        ScalarTernary,
+        ScalarTernaryFPRdByElem,
+        ScalarTernaryShlRd,
+        ScalarTernaryShrRd,
+
+        VectorUnary,
+        VectorUnaryBitwise,
+        VectorUnaryByElem,
+        VectorBinary,
+        VectorBinaryBitwise,
+        VectorBinaryBitwiseImm,
+        VectorBinaryByElem,
+        VectorBinaryFPByElem,
+        VectorBinaryRd,
+        VectorBinaryShl,
+        VectorBinaryShr,
+        VectorExt,
+        VectorFmovi,
+        VectorFPConvFixed,
+        VectorInsertByElem,
+        VectorLdSt,
+        VectorLdStSs,
+        VectorLookupTable,
+        VectorMovi,
+        VectorMvni,
+        VectorTernaryFPRdByElem,
+        VectorTernaryRd,
+        VectorTernaryRdBitwise,
+        VectorTernaryRdByElem,
+        VectorTernaryShlRd,
+        VectorTernaryShrRd,
+
+        Vector128Unary,
+        Vector128Binary,
+
+        GetRegister,
+        SetRegister
+    }
+}

ARMeilleure/CodeGen/Arm64/PreAllocator.cs

@@ -0,0 +1,892 @@
+using ARMeilleure.CodeGen.RegisterAllocators;
+using ARMeilleure.IntermediateRepresentation;
+using ARMeilleure.Translation;
+using System;
+using System.Collections.Generic;
+using System.Diagnostics;
+using static ARMeilleure.IntermediateRepresentation.Operand.Factory;
+using static ARMeilleure.IntermediateRepresentation.Operation.Factory;
+
+namespace ARMeilleure.CodeGen.Arm64
+{
+    static class PreAllocator
+    {
+        private class ConstantDict
+        {
+            private readonly Dictionary<(ulong, OperandType), Operand> _constants;
+
+            public ConstantDict()
+            {
+                _constants = new Dictionary<(ulong, OperandType), Operand>();
+            }
+
+            public void Add(ulong value, OperandType type, Operand local)
+            {
+                _constants.Add((value, type), local);
+            }
+
+            public bool TryGetValue(ulong value, OperandType type, out Operand local)
+            {
+                return _constants.TryGetValue((value, type), out local);
+            }
+        }
+
+        public static void RunPass(CompilerContext cctx, StackAllocator stackAlloc, out int maxCallArgs)
+        {
+            maxCallArgs = -1;
+
+            Span<Operation> buffer = default;
+
+            Operand[] preservedArgs = new Operand[CallingConvention.GetArgumentsOnRegsCount()];
+
+            for (BasicBlock block = cctx.Cfg.Blocks.First; block != null; block = block.ListNext)
+            {
+                ConstantDict constants = new ConstantDict();
+
+                Operation nextNode;
+
+                for (Operation node = block.Operations.First; node != default; node = nextNode)
+                {
+                    nextNode = node.ListNext;
+
+                    if (node.Instruction == Instruction.Phi)
+                    {
+                        continue;
+                    }
+
+                    InsertConstantRegCopies(constants, block.Operations, node);
+                    InsertDestructiveRegCopies(block.Operations, node);
+
+                    switch (node.Instruction)
+                    {
+                        case Instruction.Call:
+                            // Get the maximum number of arguments used on a call.
+                            // On windows, when a struct is returned from the call,
+                            // we also need to pass the pointer where the struct
+                            // should be written on the first argument.
+                            int argsCount = node.SourcesCount - 1;
+
+                            if (node.Destination != default && node.Destination.Type == OperandType.V128)
+                            {
+                                argsCount++;
+                            }
+
+                            if (maxCallArgs < argsCount)
+                            {
+                                maxCallArgs = argsCount;
+                            }
+
+                            // Copy values to registers expected by the function
+                            // being called, as mandated by the ABI.
+                            InsertCallCopies(constants, block.Operations, node);
+                            break;
+                        case Instruction.CompareAndSwap:
+                        case Instruction.CompareAndSwap16:
+                        case Instruction.CompareAndSwap8:
+                            nextNode = GenerateCompareAndSwap(block.Operations, node);
+                            break;
+                        case Instruction.LoadArgument:
+                            nextNode = InsertLoadArgumentCopy(cctx, ref buffer, block.Operations, preservedArgs, node);
+                            break;
+                        case Instruction.Return:
+                            InsertReturnCopy(block.Operations, node);
+                            break;
+                        case Instruction.Tailcall:
+                            InsertTailcallCopies(constants, block.Operations, stackAlloc, node, node);
+                            break;
+                    }
+                }
+            }
+        }
+
+        private static void InsertConstantRegCopies(ConstantDict constants, IntrusiveList<Operation> nodes, Operation node)
+        {
+            if (node.SourcesCount == 0 || IsIntrinsicWithConst(node))
+            {
+                return;
+            }
+
+            Instruction inst = node.Instruction;
+
+            Operand src1 = node.GetSource(0);
+            Operand src2;
+
+            if (src1.Kind == OperandKind.Constant)
+            {
+                if (!src1.Type.IsInteger())
+                {
+                    // Handle non-integer types (FP32, FP64 and V128).
+                    // For instructions without an immediate operand, we do the following:
+                    // - Insert a copy with the constant value (as integer) to a GPR.
+                    // - Insert a copy from the GPR to a XMM register.
+                    // - Replace the constant use with the XMM register.
+                    src1 = AddFloatConstantCopy(constants, nodes, node, src1);
+
+                    node.SetSource(0, src1);
+                }
+                else if (!HasConstSrc1(node, src1.Value))
+                {
+                    // Handle integer types.
+                    // Most ALU instructions accepts a 32-bits immediate on the second operand.
+                    // We need to ensure the following:
+                    // - If the constant is on operand 1, we need to move it.
+                    // -- But first, we try to swap operand 1 and 2 if the instruction is commutative.
+                    // -- Doing so may allow us to encode the constant as operand 2 and avoid a copy.
+                    // - If the constant is on operand 2, we check if the instruction supports it,
+                    // if not, we also add a copy. 64-bits constants are usually not supported.
+                    if (IsCommutative(node))
+                    {
+                        src2 = node.GetSource(1);
+
+                        Operand temp = src1;
+
+                        src1 = src2;
+                        src2 = temp;
+
+                        node.SetSource(0, src1);
+                        node.SetSource(1, src2);
+                    }
+
+                    if (src1.Kind == OperandKind.Constant)
+                    {
+                        src1 = AddIntConstantCopy(constants, nodes, node, src1);
+
+                        node.SetSource(0, src1);
+                    }
+                }
+            }
+
+            if (node.SourcesCount < 2)
+            {
+                return;
+            }
+
+            src2 = node.GetSource(1);
+
+            if (src2.Kind == OperandKind.Constant)
+            {
+                if (!src2.Type.IsInteger())
+                {
+                    src2 = AddFloatConstantCopy(constants, nodes, node, src2);
+
+                    node.SetSource(1, src2);
+                }
+                else if (!HasConstSrc2(inst, src2))
+                {
+                    src2 = AddIntConstantCopy(constants, nodes, node, src2);
+
+                    node.SetSource(1, src2);
+                }
+            }
+
+            if (node.SourcesCount < 3 ||
+                node.Instruction == Instruction.BranchIf ||
+                node.Instruction == Instruction.Compare ||
+                node.Instruction == Instruction.VectorInsert ||
+                node.Instruction == Instruction.VectorInsert16 ||
+                node.Instruction == Instruction.VectorInsert8)
+            {
+                return;
+            }
+
+            for (int srcIndex = 2; srcIndex < node.SourcesCount; srcIndex++)
+            {
+                Operand src = node.GetSource(srcIndex);
+
+                if (src.Kind == OperandKind.Constant)
+                {
+                    if (!src.Type.IsInteger())
+                    {
+                        src = AddFloatConstantCopy(constants, nodes, node, src);
+
+                        node.SetSource(srcIndex, src);
+                    }
+                    else
+                    {
+                        src = AddIntConstantCopy(constants, nodes, node, src);
+
+                        node.SetSource(srcIndex, src);
+                    }
+                }
+            }
+        }
+
+        private static void InsertDestructiveRegCopies(IntrusiveList<Operation> nodes, Operation node)
+        {
+            if (node.Destination == default || node.SourcesCount == 0)
+            {
+                return;
+            }
+
+            Operand dest = node.Destination;
+            Operand src1 = node.GetSource(0);
+
+            if (IsSameOperandDestSrc1(node) && src1.Kind == OperandKind.LocalVariable)
+            {
+                bool useNewLocal = false;
+
+                for (int srcIndex = 1; srcIndex < node.SourcesCount; srcIndex++)
+                {
+                    if (node.GetSource(srcIndex) == dest)
+                    {
+                        useNewLocal = true;
+
+                        break;
+                    }
+                }
+
+                if (useNewLocal)
+                {
+                    // Dest is being used as some source already, we need to use a new
+                    // local to store the temporary value, otherwise the value on dest
+                    // local would be overwritten.
+                    Operand temp = Local(dest.Type);
+
+                    nodes.AddBefore(node, Operation(Instruction.Copy, temp, src1));
+
+                    node.SetSource(0, temp);
+
+                    nodes.AddAfter(node, Operation(Instruction.Copy, dest, temp));
+
+                    node.Destination = temp;
+                }
+                else
+                {
+                    nodes.AddBefore(node, Operation(Instruction.Copy, dest, src1));
+
+                    node.SetSource(0, dest);
+                }
+            }
+        }
+
+        private static void InsertCallCopies(ConstantDict constants, IntrusiveList<Operation> nodes, Operation node)
+        {
+            Operation operation = node;
+
+            Operand dest = operation.Destination;
+
+            List<Operand> sources = new List<Operand>
+            {
+                operation.GetSource(0)
+            };
+
+            int argsCount = operation.SourcesCount - 1;
+
+            int intMax = CallingConvention.GetArgumentsOnRegsCount();
+            int vecMax = CallingConvention.GetArgumentsOnRegsCount();
+
+            int intCount = 0;
+            int vecCount = 0;
+
+            int stackOffset = 0;
+
+            for (int index = 0; index < argsCount; index++)
+            {
+                Operand source = operation.GetSource(index + 1);
+
+                bool passOnReg;
+
+                if (source.Type.IsInteger())
+                {
+                    passOnReg = intCount < intMax;
+                }
+                else if (source.Type == OperandType.V128)
+                {
+                    passOnReg = intCount + 1 < intMax;
+                }
+                else
+                {
+                    passOnReg = vecCount < vecMax;
+                }
+
+                if (source.Type == OperandType.V128 && passOnReg)
+                {
+                    // V128 is a struct, we pass each half on a GPR if possible.
+                    Operand argReg  = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
+                    Operand argReg2 = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
+
+                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg,  source, Const(0)));
+                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg2, source, Const(1)));
+
+                    continue;
+                }
+
+                if (passOnReg)
+                {
+                    Operand argReg = source.Type.IsInteger()
+                        ? Gpr(CallingConvention.GetIntArgumentRegister(intCount++), source.Type)
+                        : Xmm(CallingConvention.GetVecArgumentRegister(vecCount++), source.Type);
+
+                    Operation copyOp = Operation(Instruction.Copy, argReg, source);
+
+                    InsertConstantRegCopies(constants, nodes, nodes.AddBefore(node, copyOp));
+
+                    sources.Add(argReg);
+                }
+                else
+                {
+                    Operand offset = Const(stackOffset);
+
+                    Operation spillOp = Operation(Instruction.SpillArg, default, offset, source);
+
+                    InsertConstantRegCopies(constants, nodes, nodes.AddBefore(node, spillOp));
+
+                    stackOffset += source.Type.GetSizeInBytes();
+                }
+            }
+
+            if (dest != default)
+            {
+                if (dest.Type == OperandType.V128)
+                {
+                    Operand retLReg = Gpr(CallingConvention.GetIntReturnRegister(),     OperandType.I64);
+                    Operand retHReg = Gpr(CallingConvention.GetIntReturnRegisterHigh(), OperandType.I64);
+
+                    node = nodes.AddAfter(node, Operation(Instruction.VectorCreateScalar, dest, retLReg));
+                    nodes.AddAfter(node, Operation(Instruction.VectorInsert, dest, dest, retHReg, Const(1)));
+
+                    operation.Destination = default;
+                }
+                else
+                {
+                    Operand retReg = dest.Type.IsInteger()
+                        ? Gpr(CallingConvention.GetIntReturnRegister(), dest.Type)
+                        : Xmm(CallingConvention.GetVecReturnRegister(), dest.Type);
+
+                    Operation copyOp = Operation(Instruction.Copy, dest, retReg);
+
+                    nodes.AddAfter(node, copyOp);
+
+                    operation.Destination = retReg;
+                }
+            }
+
+            operation.SetSources(sources.ToArray());
+        }
+
+        private static void InsertTailcallCopies(
+            ConstantDict constants,
+            IntrusiveList<Operation> nodes,
+            StackAllocator stackAlloc,
+            Operation node,
+            Operation operation)
+        {
+            List<Operand> sources = new List<Operand>
+            {
+                operation.GetSource(0)
+            };
+
+            int argsCount = operation.SourcesCount - 1;
+
+            int intMax = CallingConvention.GetArgumentsOnRegsCount();
+            int vecMax = CallingConvention.GetArgumentsOnRegsCount();
+
+            int intCount = 0;
+            int vecCount = 0;
+
+            // Handle arguments passed on registers.
+            for (int index = 0; index < argsCount; index++)
+            {
+                Operand source = operation.GetSource(1 + index);
+
+                bool passOnReg;
+
+                if (source.Type.IsInteger())
+                {
+                    passOnReg = intCount + 1 < intMax;
+                }
+                else
+                {
+                    passOnReg = vecCount < vecMax;
+                }
+
+                if (source.Type == OperandType.V128 && passOnReg)
+                {
+                    // V128 is a struct, we pass each half on a GPR if possible.
+                    Operand argReg  = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
+                    Operand argReg2 = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
+
+                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg, source, Const(0)));
+                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg2, source, Const(1)));
+
+                    continue;
+                }
+
+                if (passOnReg)
+                {
+                    Operand argReg = source.Type.IsInteger()
+                        ? Gpr(CallingConvention.GetIntArgumentRegister(intCount++), source.Type)
+                        : Xmm(CallingConvention.GetVecArgumentRegister(vecCount++), source.Type);
+
+                    Operation copyOp = Operation(Instruction.Copy, argReg, source);
+
+                    InsertConstantRegCopies(constants, nodes, nodes.AddBefore(node, copyOp));
+
+                    sources.Add(argReg);
+                }
+                else
+                {
+                    throw new NotImplementedException("Spilling is not currently supported for tail calls. (too many arguments)");
+                }
+            }
+
+            // The target address must be on the return registers, since we
+            // don't return anything and it is guaranteed to not be a
+            // callee saved register (which would be trashed on the epilogue).
+            Operand tcAddress = Gpr(CodeGenCommon.TcAddressRegister, OperandType.I64);
+
+            Operation addrCopyOp = Operation(Instruction.Copy, tcAddress, operation.GetSource(0));
+
+            nodes.AddBefore(node, addrCopyOp);
+
+            sources[0] = tcAddress;
+
+            operation.SetSources(sources.ToArray());
+        }
+
+        private static Operation GenerateCompareAndSwap(IntrusiveList<Operation> nodes, Operation node)
+        {
+            Operand expected = node.GetSource(1);
+
+            if (expected.Type == OperandType.V128)
+            {
+                Operand dest = node.Destination;
+                Operand expectedLow = Local(OperandType.I64);
+                Operand expectedHigh = Local(OperandType.I64);
+                Operand desiredLow = Local(OperandType.I64);
+                Operand desiredHigh = Local(OperandType.I64);
+                Operand actualLow = Local(OperandType.I64);
+                Operand actualHigh = Local(OperandType.I64);
+
+                Operand address = node.GetSource(0);
+                Operand desired = node.GetSource(2);
+
+                void SplitOperand(Operand source, Operand low, Operand high)
+                {
+                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, low, source, Const(0)));
+                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, high, source, Const(1)));
+                }
+
+                SplitOperand(expected, expectedLow, expectedHigh);
+                SplitOperand(desired, desiredLow, desiredHigh);
+
+                Operation operation = node;
+
+                // Update the sources and destinations with split 64-bit halfs of the whole 128-bit values.
+                // We also need a additional registers that will be used to store temporary information.
+                operation.SetDestinations(new[] { actualLow, actualHigh, Local(OperandType.I64), Local(OperandType.I64) });
+                operation.SetSources(new[] { address, expectedLow, expectedHigh, desiredLow, desiredHigh });
+
+                // Add some dummy uses of the input operands, as the CAS operation will be a loop,
+                // so they can't be used as destination operand.
+                for (int i = 0; i < operation.SourcesCount; i++)
+                {
+                    Operand src = operation.GetSource(i);
+                    node = nodes.AddAfter(node, Operation(Instruction.Copy, src, src));
+                }
+
+                // Assemble the vector with the 64-bit values at the given memory location.
+                node = nodes.AddAfter(node, Operation(Instruction.VectorCreateScalar, dest, actualLow));
+                node = nodes.AddAfter(node, Operation(Instruction.VectorInsert, dest, dest, actualHigh, Const(1)));
+            }
+            else
+            {
+                // We need a additional register where the store result will be written to.
+                node.SetDestinations(new[] { node.Destination, Local(OperandType.I32) });
+
+                // Add some dummy uses of the input operands, as the CAS operation will be a loop,
+                // so they can't be used as destination operand.
+                Operation operation = node;
+
+                for (int i = 0; i < operation.SourcesCount; i++)
+                {
+                    Operand src = operation.GetSource(i);
+                    node = nodes.AddAfter(node, Operation(Instruction.Copy, src, src));
+                }
+            }
+
+            return node.ListNext;
+        }
+
+        private static void InsertReturnCopy(IntrusiveList<Operation> nodes, Operation node)
+        {
+            if (node.SourcesCount == 0)
+            {
+                return;
+            }
+
+            Operand source = node.GetSource(0);
+
+            if (source.Type == OperandType.V128)
+            {
+                Operand retLReg = Gpr(CallingConvention.GetIntReturnRegister(),     OperandType.I64);
+                Operand retHReg = Gpr(CallingConvention.GetIntReturnRegisterHigh(), OperandType.I64);
+
+                nodes.AddBefore(node, Operation(Instruction.VectorExtract, retLReg, source, Const(0)));
+                nodes.AddBefore(node, Operation(Instruction.VectorExtract, retHReg, source, Const(1)));
+            }
+            else
+            {
+                Operand retReg = source.Type.IsInteger()
+                    ? Gpr(CallingConvention.GetIntReturnRegister(), source.Type)
+                    : Xmm(CallingConvention.GetVecReturnRegister(), source.Type);
+
+                Operation retCopyOp = Operation(Instruction.Copy, retReg, source);
+
+                nodes.AddBefore(node, retCopyOp);
+            }
+        }
+
+        private static Operation InsertLoadArgumentCopy(
+            CompilerContext cctx,
+            ref Span<Operation> buffer,
+            IntrusiveList<Operation> nodes,
+            Operand[] preservedArgs,
+            Operation node)
+        {
+            Operand source = node.GetSource(0);
+
+            Debug.Assert(source.Kind == OperandKind.Constant, "Non-constant LoadArgument source kind.");
+
+            int index = source.AsInt32();
+
+            int intCount = 0;
+            int vecCount = 0;
+
+            for (int cIndex = 0; cIndex < index; cIndex++)
+            {
+                OperandType argType = cctx.FuncArgTypes[cIndex];
+
+                if (argType.IsInteger())
+                {
+                    intCount++;
+                }
+                else if (argType == OperandType.V128)
+                {
+                    intCount += 2;
+                }
+                else
+                {
+                    vecCount++;
+                }
+            }
+
+            bool passOnReg;
+
+            if (source.Type.IsInteger())
+            {
+                passOnReg = intCount < CallingConvention.GetArgumentsOnRegsCount();
+            }
+            else if (source.Type == OperandType.V128)
+            {
+                passOnReg = intCount + 1 < CallingConvention.GetArgumentsOnRegsCount();
+            }
+            else
+            {
+                passOnReg = vecCount < CallingConvention.GetArgumentsOnRegsCount();
+            }
+
+            if (passOnReg)
+            {
+                Operand dest = node.Destination;
+
+                if (preservedArgs[index] == default)
+                {
+                    if (dest.Type == OperandType.V128)
+                    {
+                        // V128 is a struct, we pass each half on a GPR if possible.
+                        Operand pArg = Local(OperandType.V128);
+
+                        Operand argLReg = Gpr(CallingConvention.GetIntArgumentRegister(intCount), OperandType.I64);
+                        Operand argHReg = Gpr(CallingConvention.GetIntArgumentRegister(intCount + 1), OperandType.I64);
+
+                        Operation copyL = Operation(Instruction.VectorCreateScalar, pArg, argLReg);
+                        Operation copyH = Operation(Instruction.VectorInsert, pArg, pArg, argHReg, Const(1));
+
+                        cctx.Cfg.Entry.Operations.AddFirst(copyH);
+                        cctx.Cfg.Entry.Operations.AddFirst(copyL);
+
+                        preservedArgs[index] = pArg;
+                    }
+                    else
+                    {
+                        Operand pArg = Local(dest.Type);
+
+                        Operand argReg = dest.Type.IsInteger()
+                            ? Gpr(CallingConvention.GetIntArgumentRegister(intCount), dest.Type)
+                            : Xmm(CallingConvention.GetVecArgumentRegister(vecCount), dest.Type);
+
+                        Operation copyOp = Operation(Instruction.Copy, pArg, argReg);
+
+                        cctx.Cfg.Entry.Operations.AddFirst(copyOp);
+
+                        preservedArgs[index] = pArg;
+                    }
+                }
+
+                Operation nextNode;
+
+                if (dest.AssignmentsCount == 1)
+                {
+                    // Let's propagate the argument if we can to avoid copies.
+                    PreAllocatorCommon.Propagate(ref buffer, dest, preservedArgs[index]);
+                    nextNode = node.ListNext;
+                }
+                else
+                {
+                    Operation argCopyOp = Operation(Instruction.Copy, dest, preservedArgs[index]);
+                    nextNode = nodes.AddBefore(node, argCopyOp);
+                }
+
+                Delete(nodes, node);
+                return nextNode;
+            }
+            else
+            {
+                // TODO: Pass on stack.
+                return node;
+            }
+        }
+
+        private static Operand AddFloatConstantCopy(
+            ConstantDict constants,
+            IntrusiveList<Operation> nodes,
+            Operation node,
+            Operand source)
+        {
+            Operand temp = Local(source.Type);
+
+            Operand intConst = AddIntConstantCopy(constants, nodes, node, GetIntConst(source));
+
+            Operation copyOp = Operation(Instruction.VectorCreateScalar, temp, intConst);
+
+            nodes.AddBefore(node, copyOp);
+
+            return temp;
+        }
+
+        private static Operand AddIntConstantCopy(
+            ConstantDict constants,
+            IntrusiveList<Operation> nodes,
+            Operation node,
+            Operand source)
+        {
+            if (constants.TryGetValue(source.Value, source.Type, out Operand temp))
+            {
+                return temp;
+            }
+
+            temp = Local(source.Type);
+
+            Operation copyOp = Operation(Instruction.Copy, temp, source);
+
+            nodes.AddBefore(node, copyOp);
+
+            constants.Add(source.Value, source.Type, temp);
+
+            return temp;
+        }
+
+        private static Operand GetIntConst(Operand value)
+        {
+            if (value.Type == OperandType.FP32)
+            {
+                return Const(value.AsInt32());
+            }
+            else if (value.Type == OperandType.FP64)
+            {
+                return Const(value.AsInt64());
+            }
+
+            return value;
+        }
+
+        private static void Delete(IntrusiveList<Operation> nodes, Operation node)
+        {
+            node.Destination = default;
+
+            for (int index = 0; index < node.SourcesCount; index++)
+            {
+                node.SetSource(index, default);
+            }
+
+            nodes.Remove(node);
+        }
+
+        private static Operand Gpr(int register, OperandType type)
+        {
+            return Register(register, RegisterType.Integer, type);
+        }
+
+        private static Operand Xmm(int register, OperandType type)
+        {
+            return Register(register, RegisterType.Vector, type);
+        }
+
+        private static bool IsSameOperandDestSrc1(Operation operation)
+        {
+            switch (operation.Instruction)
+            {
+                case Instruction.Extended:
+                    return IsSameOperandDestSrc1(operation.Intrinsic);
+                case Instruction.VectorInsert:
+                case Instruction.VectorInsert16:
+                case Instruction.VectorInsert8:
+                    return true;
+            }
+
+            return false;
+        }
+
+        private static bool IsSameOperandDestSrc1(Intrinsic intrinsic)
+        {
+            IntrinsicInfo info = IntrinsicTable.GetInfo(intrinsic & ~(Intrinsic.Arm64VTypeMask | Intrinsic.Arm64VSizeMask));
+
+            return info.Type == IntrinsicType.ScalarBinaryRd ||
+                   info.Type == IntrinsicType.ScalarTernaryFPRdByElem ||
+                   info.Type == IntrinsicType.ScalarTernaryShlRd ||
+                   info.Type == IntrinsicType.ScalarTernaryShrRd ||
+                   info.Type == IntrinsicType.VectorBinaryRd ||
+                   info.Type == IntrinsicType.VectorInsertByElem ||
+                   info.Type == IntrinsicType.VectorTernaryRd ||
+                   info.Type == IntrinsicType.VectorTernaryRdBitwise ||
+                   info.Type == IntrinsicType.VectorTernaryFPRdByElem ||
+                   info.Type == IntrinsicType.VectorTernaryRdByElem ||
+                   info.Type == IntrinsicType.VectorTernaryShlRd ||
+                   info.Type == IntrinsicType.VectorTernaryShrRd;
+        }
+
+        private static bool HasConstSrc1(Operation node, ulong value)
+        {
+            switch (node.Instruction)
+            {
+                case Instruction.Add:
+                case Instruction.BranchIf:
+                case Instruction.Compare:
+                case Instruction.Subtract:
+                    // The immediate encoding of those instructions does not allow Rn to be
+                    // XZR (it will be SP instead), so we can't allow a Rn constant in this case.
+                    return value == 0 && NotConstOrConst0(node.GetSource(1));
+                case Instruction.BitwiseAnd:
+                case Instruction.BitwiseExclusiveOr:
+                case Instruction.BitwiseNot:
+                case Instruction.BitwiseOr:
+                case Instruction.ByteSwap:
+                case Instruction.CountLeadingZeros:
+                case Instruction.Multiply:
+                case Instruction.Negate:
+                case Instruction.RotateRight:
+                case Instruction.ShiftLeft:
+                case Instruction.ShiftRightSI:
+                case Instruction.ShiftRightUI:
+                    return value == 0;
+                case Instruction.Copy:
+                case Instruction.LoadArgument:
+                case Instruction.Spill:
+                case Instruction.SpillArg:
+                    return true;
+                case Instruction.Extended:
+                    return value == 0;
+            }
+
+            return false;
+        }
+
+        private static bool NotConstOrConst0(Operand operand)
+        {
+            return operand.Kind != OperandKind.Constant || operand.Value == 0;
+        }
+
+        private static bool HasConstSrc2(Instruction inst, Operand operand)
+        {
+            ulong value = operand.Value;
+
+            switch (inst)
+            {
+                case Instruction.Add:
+                case Instruction.BranchIf:
+                case Instruction.Compare:
+                case Instruction.Subtract:
+                    return ConstFitsOnUImm12Sh(value);
+                case Instruction.BitwiseAnd:
+                case Instruction.BitwiseExclusiveOr:
+                case Instruction.BitwiseOr:
+                    return value == 0 || CodeGenCommon.TryEncodeBitMask(operand, out _, out _, out _);
+                case Instruction.Multiply:
+                case Instruction.Store:
+                case Instruction.Store16:
+                case Instruction.Store8:
+                    return value == 0;
+                case Instruction.RotateRight:
+                case Instruction.ShiftLeft:
+                case Instruction.ShiftRightSI:
+                case Instruction.ShiftRightUI:
+                case Instruction.VectorExtract:
+                case Instruction.VectorExtract16:
+                case Instruction.VectorExtract8:
+                    return true;
+                case Instruction.Extended:
+                    // TODO: Check if actual intrinsic is supposed to have consts here?
+                    // Right now we only hit this case for fixed-point int <-> FP conversion instructions.
+                    return true;
+            }
+
+            return false;
+        }
+
+        private static bool IsCommutative(Operation operation)
+        {
+            switch (operation.Instruction)
+            {
+                case Instruction.Add:
+                case Instruction.BitwiseAnd:
+                case Instruction.BitwiseExclusiveOr:
+                case Instruction.BitwiseOr:
+                case Instruction.Multiply:
+                    return true;
+
+                case Instruction.BranchIf:
+                case Instruction.Compare:
+                    {
+                        Operand comp = operation.GetSource(2);
+
+                        Debug.Assert(comp.Kind == OperandKind.Constant);
+
+                        var compType = (Comparison)comp.AsInt32();
+
+                        return compType == Comparison.Equal || compType == Comparison.NotEqual;
+                    }
+            }
+
+            return false;
+        }
+
+        private static bool ConstFitsOnUImm12Sh(ulong value)
+        {
+            return (value & ~0xfffUL) == 0 || (value & ~0xfff000UL) == 0;
+        }
+
+        private static bool IsIntrinsicWithConst(Operation operation)
+        {
+            bool isIntrinsic = IsIntrinsic(operation.Instruction);
+
+            if (isIntrinsic)
+            {
+                Intrinsic intrinsic = operation.Intrinsic;
+                IntrinsicInfo info = IntrinsicTable.GetInfo(intrinsic & ~(Intrinsic.Arm64VTypeMask | Intrinsic.Arm64VSizeMask));
+
+                // Those have integer inputs that don't support consts.
+                return info.Type != IntrinsicType.ScalarFPConvGpr &&
+                       info.Type != IntrinsicType.ScalarFPConvFixedGpr &&
+                       info.Type != IntrinsicType.SetRegister;
+            }
+
+            return false;
+        }
+
+        private static bool IsIntrinsic(Instruction inst)
+        {
+            return inst == Instruction.Extended;
+        }
+    }
+}

ARMeilleure/CodeGen/CompiledFunction.cs

@@ -48,9 +48,21 @@ namespace ARMeilleure.CodeGen
         /// <returns>A delegate of type <typeparamref name="T"/> pointing to the mapped function</returns>
         public T Map<T>()
         {
-            IntPtr codePtr = JitCache.Map(this);
+            return MapWithPointer<T>(out _);
+        }
 
-            return Marshal.GetDelegateForFunctionPointer<T>(codePtr);
+        /// <summary>
+        /// Maps the <see cref="CompiledFunction"/> onto the <see cref="JitCache"/> and returns a delegate of type
+        /// <typeparamref name="T"/> pointing to the mapped function.
+        /// </summary>
+        /// <typeparam name="T">Type of delegate</typeparam>
+        /// <param name="codePointer">Pointer to the function code in memory</param>
+        /// <returns>A delegate of type <typeparamref name="T"/> pointing to the mapped function</returns>
+        public T MapWithPointer<T>(out IntPtr codePointer)
+        {
+            codePointer = JitCache.Map(this);
+
+            return Marshal.GetDelegateForFunctionPointer<T>(codePointer);
         }
     }
 }

ARMeilleure/CodeGen/Linking/Symbol.cs

@@ -58,7 +58,6 @@ namespace ARMeilleure.CodeGen.Linking
         /// <param name="a">First instance</param>
         /// <param name="b">Second instance</param>
         /// <returns><see langword="true"/> if not equal; otherwise <see langword="false"/></returns>
-        /// <inheritdoc/>
         public static bool operator !=(Symbol a, Symbol b)
         {
             return !(a == b);

ARMeilleure/CodeGen/Optimizations/ConstantFolding.cs

@@ -90,6 +90,47 @@ namespace ARMeilleure.CodeGen.Optimizations
                     }
                     break;
 
+                case Instruction.Compare:
+                    if (type == OperandType.I32 &&
+                        operation.GetSource(0).Type == type &&
+                        operation.GetSource(1).Type == type)
+                    {
+                        switch ((Comparison)operation.GetSource(2).Value)
+                        {
+                            case Comparison.Equal:
+                                EvaluateBinaryI32(operation, (x, y) => x == y ? 1 : 0);
+                                break;
+                            case Comparison.NotEqual:
+                                EvaluateBinaryI32(operation, (x, y) => x != y ? 1 : 0);
+                                break;
+                            case Comparison.Greater:
+                                EvaluateBinaryI32(operation, (x, y) => x > y ? 1 : 0);
+                                break;
+                            case Comparison.LessOrEqual:
+                                EvaluateBinaryI32(operation, (x, y) => x <= y ? 1 : 0);
+                                break;
+                            case Comparison.GreaterUI:
+                                EvaluateBinaryI32(operation, (x, y) => (uint)x > (uint)y ? 1 : 0);
+                                break;
+                            case Comparison.LessOrEqualUI:
+                                EvaluateBinaryI32(operation, (x, y) => (uint)x <= (uint)y ? 1 : 0);
+                                break;
+                            case Comparison.GreaterOrEqual:
+                                EvaluateBinaryI32(operation, (x, y) => x >= y ? 1 : 0);
+                                break;
+                            case Comparison.Less:
+                                EvaluateBinaryI32(operation, (x, y) => x < y ? 1 : 0);
+                                break;
+                            case Comparison.GreaterOrEqualUI:
+                                EvaluateBinaryI32(operation, (x, y) => (uint)x >= (uint)y ? 1 : 0);
+                                break;
+                            case Comparison.LessUI:
+                                EvaluateBinaryI32(operation, (x, y) => (uint)x < (uint)y ? 1 : 0);
+                                break;
+                        }
+                    }
+                    break;
+
                 case Instruction.Copy:
                     if (type == OperandType.I32)
                     {

ARMeilleure/CodeGen/Optimizations/Optimizer.cs

@@ -44,8 +44,8 @@ namespace ARMeilleure.CodeGen.Optimizations
                         ConstantFolding.RunPass(node);
                         Simplification.RunPass(node);
 
-                        if (DestIsLocalVar(node))
-                        {   
+                        if (DestIsSingleLocalVar(node))
+                        {
                             if (IsPropagableCompare(node))
                             {
                                 modified |= PropagateCompare(ref buffer, node);
@@ -99,20 +99,6 @@ namespace ARMeilleure.CodeGen.Optimizations
             while (modified);
         }
 
-        private static Span<Operation> GetUses(ref Span<Operation> buffer, Operand operand)
-        {
-            ReadOnlySpan<Operation> uses = operand.Uses;
-
-            if (buffer.Length < uses.Length)
-            {
-                buffer = Allocators.Default.AllocateSpan<Operation>((uint)uses.Length);
-            }
-
-            uses.CopyTo(buffer);
-
-            return buffer.Slice(0, uses.Length);
-        }
-
         private static bool PropagateCompare(ref Span<Operation> buffer, Operation compOp)
         {
             // Try to propagate Compare operations into their BranchIf uses, when these BranchIf uses are in the form
@@ -160,7 +146,7 @@ namespace ARMeilleure.CodeGen.Optimizations
 
             Comparison compType = (Comparison)comp.AsInt32();
 
-            Span<Operation> uses = GetUses(ref buffer, dest);
+            Span<Operation> uses = dest.GetUses(ref buffer);
 
             foreach (Operation use in uses)
             {
@@ -199,7 +185,7 @@ namespace ARMeilleure.CodeGen.Optimizations
             Operand dest   = copyOp.Destination;
             Operand source = copyOp.GetSource(0);
 
-            Span<Operation> uses = GetUses(ref buffer, dest);
+            Span<Operation> uses = dest.GetUses(ref buffer);
 
             foreach (Operation use in uses)
             {
@@ -231,12 +217,12 @@ namespace ARMeilleure.CodeGen.Optimizations
 
         private static bool IsUnused(Operation node)
         {
-            return DestIsLocalVar(node) && node.Destination.UsesCount == 0 && !HasSideEffects(node);
+            return DestIsSingleLocalVar(node) && node.Destination.UsesCount == 0 && !HasSideEffects(node);
         }
 
-        private static bool DestIsLocalVar(Operation node)
+        private static bool DestIsSingleLocalVar(Operation node)
         {
-            return node.Destination != default && node.Destination.Kind == OperandKind.LocalVariable;
+            return node.DestinationsCount == 1 && node.Destination.Kind == OperandKind.LocalVariable;
         }
 
         private static bool HasSideEffects(Operation node)

ARMeilleure/CodeGen/PreAllocatorCommon.cs

@@ -0,0 +1,57 @@
+using ARMeilleure.IntermediateRepresentation;
+using System;
+using static ARMeilleure.IntermediateRepresentation.Operand.Factory;
+
+namespace ARMeilleure.CodeGen
+{
+    static class PreAllocatorCommon
+    {
+        public static void Propagate(ref Span<Operation> buffer, Operand dest, Operand value)
+        {
+            ReadOnlySpan<Operation> uses = dest.GetUses(ref buffer);
+
+            foreach (Operation use in uses)
+            {
+                for (int srcIndex = 0; srcIndex < use.SourcesCount; srcIndex++)
+                {
+                    Operand useSrc = use.GetSource(srcIndex);
+
+                    if (useSrc == dest)
+                    {
+                        use.SetSource(srcIndex, value);
+                    }
+                    else if (useSrc.Kind == OperandKind.Memory)
+                    {
+                        MemoryOperand memoryOp = useSrc.GetMemory();
+
+                        Operand baseAddr = memoryOp.BaseAddress;
+                        Operand index = memoryOp.Index;
+                        bool changed = false;
+
+                        if (baseAddr == dest)
+                        {
+                            baseAddr = value;
+                            changed = true;
+                        }
+
+                        if (index == dest)
+                        {
+                            index = value;
+                            changed = true;
+                        }
+
+                        if (changed)
+                        {
+                            use.SetSource(srcIndex, MemoryOp(
+                                useSrc.Type,
+                                baseAddr,
+                                index,
+                                memoryOp.Scale,
+                                memoryOp.Displacement));
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

ARMeilleure/CodeGen/RegisterAllocators/AllocationResult.cs

@@ -1,6 +1,6 @@
 namespace ARMeilleure.CodeGen.RegisterAllocators
 {
-    struct AllocationResult
+    readonly struct AllocationResult
     {
         public int IntUsedRegisters { get; }
         public int VecUsedRegisters { get; }

ARMeilleure/CodeGen/RegisterAllocators/CopyResolver.cs

@@ -11,7 +11,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
     {
         private class ParallelCopy
         {
-            private struct Copy
+            private readonly struct Copy
             {
                 public Register Dest   { get; }
                 public Register Source { get; }

ARMeilleure/CodeGen/RegisterAllocators/HybridAllocator.cs

@@ -11,7 +11,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
 {
     class HybridAllocator : IRegisterAllocator
     {
-        private struct BlockInfo
+        private readonly struct BlockInfo
         {
             public bool HasCall { get; }
 

ARMeilleure/CodeGen/RegisterAllocators/LinearScanAllocator.cs

@@ -17,8 +17,6 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
         private const int InstructionGap     = 2;
         private const int InstructionGapMask = InstructionGap - 1;
 
-        private const int RegistersCount = 16;
-
         private HashSet<int> _blockEdges;
         private LiveRange[] _blockRanges;
         private BitMap[] _blockLiveIn;
@@ -59,7 +57,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
 
                 void PopulateFreePositions(RegisterType type, out int[] positions, out int count)
                 {
-                    positions = new int[RegistersCount];
+                    positions = new int[masks.RegistersCount];
                     count = BitOperations.PopCount((uint)masks.GetAvailableRegisters(type));
 
                     int mask = masks.GetAvailableRegisters(type);
@@ -115,7 +113,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             StackAllocator stackAlloc,
             RegisterMasks regMasks)
         {
-            NumberLocals(cfg);
+            NumberLocals(cfg, regMasks.RegistersCount);
 
             var context = new AllocationContext(stackAlloc, regMasks, _intervals.Count);
 
@@ -134,22 +132,25 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
                 {
                     context.Active.Set(index);
 
-                    if (current.Register.Type == RegisterType.Integer)
+                    if (current.IsFixedAndUsed)
                     {
-                        context.IntUsedRegisters |= 1 << current.Register.Index;
-                    }
-                    else /* if (interval.Register.Type == RegisterType.Vector) */
-                    {
-                        context.VecUsedRegisters |= 1 << current.Register.Index;
+                        if (current.Register.Type == RegisterType.Integer)
+                        {
+                            context.IntUsedRegisters |= 1 << current.Register.Index;
+                        }
+                        else /* if (interval.Register.Type == RegisterType.Vector) */
+                        {
+                            context.VecUsedRegisters |= 1 << current.Register.Index;
+                        }
                     }
 
                     continue;
                 }
 
-                AllocateInterval(context, current, index);
+                AllocateInterval(context, current, index, regMasks.RegistersCount);
             }
 
-            for (int index = RegistersCount * 2; index < _intervals.Count; index++)
+            for (int index = regMasks.RegistersCount * 2; index < _intervals.Count; index++)
             {
                 if (!_intervals[index].IsSpilled)
                 {
@@ -163,7 +164,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             return new AllocationResult(context.IntUsedRegisters, context.VecUsedRegisters, context.StackAlloc.TotalSize);
         }
 
-        private void AllocateInterval(AllocationContext context, LiveInterval current, int cIndex)
+        private void AllocateInterval(AllocationContext context, LiveInterval current, int cIndex, int registersCount)
         {
             // Check active intervals that already ended.
             foreach (int iIndex in context.Active)
@@ -199,17 +200,17 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
                 }
             }
 
-            if (!TryAllocateRegWithoutSpill(context, current, cIndex))
+            if (!TryAllocateRegWithoutSpill(context, current, cIndex, registersCount))
             {
-                AllocateRegWithSpill(context, current, cIndex);
+                AllocateRegWithSpill(context, current, cIndex, registersCount);
             }
         }
 
-        private bool TryAllocateRegWithoutSpill(AllocationContext context, LiveInterval current, int cIndex)
+        private bool TryAllocateRegWithoutSpill(AllocationContext context, LiveInterval current, int cIndex, int registersCount)
         {
             RegisterType regType = current.Local.Type.ToRegisterType();
 
-            Span<int> freePositions = stackalloc int[RegistersCount];
+            Span<int> freePositions = stackalloc int[registersCount];
 
             context.GetFreePositions(regType, freePositions, out int freePositionsCount);
 
@@ -278,7 +279,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
                 {
                     Debug.Assert(splitChild.GetStart() > current.GetStart(), "Split interval has an invalid start position.");
 
-                    InsertInterval(splitChild);
+                    InsertInterval(splitChild, registersCount);
                 }
                 else
                 {
@@ -302,12 +303,12 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             return true;
         }
 
-        private void AllocateRegWithSpill(AllocationContext context, LiveInterval current, int cIndex)
+        private void AllocateRegWithSpill(AllocationContext context, LiveInterval current, int cIndex, int registersCount)
         {
             RegisterType regType = current.Local.Type.ToRegisterType();
 
-            Span<int> usePositions = stackalloc int[RegistersCount];
-            Span<int> blockedPositions = stackalloc int[RegistersCount];
+            Span<int> usePositions = stackalloc int[registersCount];
+            Span<int> blockedPositions = stackalloc int[registersCount];
 
             context.GetFreePositions(regType, usePositions, out _);
             context.GetFreePositions(regType, blockedPositions, out _);
@@ -386,7 +387,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
 
                 Debug.Assert(splitChild.GetStart() > current.GetStart(), "Split interval has an invalid start position.");
 
-                InsertInterval(splitChild);
+                InsertInterval(splitChild, registersCount);
 
                 Spill(context, current);
             }
@@ -396,7 +397,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
                 // so we only need to split the intervals using the selected register.
                 current.Register = new Register(selectedReg, regType);
 
-                SplitAndSpillOverlappingIntervals(context, current);
+                SplitAndSpillOverlappingIntervals(context, current, registersCount);
 
                 context.Active.Set(cIndex);
             }
@@ -417,14 +418,14 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
                 {
                     Debug.Assert(splitChild.GetStart() > current.GetStart(), "Split interval has an invalid start position.");
 
-                    InsertInterval(splitChild);
+                    InsertInterval(splitChild, registersCount);
                 }
                 else
                 {
                     Spill(context, splitChild);
                 }
 
-                SplitAndSpillOverlappingIntervals(context, current);
+                SplitAndSpillOverlappingIntervals(context, current, registersCount);
 
                 context.Active.Set(cIndex);
             }
@@ -432,16 +433,11 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
 
         private static int GetHighestValueIndex(Span<int> span)
         {
-            int highest = span[0];
-
-            if (highest == int.MaxValue)
-            {
-                return 0;
-            }
+            int highest = int.MinValue;
 
             int selected = 0;
 
-            for (int index = 1; index < span.Length; index++)
+            for (int index = 0; index < span.Length; index++)
             {
                 int current = span[index];
 
@@ -460,7 +456,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             return selected;
         }
 
-        private void SplitAndSpillOverlappingIntervals(AllocationContext context, LiveInterval current)
+        private void SplitAndSpillOverlappingIntervals(AllocationContext context, LiveInterval current, int registersCount)
         {
             foreach (int iIndex in context.Active)
             {
@@ -468,7 +464,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
 
                 if (!interval.IsFixed && interval.Register == current.Register)
                 {
-                    SplitAndSpillOverlappingInterval(context, current, interval);
+                    SplitAndSpillOverlappingInterval(context, current, interval, registersCount);
 
                     context.Active.Clear(iIndex);
                 }
@@ -480,7 +476,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
 
                 if (!interval.IsFixed && interval.Register == current.Register && interval.Overlaps(current))
                 {
-                    SplitAndSpillOverlappingInterval(context, current, interval);
+                    SplitAndSpillOverlappingInterval(context, current, interval, registersCount);
 
                     context.Inactive.Clear(iIndex);
                 }
@@ -490,7 +486,8 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
         private void SplitAndSpillOverlappingInterval(
             AllocationContext context,
             LiveInterval      current,
-            LiveInterval      interval)
+            LiveInterval      interval,
+            int               registersCount)
         {
             // If there's a next use after the start of the current interval,
             // we need to split the spilled interval twice, and re-insert it
@@ -522,7 +519,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
                     splitChild = right;
                 }
 
-                InsertInterval(splitChild);
+                InsertInterval(splitChild, registersCount);
             }
             else
             {
@@ -530,13 +527,13 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             }
         }
 
-        private void InsertInterval(LiveInterval interval)
+        private void InsertInterval(LiveInterval interval, int registersCount)
         {
             Debug.Assert(interval.UsesCount != 0, "Trying to insert a interval without uses.");
             Debug.Assert(!interval.IsEmpty,       "Trying to insert a empty interval.");
             Debug.Assert(!interval.IsSpilled,     "Trying to insert a spilled interval.");
 
-            int startIndex = RegistersCount * 2;
+            int startIndex = registersCount * 2;
 
             int insertIndex = _intervals.BinarySearch(startIndex, _intervals.Count - startIndex, interval, null);
 
@@ -790,12 +787,12 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             return _operationNodes[position / InstructionGap];
         }
 
-        private void NumberLocals(ControlFlowGraph cfg)
+        private void NumberLocals(ControlFlowGraph cfg, int registersCount)
         {
             _operationNodes = new List<(IntrusiveList<Operation>, Operation)>();
             _intervals = new List<LiveInterval>();
 
-            for (int index = 0; index < RegistersCount; index++)
+            for (int index = 0; index < registersCount; index++)
             {
                 _intervals.Add(new LiveInterval(new Register(index, RegisterType.Integer)));
                 _intervals.Add(new LiveInterval(new Register(index, RegisterType.Vector)));
@@ -1041,6 +1038,11 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
                     {
                         LiveInterval interval = _intervals[GetOperandId(dest)];
 
+                        if (interval.IsFixed)
+                        {
+                            interval.IsFixedAndUsed = true;
+                        }
+
                         interval.SetStart(operationPos + 1);
                         interval.AddUsePosition(operationPos + 1);
                     }

ARMeilleure/CodeGen/RegisterAllocators/LiveInterval.cs

@@ -27,6 +27,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             public Register Register;
 
             public bool IsFixed;
+            public bool IsFixedAndUsed;
         }
 
         private readonly Data* _data;
@@ -44,6 +45,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
         public ref int SpillOffset => ref _data->SpillOffset;
 
         public bool IsFixed => _data->IsFixed;
+        public ref bool IsFixedAndUsed => ref _data->IsFixedAndUsed;
         public bool IsEmpty => FirstRange == default;
         public bool IsSplit => Children.Count != 0;
         public bool IsSpilled => SpillOffset != -1;
@@ -114,7 +116,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             }
             else
             {
-                FirstRange = new LiveRange(position, position + 1); 
+                FirstRange = new LiveRange(position, position + 1);
                 End = position + 1;
             }
         }

ARMeilleure/CodeGen/RegisterAllocators/RegisterMasks.cs

@@ -3,7 +3,7 @@ using System;
 
 namespace ARMeilleure.CodeGen.RegisterAllocators
 {
-    struct RegisterMasks
+    readonly struct RegisterMasks
     {
         public int IntAvailableRegisters   { get; }
         public int VecAvailableRegisters   { get; }
@@ -11,6 +11,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
         public int VecCallerSavedRegisters { get; }
         public int IntCalleeSavedRegisters { get; }
         public int VecCalleeSavedRegisters { get; }
+        public int RegistersCount { get; }
 
         public RegisterMasks(
             int intAvailableRegisters,
@@ -18,7 +19,8 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             int intCallerSavedRegisters,
             int vecCallerSavedRegisters,
             int intCalleeSavedRegisters,
-            int vecCalleeSavedRegisters)
+            int vecCalleeSavedRegisters,
+            int registersCount)
         {
             IntAvailableRegisters   = intAvailableRegisters;
             VecAvailableRegisters   = vecAvailableRegisters;
@@ -26,6 +28,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             VecCallerSavedRegisters = vecCallerSavedRegisters;
             IntCalleeSavedRegisters = intCalleeSavedRegisters;
             VecCalleeSavedRegisters = vecCalleeSavedRegisters;
+            RegistersCount          = registersCount;
         }
 
         public int GetAvailableRegisters(RegisterType type)

ARMeilleure/CodeGen/RegisterAllocators/StackAllocator.cs

@@ -1,6 +1,4 @@
-using ARMeilleure.Common;
 using ARMeilleure.IntermediateRepresentation;
-using System;
 
 namespace ARMeilleure.CodeGen.RegisterAllocators
 {

ARMeilleure/CodeGen/X86/Assembler.cs

@@ -1,5 +1,6 @@
 using ARMeilleure.CodeGen.Linking;
 using ARMeilleure.IntermediateRepresentation;
+using Ryujinx.Common.Memory;
 using System;
 using System.Collections.Generic;
 using System.Diagnostics;
@@ -1285,7 +1286,7 @@ namespace ARMeilleure.CodeGen.X86
             // Write the code, ignoring the dummy bytes after jumps, into a new stream.
             _stream.Seek(0, SeekOrigin.Begin);
 
-            using var codeStream = new MemoryStream();
+            using var codeStream = MemoryStreamManager.Shared.GetStream();
             var assembler = new Assembler(codeStream, HasRelocs);
 
             bool hasRelocs = HasRelocs;

ARMeilleure/CodeGen/X86/AssemblerTable.cs

@@ -4,6 +4,11 @@ namespace ARMeilleure.CodeGen.X86
 {
     partial class Assembler
     {
+        public static bool SupportsVexPrefix(X86Instruction inst)
+        {
+            return _instTable[(int)inst].Flags.HasFlag(InstructionFlags.Vex);
+        }
+
         private const int BadOp = 0;
 
         [Flags]
@@ -57,220 +62,225 @@ namespace ARMeilleure.CodeGen.X86
             _instTable = new InstructionInfo[(int)X86Instruction.Count];
 
             //  Name                                             RM/R        RM/I8       RM/I32      R/I64       R/RM        Flags
-            Add(X86Instruction.Add,          new InstructionInfo(0x00000001, 0x00000083, 0x00000081, BadOp,      0x00000003, InstructionFlags.None));
-            Add(X86Instruction.Addpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f58, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Addps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f58, InstructionFlags.Vex));
-            Add(X86Instruction.Addsd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f58, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Addss,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f58, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Aesdec,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38de, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Aesdeclast,   new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38df, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Aesenc,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38dc, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Aesenclast,   new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38dd, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Aesimc,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38db, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.And,          new InstructionInfo(0x00000021, 0x04000083, 0x04000081, BadOp,      0x00000023, InstructionFlags.None));
-            Add(X86Instruction.Andnpd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f55, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Andnps,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f55, InstructionFlags.Vex));
-            Add(X86Instruction.Andpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f54, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Andps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f54, InstructionFlags.Vex));
-            Add(X86Instruction.Blendvpd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3815, InstructionFlags.Prefix66));
-            Add(X86Instruction.Blendvps,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3814, InstructionFlags.Prefix66));
-            Add(X86Instruction.Bsr,          new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fbd, InstructionFlags.None));
-            Add(X86Instruction.Bswap,        new InstructionInfo(0x00000fc8, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.RegOnly));
-            Add(X86Instruction.Call,         new InstructionInfo(0x020000ff, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Cmovcc,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f40, InstructionFlags.None));
-            Add(X86Instruction.Cmp,          new InstructionInfo(0x00000039, 0x07000083, 0x07000081, BadOp,      0x0000003b, InstructionFlags.None));
-            Add(X86Instruction.Cmppd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc2, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Cmpps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc2, InstructionFlags.Vex));
-            Add(X86Instruction.Cmpsd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc2, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Cmpss,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc2, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Cmpxchg,      new InstructionInfo(0x00000fb1, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Cmpxchg16b,   new InstructionInfo(0x01000fc7, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.RexW));
-            Add(X86Instruction.Cmpxchg8,     new InstructionInfo(0x00000fb0, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Reg8Src));
-            Add(X86Instruction.Comisd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2f, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Comiss,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2f, InstructionFlags.Vex));
-            Add(X86Instruction.Crc32,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38f1, InstructionFlags.PrefixF2));
-            Add(X86Instruction.Crc32_16,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38f1, InstructionFlags.PrefixF2 | InstructionFlags.Prefix66));
-            Add(X86Instruction.Crc32_8,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38f0, InstructionFlags.PrefixF2 | InstructionFlags.Reg8Src));
-            Add(X86Instruction.Cvtdq2pd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fe6, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Cvtdq2ps,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5b, InstructionFlags.Vex));
-            Add(X86Instruction.Cvtpd2dq,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fe6, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Cvtpd2ps,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5a, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Cvtps2dq,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5b, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Cvtps2pd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5a, InstructionFlags.Vex));
-            Add(X86Instruction.Cvtsd2si,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2d, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Cvtsd2ss,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5a, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Cvtsi2sd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2a, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Cvtsi2ss,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2a, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Cvtss2sd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5a, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Cvtss2si,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2d, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Div,          new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x060000f7, InstructionFlags.None));
-            Add(X86Instruction.Divpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5e, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Divps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5e, InstructionFlags.Vex));
-            Add(X86Instruction.Divsd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5e, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Divss,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5e, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Haddpd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f7c, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Haddps,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f7c, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Idiv,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x070000f7, InstructionFlags.None));
-            Add(X86Instruction.Imul,         new InstructionInfo(BadOp,      0x0000006b, 0x00000069, BadOp,      0x00000faf, InstructionFlags.None));
-            Add(X86Instruction.Imul128,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x050000f7, InstructionFlags.None));
-            Add(X86Instruction.Insertps,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a21, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Jmp,          new InstructionInfo(0x040000ff, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Ldmxcsr,      new InstructionInfo(0x02000fae, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex));
-            Add(X86Instruction.Lea,          new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x0000008d, InstructionFlags.None));
-            Add(X86Instruction.Maxpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5f, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Maxps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5f, InstructionFlags.Vex));
-            Add(X86Instruction.Maxsd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5f, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Maxss,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5f, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Minpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5d, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Minps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5d, InstructionFlags.Vex));
-            Add(X86Instruction.Minsd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5d, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Minss,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5d, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Mov,          new InstructionInfo(0x00000089, BadOp,      0x000000c7, 0x000000b8, 0x0000008b, InstructionFlags.None));
-            Add(X86Instruction.Mov16,        new InstructionInfo(0x00000089, BadOp,      0x000000c7, BadOp,      0x0000008b, InstructionFlags.Prefix66));
-            Add(X86Instruction.Mov8,         new InstructionInfo(0x00000088, 0x000000c6, BadOp,      BadOp,      0x0000008a, InstructionFlags.Reg8Src | InstructionFlags.Reg8Dest));
-            Add(X86Instruction.Movd,         new InstructionInfo(0x00000f7e, BadOp,      BadOp,      BadOp,      0x00000f6e, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Movdqu,       new InstructionInfo(0x00000f7f, BadOp,      BadOp,      BadOp,      0x00000f6f, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Movhlps,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f12, InstructionFlags.Vex));
-            Add(X86Instruction.Movlhps,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f16, InstructionFlags.Vex));
-            Add(X86Instruction.Movq,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f7e, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Movsd,        new InstructionInfo(0x00000f11, BadOp,      BadOp,      BadOp,      0x00000f10, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Movss,        new InstructionInfo(0x00000f11, BadOp,      BadOp,      BadOp,      0x00000f10, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Movsx16,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fbf, InstructionFlags.None));
-            Add(X86Instruction.Movsx32,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000063, InstructionFlags.None));
-            Add(X86Instruction.Movsx8,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fbe, InstructionFlags.Reg8Src));
-            Add(X86Instruction.Movzx16,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fb7, InstructionFlags.None));
-            Add(X86Instruction.Movzx8,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fb6, InstructionFlags.Reg8Src));
-            Add(X86Instruction.Mul128,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x040000f7, InstructionFlags.None));
-            Add(X86Instruction.Mulpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f59, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Mulps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f59, InstructionFlags.Vex));
-            Add(X86Instruction.Mulsd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f59, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Mulss,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f59, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Neg,          new InstructionInfo(0x030000f7, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Not,          new InstructionInfo(0x020000f7, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Or,           new InstructionInfo(0x00000009, 0x01000083, 0x01000081, BadOp,      0x0000000b, InstructionFlags.None));
-            Add(X86Instruction.Paddb,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ffc, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Paddd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ffe, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Paddq,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fd4, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Paddw,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ffd, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pand,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fdb, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pandn,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fdf, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pavgb,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fe0, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pavgw,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fe3, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pblendvb,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3810, InstructionFlags.Prefix66));
-            Add(X86Instruction.Pclmulqdq,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a44, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pcmpeqb,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f74, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pcmpeqd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f76, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pcmpeqq,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3829, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pcmpeqw,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f75, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pcmpgtb,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f64, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pcmpgtd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f66, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pcmpgtq,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3837, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pcmpgtw,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f65, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pextrb,       new InstructionInfo(0x000f3a14, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pextrd,       new InstructionInfo(0x000f3a16, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pextrq,       new InstructionInfo(0x000f3a16, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.RexW | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pextrw,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc5, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pinsrb,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a20, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pinsrd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a22, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pinsrq,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a22, InstructionFlags.Vex | InstructionFlags.RexW | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pinsrw,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc4, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmaxsb,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383c, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmaxsd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383d, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmaxsw,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fee, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmaxub,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fde, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmaxud,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383f, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmaxuw,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383e, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pminsb,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3838, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pminsd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3839, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pminsw,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fea, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pminub,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fda, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pminud,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383b, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pminuw,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383a, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmovsxbw,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3820, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmovsxdq,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3825, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmovsxwd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3823, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmovzxbw,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3830, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmovzxdq,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3835, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmovzxwd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3833, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmulld,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3840, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pmullw,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fd5, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pop,          new InstructionInfo(0x0000008f, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Popcnt,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fb8, InstructionFlags.PrefixF3));
-            Add(X86Instruction.Por,          new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000feb, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pshufb,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3800, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pshufd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f70, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pslld,        new InstructionInfo(BadOp,      0x06000f72, BadOp,      BadOp,      0x00000ff2, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Pslldq,       new InstructionInfo(BadOp,      0x07000f73, BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psllq,        new InstructionInfo(BadOp,      0x06000f73, BadOp,      BadOp,      0x00000ff3, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psllw,        new InstructionInfo(BadOp,      0x06000f71, BadOp,      BadOp,      0x00000ff1, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psrad,        new InstructionInfo(BadOp,      0x04000f72, BadOp,      BadOp,      0x00000fe2, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psraw,        new InstructionInfo(BadOp,      0x04000f71, BadOp,      BadOp,      0x00000fe1, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psrld,        new InstructionInfo(BadOp,      0x02000f72, BadOp,      BadOp,      0x00000fd2, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psrlq,        new InstructionInfo(BadOp,      0x02000f73, BadOp,      BadOp,      0x00000fd3, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psrldq,       new InstructionInfo(BadOp,      0x03000f73, BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psrlw,        new InstructionInfo(BadOp,      0x02000f71, BadOp,      BadOp,      0x00000fd1, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psubb,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ff8, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psubd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ffa, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psubq,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ffb, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Psubw,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ff9, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Punpckhbw,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f68, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Punpckhdq,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f6a, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Punpckhqdq,   new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f6d, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Punpckhwd,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f69, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Punpcklbw,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f60, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Punpckldq,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f62, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Punpcklqdq,   new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f6c, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Punpcklwd,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f61, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Push,         new InstructionInfo(BadOp,      0x0000006a, 0x00000068, BadOp,      0x060000ff, InstructionFlags.None));
-            Add(X86Instruction.Pxor,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fef, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Rcpps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f53, InstructionFlags.Vex));
-            Add(X86Instruction.Rcpss,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f53, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Ror,          new InstructionInfo(0x010000d3, 0x010000c1, BadOp,      BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Roundpd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a09, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Roundps,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a08, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Roundsd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a0b, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Roundss,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a0a, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Rsqrtps,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f52, InstructionFlags.Vex));
-            Add(X86Instruction.Rsqrtss,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f52, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Sar,          new InstructionInfo(0x070000d3, 0x070000c1, BadOp,      BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Setcc,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f90, InstructionFlags.Reg8Dest));
-            Add(X86Instruction.Shl,          new InstructionInfo(0x040000d3, 0x040000c1, BadOp,      BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Shr,          new InstructionInfo(0x050000d3, 0x050000c1, BadOp,      BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Shufpd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc6, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Shufps,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc6, InstructionFlags.Vex));
-            Add(X86Instruction.Sqrtpd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f51, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Sqrtps,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f51, InstructionFlags.Vex));
-            Add(X86Instruction.Sqrtsd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f51, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Sqrtss,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f51, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Stmxcsr,      new InstructionInfo(0x03000fae, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex));
-            Add(X86Instruction.Sub,          new InstructionInfo(0x00000029, 0x05000083, 0x05000081, BadOp,      0x0000002b, InstructionFlags.None));
-            Add(X86Instruction.Subpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5c, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Subps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5c, InstructionFlags.Vex));
-            Add(X86Instruction.Subsd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5c, InstructionFlags.Vex | InstructionFlags.PrefixF2));
-            Add(X86Instruction.Subss,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5c, InstructionFlags.Vex | InstructionFlags.PrefixF3));
-            Add(X86Instruction.Test,         new InstructionInfo(0x00000085, BadOp,      0x000000f7, BadOp,      BadOp,      InstructionFlags.None));
-            Add(X86Instruction.Unpckhpd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f15, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Unpckhps,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f15, InstructionFlags.Vex));
-            Add(X86Instruction.Unpcklpd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f14, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Unpcklps,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f14, InstructionFlags.Vex));
-            Add(X86Instruction.Vblendvpd,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a4b, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Vblendvps,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a4a, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Vcvtph2ps,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3813, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Vcvtps2ph,    new InstructionInfo(0x000f3a1d, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Vfmadd231ps,  new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38b8, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Vfmadd231sd,  new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38b9, InstructionFlags.Vex | InstructionFlags.Prefix66 | InstructionFlags.RexW));
-            Add(X86Instruction.Vfmadd231ss,  new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38b9, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Vfmsub231sd,  new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bb, InstructionFlags.Vex | InstructionFlags.Prefix66 | InstructionFlags.RexW));
-            Add(X86Instruction.Vfmsub231ss,  new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bb, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Vfnmadd231ps, new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bc, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Vfnmadd231sd, new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bd, InstructionFlags.Vex | InstructionFlags.Prefix66 | InstructionFlags.RexW));
-            Add(X86Instruction.Vfnmadd231ss, new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bd, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Vfnmsub231sd, new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bf, InstructionFlags.Vex | InstructionFlags.Prefix66 | InstructionFlags.RexW));
-            Add(X86Instruction.Vfnmsub231ss, new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bf, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Vpblendvb,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a4c, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Xor,          new InstructionInfo(0x00000031, 0x06000083, 0x06000081, BadOp,      0x00000033, InstructionFlags.None));
-            Add(X86Instruction.Xorpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f57, InstructionFlags.Vex | InstructionFlags.Prefix66));
-            Add(X86Instruction.Xorps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f57, InstructionFlags.Vex));
+            Add(X86Instruction.Add,           new InstructionInfo(0x00000001, 0x00000083, 0x00000081, BadOp,      0x00000003, InstructionFlags.None));
+            Add(X86Instruction.Addpd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f58, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Addps,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f58, InstructionFlags.Vex));
+            Add(X86Instruction.Addsd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f58, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Addss,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f58, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Aesdec,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38de, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Aesdeclast,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38df, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Aesenc,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38dc, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Aesenclast,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38dd, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Aesimc,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38db, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.And,           new InstructionInfo(0x00000021, 0x04000083, 0x04000081, BadOp,      0x00000023, InstructionFlags.None));
+            Add(X86Instruction.Andnpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f55, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Andnps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f55, InstructionFlags.Vex));
+            Add(X86Instruction.Andpd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f54, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Andps,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f54, InstructionFlags.Vex));
+            Add(X86Instruction.Blendvpd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3815, InstructionFlags.Prefix66));
+            Add(X86Instruction.Blendvps,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3814, InstructionFlags.Prefix66));
+            Add(X86Instruction.Bsr,           new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fbd, InstructionFlags.None));
+            Add(X86Instruction.Bswap,         new InstructionInfo(0x00000fc8, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.RegOnly));
+            Add(X86Instruction.Call,          new InstructionInfo(0x020000ff, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Cmovcc,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f40, InstructionFlags.None));
+            Add(X86Instruction.Cmp,           new InstructionInfo(0x00000039, 0x07000083, 0x07000081, BadOp,      0x0000003b, InstructionFlags.None));
+            Add(X86Instruction.Cmppd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc2, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Cmpps,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc2, InstructionFlags.Vex));
+            Add(X86Instruction.Cmpsd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc2, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Cmpss,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc2, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Cmpxchg,       new InstructionInfo(0x00000fb1, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Cmpxchg16b,    new InstructionInfo(0x01000fc7, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.RexW));
+            Add(X86Instruction.Cmpxchg8,      new InstructionInfo(0x00000fb0, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Reg8Src));
+            Add(X86Instruction.Comisd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2f, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Comiss,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2f, InstructionFlags.Vex));
+            Add(X86Instruction.Crc32,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38f1, InstructionFlags.PrefixF2));
+            Add(X86Instruction.Crc32_16,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38f1, InstructionFlags.PrefixF2 | InstructionFlags.Prefix66));
+            Add(X86Instruction.Crc32_8,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38f0, InstructionFlags.PrefixF2 | InstructionFlags.Reg8Src));
+            Add(X86Instruction.Cvtdq2pd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fe6, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Cvtdq2ps,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5b, InstructionFlags.Vex));
+            Add(X86Instruction.Cvtpd2dq,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fe6, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Cvtpd2ps,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5a, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Cvtps2dq,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5b, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Cvtps2pd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5a, InstructionFlags.Vex));
+            Add(X86Instruction.Cvtsd2si,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2d, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Cvtsd2ss,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5a, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Cvtsi2sd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2a, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Cvtsi2ss,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2a, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Cvtss2sd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5a, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Cvtss2si,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f2d, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Div,           new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x060000f7, InstructionFlags.None));
+            Add(X86Instruction.Divpd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5e, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Divps,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5e, InstructionFlags.Vex));
+            Add(X86Instruction.Divsd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5e, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Divss,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5e, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Gf2p8affineqb, new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3ace, InstructionFlags.Prefix66));
+            Add(X86Instruction.Haddpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f7c, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Haddps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f7c, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Idiv,          new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x070000f7, InstructionFlags.None));
+            Add(X86Instruction.Imul,          new InstructionInfo(BadOp,      0x0000006b, 0x00000069, BadOp,      0x00000faf, InstructionFlags.None));
+            Add(X86Instruction.Imul128,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x050000f7, InstructionFlags.None));
+            Add(X86Instruction.Insertps,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a21, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Jmp,           new InstructionInfo(0x040000ff, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Ldmxcsr,       new InstructionInfo(0x02000fae, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex));
+            Add(X86Instruction.Lea,           new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x0000008d, InstructionFlags.None));
+            Add(X86Instruction.Maxpd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5f, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Maxps,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5f, InstructionFlags.Vex));
+            Add(X86Instruction.Maxsd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5f, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Maxss,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5f, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Minpd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5d, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Minps,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5d, InstructionFlags.Vex));
+            Add(X86Instruction.Minsd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5d, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Minss,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5d, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Mov,           new InstructionInfo(0x00000089, BadOp,      0x000000c7, 0x000000b8, 0x0000008b, InstructionFlags.None));
+            Add(X86Instruction.Mov16,         new InstructionInfo(0x00000089, BadOp,      0x000000c7, BadOp,      0x0000008b, InstructionFlags.Prefix66));
+            Add(X86Instruction.Mov8,          new InstructionInfo(0x00000088, 0x000000c6, BadOp,      BadOp,      0x0000008a, InstructionFlags.Reg8Src | InstructionFlags.Reg8Dest));
+            Add(X86Instruction.Movd,          new InstructionInfo(0x00000f7e, BadOp,      BadOp,      BadOp,      0x00000f6e, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Movdqu,        new InstructionInfo(0x00000f7f, BadOp,      BadOp,      BadOp,      0x00000f6f, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Movhlps,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f12, InstructionFlags.Vex));
+            Add(X86Instruction.Movlhps,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f16, InstructionFlags.Vex));
+            Add(X86Instruction.Movq,          new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f7e, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Movsd,         new InstructionInfo(0x00000f11, BadOp,      BadOp,      BadOp,      0x00000f10, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Movss,         new InstructionInfo(0x00000f11, BadOp,      BadOp,      BadOp,      0x00000f10, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Movsx16,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fbf, InstructionFlags.None));
+            Add(X86Instruction.Movsx32,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000063, InstructionFlags.None));
+            Add(X86Instruction.Movsx8,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fbe, InstructionFlags.Reg8Src));
+            Add(X86Instruction.Movzx16,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fb7, InstructionFlags.None));
+            Add(X86Instruction.Movzx8,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fb6, InstructionFlags.Reg8Src));
+            Add(X86Instruction.Mul128,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x040000f7, InstructionFlags.None));
+            Add(X86Instruction.Mulpd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f59, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Mulps,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f59, InstructionFlags.Vex));
+            Add(X86Instruction.Mulsd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f59, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Mulss,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f59, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Neg,           new InstructionInfo(0x030000f7, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Not,           new InstructionInfo(0x020000f7, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Or,            new InstructionInfo(0x00000009, 0x01000083, 0x01000081, BadOp,      0x0000000b, InstructionFlags.None));
+            Add(X86Instruction.Paddb,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ffc, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Paddd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ffe, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Paddq,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fd4, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Paddw,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ffd, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Palignr,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a0f, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pand,          new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fdb, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pandn,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fdf, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pavgb,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fe0, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pavgw,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fe3, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pblendvb,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3810, InstructionFlags.Prefix66));
+            Add(X86Instruction.Pclmulqdq,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a44, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pcmpeqb,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f74, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pcmpeqd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f76, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pcmpeqq,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3829, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pcmpeqw,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f75, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pcmpgtb,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f64, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pcmpgtd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f66, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pcmpgtq,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3837, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pcmpgtw,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f65, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pextrb,        new InstructionInfo(0x000f3a14, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pextrd,        new InstructionInfo(0x000f3a16, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pextrq,        new InstructionInfo(0x000f3a16, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.RexW | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pextrw,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc5, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pinsrb,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a20, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pinsrd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a22, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pinsrq,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a22, InstructionFlags.Vex | InstructionFlags.RexW | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pinsrw,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc4, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmaxsb,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383c, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmaxsd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383d, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmaxsw,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fee, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmaxub,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fde, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmaxud,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383f, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmaxuw,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383e, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pminsb,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3838, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pminsd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3839, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pminsw,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fea, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pminub,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fda, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pminud,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383b, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pminuw,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f383a, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmovsxbw,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3820, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmovsxdq,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3825, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmovsxwd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3823, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmovzxbw,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3830, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmovzxdq,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3835, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmovzxwd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3833, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmulld,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3840, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pmullw,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fd5, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pop,           new InstructionInfo(0x0000008f, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Popcnt,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fb8, InstructionFlags.PrefixF3));
+            Add(X86Instruction.Por,           new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000feb, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pshufb,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3800, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pshufd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f70, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pslld,         new InstructionInfo(BadOp,      0x06000f72, BadOp,      BadOp,      0x00000ff2, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Pslldq,        new InstructionInfo(BadOp,      0x07000f73, BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psllq,         new InstructionInfo(BadOp,      0x06000f73, BadOp,      BadOp,      0x00000ff3, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psllw,         new InstructionInfo(BadOp,      0x06000f71, BadOp,      BadOp,      0x00000ff1, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psrad,         new InstructionInfo(BadOp,      0x04000f72, BadOp,      BadOp,      0x00000fe2, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psraw,         new InstructionInfo(BadOp,      0x04000f71, BadOp,      BadOp,      0x00000fe1, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psrld,         new InstructionInfo(BadOp,      0x02000f72, BadOp,      BadOp,      0x00000fd2, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psrlq,         new InstructionInfo(BadOp,      0x02000f73, BadOp,      BadOp,      0x00000fd3, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psrldq,        new InstructionInfo(BadOp,      0x03000f73, BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psrlw,         new InstructionInfo(BadOp,      0x02000f71, BadOp,      BadOp,      0x00000fd1, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psubb,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ff8, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psubd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ffa, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psubq,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ffb, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Psubw,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000ff9, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Punpckhbw,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f68, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Punpckhdq,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f6a, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Punpckhqdq,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f6d, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Punpckhwd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f69, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Punpcklbw,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f60, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Punpckldq,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f62, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Punpcklqdq,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f6c, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Punpcklwd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f61, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Push,          new InstructionInfo(BadOp,      0x0000006a, 0x00000068, BadOp,      0x060000ff, InstructionFlags.None));
+            Add(X86Instruction.Pxor,          new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fef, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Rcpps,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f53, InstructionFlags.Vex));
+            Add(X86Instruction.Rcpss,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f53, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Ror,           new InstructionInfo(0x010000d3, 0x010000c1, BadOp,      BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Roundpd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a09, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Roundps,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a08, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Roundsd,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a0b, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Roundss,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a0a, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Rsqrtps,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f52, InstructionFlags.Vex));
+            Add(X86Instruction.Rsqrtss,       new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f52, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Sar,           new InstructionInfo(0x070000d3, 0x070000c1, BadOp,      BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Setcc,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f90, InstructionFlags.Reg8Dest));
+            Add(X86Instruction.Sha256Msg1,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38cc, InstructionFlags.None));
+            Add(X86Instruction.Sha256Msg2,    new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38cd, InstructionFlags.None));
+            Add(X86Instruction.Sha256Rnds2,   new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38cb, InstructionFlags.None));
+            Add(X86Instruction.Shl,           new InstructionInfo(0x040000d3, 0x040000c1, BadOp,      BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Shr,           new InstructionInfo(0x050000d3, 0x050000c1, BadOp,      BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Shufpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc6, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Shufps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000fc6, InstructionFlags.Vex));
+            Add(X86Instruction.Sqrtpd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f51, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Sqrtps,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f51, InstructionFlags.Vex));
+            Add(X86Instruction.Sqrtsd,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f51, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Sqrtss,        new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f51, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Stmxcsr,       new InstructionInfo(0x03000fae, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex));
+            Add(X86Instruction.Sub,           new InstructionInfo(0x00000029, 0x05000083, 0x05000081, BadOp,      0x0000002b, InstructionFlags.None));
+            Add(X86Instruction.Subpd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5c, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Subps,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5c, InstructionFlags.Vex));
+            Add(X86Instruction.Subsd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5c, InstructionFlags.Vex | InstructionFlags.PrefixF2));
+            Add(X86Instruction.Subss,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f5c, InstructionFlags.Vex | InstructionFlags.PrefixF3));
+            Add(X86Instruction.Test,          new InstructionInfo(0x00000085, BadOp,      0x000000f7, BadOp,      BadOp,      InstructionFlags.None));
+            Add(X86Instruction.Unpckhpd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f15, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Unpckhps,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f15, InstructionFlags.Vex));
+            Add(X86Instruction.Unpcklpd,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f14, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Unpcklps,      new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f14, InstructionFlags.Vex));
+            Add(X86Instruction.Vblendvpd,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a4b, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Vblendvps,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a4a, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Vcvtph2ps,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3813, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Vcvtps2ph,     new InstructionInfo(0x000f3a1d, BadOp,      BadOp,      BadOp,      BadOp,      InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Vfmadd231ps,   new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38b8, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Vfmadd231sd,   new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38b9, InstructionFlags.Vex | InstructionFlags.Prefix66 | InstructionFlags.RexW));
+            Add(X86Instruction.Vfmadd231ss,   new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38b9, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Vfmsub231sd,   new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bb, InstructionFlags.Vex | InstructionFlags.Prefix66 | InstructionFlags.RexW));
+            Add(X86Instruction.Vfmsub231ss,   new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bb, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Vfnmadd231ps,  new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bc, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Vfnmadd231sd,  new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bd, InstructionFlags.Vex | InstructionFlags.Prefix66 | InstructionFlags.RexW));
+            Add(X86Instruction.Vfnmadd231ss,  new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bd, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Vfnmsub231sd,  new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bf, InstructionFlags.Vex | InstructionFlags.Prefix66 | InstructionFlags.RexW));
+            Add(X86Instruction.Vfnmsub231ss,  new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f38bf, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Vpblendvb,     new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x000f3a4c, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Xor,           new InstructionInfo(0x00000031, 0x06000083, 0x06000081, BadOp,      0x00000033, InstructionFlags.None));
+            Add(X86Instruction.Xorpd,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f57, InstructionFlags.Vex | InstructionFlags.Prefix66));
+            Add(X86Instruction.Xorps,         new InstructionInfo(BadOp,      BadOp,      BadOp,      BadOp,      0x00000f57, InstructionFlags.Vex));
 
             static void Add(X86Instruction inst, in InstructionInfo info)
             {

ARMeilleure/CodeGen/X86/CallingConvention.cs

@@ -1,5 +1,4 @@
 using System;
-using System.Runtime.InteropServices;
 
 namespace ARMeilleure.CodeGen.X86
 {

ARMeilleure/CodeGen/X86/CodeGenContext.cs

@@ -1,5 +1,6 @@
 using ARMeilleure.CodeGen.RegisterAllocators;
 using ARMeilleure.IntermediateRepresentation;
+using Ryujinx.Common.Memory;
 using System.IO;
 using System.Numerics;
 
@@ -22,7 +23,7 @@ namespace ARMeilleure.CodeGen.X86
 
         public CodeGenContext(AllocationResult allocResult, int maxCallArgs, int blocksCount, bool relocatable)
         {
-            _stream = new MemoryStream();
+            _stream = MemoryStreamManager.Shared.GetStream();
             _blockLabels = new Operand[blocksCount];
 
             AllocResult = allocResult;

ARMeilleure/CodeGen/X86/CodeGenerator.cs

@@ -16,6 +16,7 @@ namespace ARMeilleure.CodeGen.X86
 {
     static class CodeGenerator
     {
+        private const int RegistersCount = 16;
         private const int PageSize       = 0x1000;
         private const int StackGuardSize = 0x2000;
 
@@ -143,7 +144,8 @@ namespace ARMeilleure.CodeGen.X86
                 CallingConvention.GetIntCallerSavedRegisters(),
                 CallingConvention.GetVecCallerSavedRegisters(),
                 CallingConvention.GetIntCalleeSavedRegisters(),
-                CallingConvention.GetVecCalleeSavedRegisters());
+                CallingConvention.GetVecCalleeSavedRegisters(),
+                RegistersCount);
 
             AllocationResult allocResult = regAlloc.RunPass(cfg, stackAlloc, regMasks);
 
@@ -1587,6 +1589,12 @@ namespace ARMeilleure.CodeGen.X86
 
             Debug.Assert(dest.Type.IsInteger() && source.Type.IsInteger());
 
+            // We can eliminate the move if source is already 32-bit and the registers are the same.
+            if (dest.Value == source.Value && source.Type == OperandType.I32)
+            {
+                return;
+            }
+
             context.Assembler.Mov(dest, source, OperandType.I32);
         }
 

ARMeilleure/CodeGen/X86/HardwareCapabilities.cs

@@ -12,21 +12,29 @@ namespace ARMeilleure.CodeGen.X86
                 return;
             }
 
-            (_, _, int ecx, int edx) = X86Base.CpuId(0x00000001, 0x00000000);
+            (int maxNum, _, _, _) = X86Base.CpuId(0x00000000, 0x00000000);
 
-            FeatureInfoEdx = (FeatureFlagsEdx)edx;
-            FeatureInfoEcx = (FeatureFlagsEcx)ecx;
+            (_, _, int ecx1, int edx1) = X86Base.CpuId(0x00000001, 0x00000000);
+            FeatureInfo1Edx = (FeatureFlags1Edx)edx1;
+            FeatureInfo1Ecx = (FeatureFlags1Ecx)ecx1;
+
+            if (maxNum >= 7)
+            {
+                (_, int ebx7, int ecx7, _) = X86Base.CpuId(0x00000007, 0x00000000);
+                FeatureInfo7Ebx = (FeatureFlags7Ebx)ebx7;
+                FeatureInfo7Ecx = (FeatureFlags7Ecx)ecx7;
+            }
         }
 
         [Flags]
-        public enum FeatureFlagsEdx
+        public enum FeatureFlags1Edx
         {
             Sse = 1 << 25,
             Sse2 = 1 << 26
         }
 
         [Flags]
-        public enum FeatureFlagsEcx
+        public enum FeatureFlags1Ecx
         {
             Sse3 = 1 << 0,
             Pclmulqdq = 1 << 1,
@@ -40,21 +48,39 @@ namespace ARMeilleure.CodeGen.X86
             F16c = 1 << 29
         }
 
-        public static FeatureFlagsEdx FeatureInfoEdx { get; }
-        public static FeatureFlagsEcx FeatureInfoEcx { get; }
+        [Flags]
+        public enum FeatureFlags7Ebx
+        {
+            Avx2 = 1 << 5,
+            Sha = 1 << 29
+        }
 
-        public static bool SupportsSse => FeatureInfoEdx.HasFlag(FeatureFlagsEdx.Sse);
-        public static bool SupportsSse2 => FeatureInfoEdx.HasFlag(FeatureFlagsEdx.Sse2);
-        public static bool SupportsSse3 => FeatureInfoEcx.HasFlag(FeatureFlagsEcx.Sse3);
-        public static bool SupportsPclmulqdq => FeatureInfoEcx.HasFlag(FeatureFlagsEcx.Pclmulqdq);
-        public static bool SupportsSsse3 => FeatureInfoEcx.HasFlag(FeatureFlagsEcx.Ssse3);
-        public static bool SupportsFma => FeatureInfoEcx.HasFlag(FeatureFlagsEcx.Fma);
-        public static bool SupportsSse41 => FeatureInfoEcx.HasFlag(FeatureFlagsEcx.Sse41);
-        public static bool SupportsSse42 => FeatureInfoEcx.HasFlag(FeatureFlagsEcx.Sse42);
-        public static bool SupportsPopcnt => FeatureInfoEcx.HasFlag(FeatureFlagsEcx.Popcnt);
-        public static bool SupportsAesni => FeatureInfoEcx.HasFlag(FeatureFlagsEcx.Aes);
-        public static bool SupportsAvx => FeatureInfoEcx.HasFlag(FeatureFlagsEcx.Avx);
-        public static bool SupportsF16c => FeatureInfoEcx.HasFlag(FeatureFlagsEcx.F16c);
+        [Flags]
+        public enum FeatureFlags7Ecx
+        {
+            Gfni = 1 << 8,
+        }
+
+        public static FeatureFlags1Edx FeatureInfo1Edx { get; }
+        public static FeatureFlags1Ecx FeatureInfo1Ecx { get; }
+        public static FeatureFlags7Ebx FeatureInfo7Ebx { get; } = 0;
+        public static FeatureFlags7Ecx FeatureInfo7Ecx { get; } = 0;
+
+        public static bool SupportsSse => FeatureInfo1Edx.HasFlag(FeatureFlags1Edx.Sse);
+        public static bool SupportsSse2 => FeatureInfo1Edx.HasFlag(FeatureFlags1Edx.Sse2);
+        public static bool SupportsSse3 => FeatureInfo1Ecx.HasFlag(FeatureFlags1Ecx.Sse3);
+        public static bool SupportsPclmulqdq => FeatureInfo1Ecx.HasFlag(FeatureFlags1Ecx.Pclmulqdq);
+        public static bool SupportsSsse3 => FeatureInfo1Ecx.HasFlag(FeatureFlags1Ecx.Ssse3);
+        public static bool SupportsFma => FeatureInfo1Ecx.HasFlag(FeatureFlags1Ecx.Fma);
+        public static bool SupportsSse41 => FeatureInfo1Ecx.HasFlag(FeatureFlags1Ecx.Sse41);
+        public static bool SupportsSse42 => FeatureInfo1Ecx.HasFlag(FeatureFlags1Ecx.Sse42);
+        public static bool SupportsPopcnt => FeatureInfo1Ecx.HasFlag(FeatureFlags1Ecx.Popcnt);
+        public static bool SupportsAesni => FeatureInfo1Ecx.HasFlag(FeatureFlags1Ecx.Aes);
+        public static bool SupportsAvx => FeatureInfo1Ecx.HasFlag(FeatureFlags1Ecx.Avx);
+        public static bool SupportsAvx2 => FeatureInfo7Ebx.HasFlag(FeatureFlags7Ebx.Avx2) && SupportsAvx;
+        public static bool SupportsF16c => FeatureInfo1Ecx.HasFlag(FeatureFlags1Ecx.F16c);
+        public static bool SupportsSha => FeatureInfo7Ebx.HasFlag(FeatureFlags7Ebx.Sha);
+        public static bool SupportsGfni => FeatureInfo7Ecx.HasFlag(FeatureFlags7Ecx.Gfni);
 
         public static bool ForceLegacySse { get; set; }
 

ARMeilleure/CodeGen/X86/IntrinsicInfo.cs

@@ -1,6 +1,6 @@
 namespace ARMeilleure.CodeGen.X86
 {
-    struct IntrinsicInfo
+    readonly struct IntrinsicInfo
     {
         public X86Instruction Inst { get; }
         public IntrinsicType  Type { get; }

ARMeilleure/CodeGen/X86/IntrinsicTable.cs

@@ -5,180 +5,183 @@ namespace ARMeilleure.CodeGen.X86
 {
     static class IntrinsicTable
     {
-        private const int BadOp = 0;
-
         private static IntrinsicInfo[] _intrinTable;
 
         static IntrinsicTable()
         {
             _intrinTable = new IntrinsicInfo[EnumUtils.GetCount(typeof(Intrinsic))];
 
-            Add(Intrinsic.X86Addpd,        new IntrinsicInfo(X86Instruction.Addpd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Addps,        new IntrinsicInfo(X86Instruction.Addps,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Addsd,        new IntrinsicInfo(X86Instruction.Addsd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Addss,        new IntrinsicInfo(X86Instruction.Addss,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Aesdec,       new IntrinsicInfo(X86Instruction.Aesdec,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Aesdeclast,   new IntrinsicInfo(X86Instruction.Aesdeclast,   IntrinsicType.Binary));
-            Add(Intrinsic.X86Aesenc,       new IntrinsicInfo(X86Instruction.Aesenc,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Aesenclast,   new IntrinsicInfo(X86Instruction.Aesenclast,   IntrinsicType.Binary));
-            Add(Intrinsic.X86Aesimc,       new IntrinsicInfo(X86Instruction.Aesimc,       IntrinsicType.Unary));
-            Add(Intrinsic.X86Andnpd,       new IntrinsicInfo(X86Instruction.Andnpd,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Andnps,       new IntrinsicInfo(X86Instruction.Andnps,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Andpd,        new IntrinsicInfo(X86Instruction.Andpd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Andps,        new IntrinsicInfo(X86Instruction.Andps,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Blendvpd,     new IntrinsicInfo(X86Instruction.Blendvpd,     IntrinsicType.Ternary));
-            Add(Intrinsic.X86Blendvps,     new IntrinsicInfo(X86Instruction.Blendvps,     IntrinsicType.Ternary));
-            Add(Intrinsic.X86Cmppd,        new IntrinsicInfo(X86Instruction.Cmppd,        IntrinsicType.TernaryImm));
-            Add(Intrinsic.X86Cmpps,        new IntrinsicInfo(X86Instruction.Cmpps,        IntrinsicType.TernaryImm));
-            Add(Intrinsic.X86Cmpsd,        new IntrinsicInfo(X86Instruction.Cmpsd,        IntrinsicType.TernaryImm));
-            Add(Intrinsic.X86Cmpss,        new IntrinsicInfo(X86Instruction.Cmpss,        IntrinsicType.TernaryImm));
-            Add(Intrinsic.X86Comisdeq,     new IntrinsicInfo(X86Instruction.Comisd,       IntrinsicType.Comis_));
-            Add(Intrinsic.X86Comisdge,     new IntrinsicInfo(X86Instruction.Comisd,       IntrinsicType.Comis_));
-            Add(Intrinsic.X86Comisdlt,     new IntrinsicInfo(X86Instruction.Comisd,       IntrinsicType.Comis_));
-            Add(Intrinsic.X86Comisseq,     new IntrinsicInfo(X86Instruction.Comiss,       IntrinsicType.Comis_));
-            Add(Intrinsic.X86Comissge,     new IntrinsicInfo(X86Instruction.Comiss,       IntrinsicType.Comis_));
-            Add(Intrinsic.X86Comisslt,     new IntrinsicInfo(X86Instruction.Comiss,       IntrinsicType.Comis_));
-            Add(Intrinsic.X86Crc32,        new IntrinsicInfo(X86Instruction.Crc32,        IntrinsicType.Crc32));
-            Add(Intrinsic.X86Crc32_16,     new IntrinsicInfo(X86Instruction.Crc32_16,     IntrinsicType.Crc32));
-            Add(Intrinsic.X86Crc32_8,      new IntrinsicInfo(X86Instruction.Crc32_8,      IntrinsicType.Crc32));
-            Add(Intrinsic.X86Cvtdq2pd,     new IntrinsicInfo(X86Instruction.Cvtdq2pd,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Cvtdq2ps,     new IntrinsicInfo(X86Instruction.Cvtdq2ps,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Cvtpd2dq,     new IntrinsicInfo(X86Instruction.Cvtpd2dq,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Cvtpd2ps,     new IntrinsicInfo(X86Instruction.Cvtpd2ps,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Cvtps2dq,     new IntrinsicInfo(X86Instruction.Cvtps2dq,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Cvtps2pd,     new IntrinsicInfo(X86Instruction.Cvtps2pd,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Cvtsd2si,     new IntrinsicInfo(X86Instruction.Cvtsd2si,     IntrinsicType.UnaryToGpr));
-            Add(Intrinsic.X86Cvtsd2ss,     new IntrinsicInfo(X86Instruction.Cvtsd2ss,     IntrinsicType.Binary));
-            Add(Intrinsic.X86Cvtsi2sd,     new IntrinsicInfo(X86Instruction.Cvtsi2sd,     IntrinsicType.BinaryGpr));
-            Add(Intrinsic.X86Cvtsi2si,     new IntrinsicInfo(X86Instruction.Movd,         IntrinsicType.UnaryToGpr));
-            Add(Intrinsic.X86Cvtsi2ss,     new IntrinsicInfo(X86Instruction.Cvtsi2ss,     IntrinsicType.BinaryGpr));
-            Add(Intrinsic.X86Cvtss2sd,     new IntrinsicInfo(X86Instruction.Cvtss2sd,     IntrinsicType.Binary));
-            Add(Intrinsic.X86Cvtss2si,     new IntrinsicInfo(X86Instruction.Cvtss2si,     IntrinsicType.UnaryToGpr));
-            Add(Intrinsic.X86Divpd,        new IntrinsicInfo(X86Instruction.Divpd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Divps,        new IntrinsicInfo(X86Instruction.Divps,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Divsd,        new IntrinsicInfo(X86Instruction.Divsd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Divss,        new IntrinsicInfo(X86Instruction.Divss,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Haddpd,       new IntrinsicInfo(X86Instruction.Haddpd,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Haddps,       new IntrinsicInfo(X86Instruction.Haddps,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Insertps,     new IntrinsicInfo(X86Instruction.Insertps,     IntrinsicType.TernaryImm));
-            Add(Intrinsic.X86Maxpd,        new IntrinsicInfo(X86Instruction.Maxpd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Maxps,        new IntrinsicInfo(X86Instruction.Maxps,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Maxsd,        new IntrinsicInfo(X86Instruction.Maxsd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Maxss,        new IntrinsicInfo(X86Instruction.Maxss,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Minpd,        new IntrinsicInfo(X86Instruction.Minpd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Minps,        new IntrinsicInfo(X86Instruction.Minps,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Minsd,        new IntrinsicInfo(X86Instruction.Minsd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Minss,        new IntrinsicInfo(X86Instruction.Minss,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Movhlps,      new IntrinsicInfo(X86Instruction.Movhlps,      IntrinsicType.Binary));
-            Add(Intrinsic.X86Movlhps,      new IntrinsicInfo(X86Instruction.Movlhps,      IntrinsicType.Binary));
-            Add(Intrinsic.X86Movss,        new IntrinsicInfo(X86Instruction.Movss,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Mulpd,        new IntrinsicInfo(X86Instruction.Mulpd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Mulps,        new IntrinsicInfo(X86Instruction.Mulps,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Mulsd,        new IntrinsicInfo(X86Instruction.Mulsd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Mulss,        new IntrinsicInfo(X86Instruction.Mulss,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Mxcsrmb,      new IntrinsicInfo(X86Instruction.None,         IntrinsicType.Mxcsr)); // Mask bits.
-            Add(Intrinsic.X86Mxcsrub,      new IntrinsicInfo(X86Instruction.None,         IntrinsicType.Mxcsr)); // Unmask bits.
-            Add(Intrinsic.X86Paddb,        new IntrinsicInfo(X86Instruction.Paddb,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Paddd,        new IntrinsicInfo(X86Instruction.Paddd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Paddq,        new IntrinsicInfo(X86Instruction.Paddq,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Paddw,        new IntrinsicInfo(X86Instruction.Paddw,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Pand,         new IntrinsicInfo(X86Instruction.Pand,         IntrinsicType.Binary));
-            Add(Intrinsic.X86Pandn,        new IntrinsicInfo(X86Instruction.Pandn,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Pavgb,        new IntrinsicInfo(X86Instruction.Pavgb,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Pavgw,        new IntrinsicInfo(X86Instruction.Pavgw,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Pblendvb,     new IntrinsicInfo(X86Instruction.Pblendvb,     IntrinsicType.Ternary));
-            Add(Intrinsic.X86Pclmulqdq,    new IntrinsicInfo(X86Instruction.Pclmulqdq,    IntrinsicType.TernaryImm));
-            Add(Intrinsic.X86Pcmpeqb,      new IntrinsicInfo(X86Instruction.Pcmpeqb,      IntrinsicType.Binary));
-            Add(Intrinsic.X86Pcmpeqd,      new IntrinsicInfo(X86Instruction.Pcmpeqd,      IntrinsicType.Binary));
-            Add(Intrinsic.X86Pcmpeqq,      new IntrinsicInfo(X86Instruction.Pcmpeqq,      IntrinsicType.Binary));
-            Add(Intrinsic.X86Pcmpeqw,      new IntrinsicInfo(X86Instruction.Pcmpeqw,      IntrinsicType.Binary));
-            Add(Intrinsic.X86Pcmpgtb,      new IntrinsicInfo(X86Instruction.Pcmpgtb,      IntrinsicType.Binary));
-            Add(Intrinsic.X86Pcmpgtd,      new IntrinsicInfo(X86Instruction.Pcmpgtd,      IntrinsicType.Binary));
-            Add(Intrinsic.X86Pcmpgtq,      new IntrinsicInfo(X86Instruction.Pcmpgtq,      IntrinsicType.Binary));
-            Add(Intrinsic.X86Pcmpgtw,      new IntrinsicInfo(X86Instruction.Pcmpgtw,      IntrinsicType.Binary));
-            Add(Intrinsic.X86Pmaxsb,       new IntrinsicInfo(X86Instruction.Pmaxsb,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pmaxsd,       new IntrinsicInfo(X86Instruction.Pmaxsd,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pmaxsw,       new IntrinsicInfo(X86Instruction.Pmaxsw,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pmaxub,       new IntrinsicInfo(X86Instruction.Pmaxub,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pmaxud,       new IntrinsicInfo(X86Instruction.Pmaxud,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pmaxuw,       new IntrinsicInfo(X86Instruction.Pmaxuw,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pminsb,       new IntrinsicInfo(X86Instruction.Pminsb,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pminsd,       new IntrinsicInfo(X86Instruction.Pminsd,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pminsw,       new IntrinsicInfo(X86Instruction.Pminsw,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pminub,       new IntrinsicInfo(X86Instruction.Pminub,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pminud,       new IntrinsicInfo(X86Instruction.Pminud,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pminuw,       new IntrinsicInfo(X86Instruction.Pminuw,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pmovsxbw,     new IntrinsicInfo(X86Instruction.Pmovsxbw,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Pmovsxdq,     new IntrinsicInfo(X86Instruction.Pmovsxdq,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Pmovsxwd,     new IntrinsicInfo(X86Instruction.Pmovsxwd,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Pmovzxbw,     new IntrinsicInfo(X86Instruction.Pmovzxbw,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Pmovzxdq,     new IntrinsicInfo(X86Instruction.Pmovzxdq,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Pmovzxwd,     new IntrinsicInfo(X86Instruction.Pmovzxwd,     IntrinsicType.Unary));
-            Add(Intrinsic.X86Pmulld,       new IntrinsicInfo(X86Instruction.Pmulld,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pmullw,       new IntrinsicInfo(X86Instruction.Pmullw,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Popcnt,       new IntrinsicInfo(X86Instruction.Popcnt,       IntrinsicType.PopCount));
-            Add(Intrinsic.X86Por,          new IntrinsicInfo(X86Instruction.Por,          IntrinsicType.Binary));
-            Add(Intrinsic.X86Pshufb,       new IntrinsicInfo(X86Instruction.Pshufb,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Pshufd,       new IntrinsicInfo(X86Instruction.Pshufd,       IntrinsicType.BinaryImm));
-            Add(Intrinsic.X86Pslld,        new IntrinsicInfo(X86Instruction.Pslld,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Pslldq,       new IntrinsicInfo(X86Instruction.Pslldq,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Psllq,        new IntrinsicInfo(X86Instruction.Psllq,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Psllw,        new IntrinsicInfo(X86Instruction.Psllw,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Psrad,        new IntrinsicInfo(X86Instruction.Psrad,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Psraw,        new IntrinsicInfo(X86Instruction.Psraw,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Psrld,        new IntrinsicInfo(X86Instruction.Psrld,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Psrlq,        new IntrinsicInfo(X86Instruction.Psrlq,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Psrldq,       new IntrinsicInfo(X86Instruction.Psrldq,       IntrinsicType.Binary));
-            Add(Intrinsic.X86Psrlw,        new IntrinsicInfo(X86Instruction.Psrlw,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Psubb,        new IntrinsicInfo(X86Instruction.Psubb,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Psubd,        new IntrinsicInfo(X86Instruction.Psubd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Psubq,        new IntrinsicInfo(X86Instruction.Psubq,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Psubw,        new IntrinsicInfo(X86Instruction.Psubw,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Punpckhbw,    new IntrinsicInfo(X86Instruction.Punpckhbw,    IntrinsicType.Binary));
-            Add(Intrinsic.X86Punpckhdq,    new IntrinsicInfo(X86Instruction.Punpckhdq,    IntrinsicType.Binary));
-            Add(Intrinsic.X86Punpckhqdq,   new IntrinsicInfo(X86Instruction.Punpckhqdq,   IntrinsicType.Binary));
-            Add(Intrinsic.X86Punpckhwd,    new IntrinsicInfo(X86Instruction.Punpckhwd,    IntrinsicType.Binary));
-            Add(Intrinsic.X86Punpcklbw,    new IntrinsicInfo(X86Instruction.Punpcklbw,    IntrinsicType.Binary));
-            Add(Intrinsic.X86Punpckldq,    new IntrinsicInfo(X86Instruction.Punpckldq,    IntrinsicType.Binary));
-            Add(Intrinsic.X86Punpcklqdq,   new IntrinsicInfo(X86Instruction.Punpcklqdq,   IntrinsicType.Binary));
-            Add(Intrinsic.X86Punpcklwd,    new IntrinsicInfo(X86Instruction.Punpcklwd,    IntrinsicType.Binary));
-            Add(Intrinsic.X86Pxor,         new IntrinsicInfo(X86Instruction.Pxor,         IntrinsicType.Binary));
-            Add(Intrinsic.X86Rcpps,        new IntrinsicInfo(X86Instruction.Rcpps,        IntrinsicType.Unary));
-            Add(Intrinsic.X86Rcpss,        new IntrinsicInfo(X86Instruction.Rcpss,        IntrinsicType.Unary));
-            Add(Intrinsic.X86Roundpd,      new IntrinsicInfo(X86Instruction.Roundpd,      IntrinsicType.BinaryImm));
-            Add(Intrinsic.X86Roundps,      new IntrinsicInfo(X86Instruction.Roundps,      IntrinsicType.BinaryImm));
-            Add(Intrinsic.X86Roundsd,      new IntrinsicInfo(X86Instruction.Roundsd,      IntrinsicType.BinaryImm));
-            Add(Intrinsic.X86Roundss,      new IntrinsicInfo(X86Instruction.Roundss,      IntrinsicType.BinaryImm));
-            Add(Intrinsic.X86Rsqrtps,      new IntrinsicInfo(X86Instruction.Rsqrtps,      IntrinsicType.Unary));
-            Add(Intrinsic.X86Rsqrtss,      new IntrinsicInfo(X86Instruction.Rsqrtss,      IntrinsicType.Unary));
-            Add(Intrinsic.X86Shufpd,       new IntrinsicInfo(X86Instruction.Shufpd,       IntrinsicType.TernaryImm));
-            Add(Intrinsic.X86Shufps,       new IntrinsicInfo(X86Instruction.Shufps,       IntrinsicType.TernaryImm));
-            Add(Intrinsic.X86Sqrtpd,       new IntrinsicInfo(X86Instruction.Sqrtpd,       IntrinsicType.Unary));
-            Add(Intrinsic.X86Sqrtps,       new IntrinsicInfo(X86Instruction.Sqrtps,       IntrinsicType.Unary));
-            Add(Intrinsic.X86Sqrtsd,       new IntrinsicInfo(X86Instruction.Sqrtsd,       IntrinsicType.Unary));
-            Add(Intrinsic.X86Sqrtss,       new IntrinsicInfo(X86Instruction.Sqrtss,       IntrinsicType.Unary));
-            Add(Intrinsic.X86Subpd,        new IntrinsicInfo(X86Instruction.Subpd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Subps,        new IntrinsicInfo(X86Instruction.Subps,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Subsd,        new IntrinsicInfo(X86Instruction.Subsd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Subss,        new IntrinsicInfo(X86Instruction.Subss,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Unpckhpd,     new IntrinsicInfo(X86Instruction.Unpckhpd,     IntrinsicType.Binary));
-            Add(Intrinsic.X86Unpckhps,     new IntrinsicInfo(X86Instruction.Unpckhps,     IntrinsicType.Binary));
-            Add(Intrinsic.X86Unpcklpd,     new IntrinsicInfo(X86Instruction.Unpcklpd,     IntrinsicType.Binary));
-            Add(Intrinsic.X86Unpcklps,     new IntrinsicInfo(X86Instruction.Unpcklps,     IntrinsicType.Binary));
-            Add(Intrinsic.X86Vcvtph2ps,    new IntrinsicInfo(X86Instruction.Vcvtph2ps,    IntrinsicType.Unary));
-            Add(Intrinsic.X86Vcvtps2ph,    new IntrinsicInfo(X86Instruction.Vcvtps2ph,    IntrinsicType.BinaryImm));
-            Add(Intrinsic.X86Vfmadd231ps,  new IntrinsicInfo(X86Instruction.Vfmadd231ps,  IntrinsicType.Fma));
-            Add(Intrinsic.X86Vfmadd231sd,  new IntrinsicInfo(X86Instruction.Vfmadd231sd,  IntrinsicType.Fma));
-            Add(Intrinsic.X86Vfmadd231ss,  new IntrinsicInfo(X86Instruction.Vfmadd231ss,  IntrinsicType.Fma));
-            Add(Intrinsic.X86Vfmsub231sd,  new IntrinsicInfo(X86Instruction.Vfmsub231sd,  IntrinsicType.Fma));
-            Add(Intrinsic.X86Vfmsub231ss,  new IntrinsicInfo(X86Instruction.Vfmsub231ss,  IntrinsicType.Fma));
-            Add(Intrinsic.X86Vfnmadd231ps, new IntrinsicInfo(X86Instruction.Vfnmadd231ps, IntrinsicType.Fma));
-            Add(Intrinsic.X86Vfnmadd231sd, new IntrinsicInfo(X86Instruction.Vfnmadd231sd, IntrinsicType.Fma));
-            Add(Intrinsic.X86Vfnmadd231ss, new IntrinsicInfo(X86Instruction.Vfnmadd231ss, IntrinsicType.Fma));
-            Add(Intrinsic.X86Vfnmsub231sd, new IntrinsicInfo(X86Instruction.Vfnmsub231sd, IntrinsicType.Fma));
-            Add(Intrinsic.X86Vfnmsub231ss, new IntrinsicInfo(X86Instruction.Vfnmsub231ss, IntrinsicType.Fma));
-            Add(Intrinsic.X86Xorpd,        new IntrinsicInfo(X86Instruction.Xorpd,        IntrinsicType.Binary));
-            Add(Intrinsic.X86Xorps,        new IntrinsicInfo(X86Instruction.Xorps,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Addpd,         new IntrinsicInfo(X86Instruction.Addpd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Addps,         new IntrinsicInfo(X86Instruction.Addps,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Addsd,         new IntrinsicInfo(X86Instruction.Addsd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Addss,         new IntrinsicInfo(X86Instruction.Addss,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Aesdec,        new IntrinsicInfo(X86Instruction.Aesdec,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Aesdeclast,    new IntrinsicInfo(X86Instruction.Aesdeclast,    IntrinsicType.Binary));
+            Add(Intrinsic.X86Aesenc,        new IntrinsicInfo(X86Instruction.Aesenc,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Aesenclast,    new IntrinsicInfo(X86Instruction.Aesenclast,    IntrinsicType.Binary));
+            Add(Intrinsic.X86Aesimc,        new IntrinsicInfo(X86Instruction.Aesimc,        IntrinsicType.Unary));
+            Add(Intrinsic.X86Andnpd,        new IntrinsicInfo(X86Instruction.Andnpd,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Andnps,        new IntrinsicInfo(X86Instruction.Andnps,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Andpd,         new IntrinsicInfo(X86Instruction.Andpd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Andps,         new IntrinsicInfo(X86Instruction.Andps,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Blendvpd,      new IntrinsicInfo(X86Instruction.Blendvpd,      IntrinsicType.Ternary));
+            Add(Intrinsic.X86Blendvps,      new IntrinsicInfo(X86Instruction.Blendvps,      IntrinsicType.Ternary));
+            Add(Intrinsic.X86Cmppd,         new IntrinsicInfo(X86Instruction.Cmppd,         IntrinsicType.TernaryImm));
+            Add(Intrinsic.X86Cmpps,         new IntrinsicInfo(X86Instruction.Cmpps,         IntrinsicType.TernaryImm));
+            Add(Intrinsic.X86Cmpsd,         new IntrinsicInfo(X86Instruction.Cmpsd,         IntrinsicType.TernaryImm));
+            Add(Intrinsic.X86Cmpss,         new IntrinsicInfo(X86Instruction.Cmpss,         IntrinsicType.TernaryImm));
+            Add(Intrinsic.X86Comisdeq,      new IntrinsicInfo(X86Instruction.Comisd,        IntrinsicType.Comis_));
+            Add(Intrinsic.X86Comisdge,      new IntrinsicInfo(X86Instruction.Comisd,        IntrinsicType.Comis_));
+            Add(Intrinsic.X86Comisdlt,      new IntrinsicInfo(X86Instruction.Comisd,        IntrinsicType.Comis_));
+            Add(Intrinsic.X86Comisseq,      new IntrinsicInfo(X86Instruction.Comiss,        IntrinsicType.Comis_));
+            Add(Intrinsic.X86Comissge,      new IntrinsicInfo(X86Instruction.Comiss,        IntrinsicType.Comis_));
+            Add(Intrinsic.X86Comisslt,      new IntrinsicInfo(X86Instruction.Comiss,        IntrinsicType.Comis_));
+            Add(Intrinsic.X86Crc32,         new IntrinsicInfo(X86Instruction.Crc32,         IntrinsicType.Crc32));
+            Add(Intrinsic.X86Crc32_16,      new IntrinsicInfo(X86Instruction.Crc32_16,      IntrinsicType.Crc32));
+            Add(Intrinsic.X86Crc32_8,       new IntrinsicInfo(X86Instruction.Crc32_8,       IntrinsicType.Crc32));
+            Add(Intrinsic.X86Cvtdq2pd,      new IntrinsicInfo(X86Instruction.Cvtdq2pd,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Cvtdq2ps,      new IntrinsicInfo(X86Instruction.Cvtdq2ps,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Cvtpd2dq,      new IntrinsicInfo(X86Instruction.Cvtpd2dq,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Cvtpd2ps,      new IntrinsicInfo(X86Instruction.Cvtpd2ps,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Cvtps2dq,      new IntrinsicInfo(X86Instruction.Cvtps2dq,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Cvtps2pd,      new IntrinsicInfo(X86Instruction.Cvtps2pd,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Cvtsd2si,      new IntrinsicInfo(X86Instruction.Cvtsd2si,      IntrinsicType.UnaryToGpr));
+            Add(Intrinsic.X86Cvtsd2ss,      new IntrinsicInfo(X86Instruction.Cvtsd2ss,      IntrinsicType.Binary));
+            Add(Intrinsic.X86Cvtsi2sd,      new IntrinsicInfo(X86Instruction.Cvtsi2sd,      IntrinsicType.BinaryGpr));
+            Add(Intrinsic.X86Cvtsi2si,      new IntrinsicInfo(X86Instruction.Movd,          IntrinsicType.UnaryToGpr));
+            Add(Intrinsic.X86Cvtsi2ss,      new IntrinsicInfo(X86Instruction.Cvtsi2ss,      IntrinsicType.BinaryGpr));
+            Add(Intrinsic.X86Cvtss2sd,      new IntrinsicInfo(X86Instruction.Cvtss2sd,      IntrinsicType.Binary));
+            Add(Intrinsic.X86Cvtss2si,      new IntrinsicInfo(X86Instruction.Cvtss2si,      IntrinsicType.UnaryToGpr));
+            Add(Intrinsic.X86Divpd,         new IntrinsicInfo(X86Instruction.Divpd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Divps,         new IntrinsicInfo(X86Instruction.Divps,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Divsd,         new IntrinsicInfo(X86Instruction.Divsd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Divss,         new IntrinsicInfo(X86Instruction.Divss,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Gf2p8affineqb, new IntrinsicInfo(X86Instruction.Gf2p8affineqb, IntrinsicType.TernaryImm));
+            Add(Intrinsic.X86Haddpd,        new IntrinsicInfo(X86Instruction.Haddpd,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Haddps,        new IntrinsicInfo(X86Instruction.Haddps,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Insertps,      new IntrinsicInfo(X86Instruction.Insertps,      IntrinsicType.TernaryImm));
+            Add(Intrinsic.X86Maxpd,         new IntrinsicInfo(X86Instruction.Maxpd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Maxps,         new IntrinsicInfo(X86Instruction.Maxps,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Maxsd,         new IntrinsicInfo(X86Instruction.Maxsd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Maxss,         new IntrinsicInfo(X86Instruction.Maxss,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Minpd,         new IntrinsicInfo(X86Instruction.Minpd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Minps,         new IntrinsicInfo(X86Instruction.Minps,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Minsd,         new IntrinsicInfo(X86Instruction.Minsd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Minss,         new IntrinsicInfo(X86Instruction.Minss,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Movhlps,       new IntrinsicInfo(X86Instruction.Movhlps,       IntrinsicType.Binary));
+            Add(Intrinsic.X86Movlhps,       new IntrinsicInfo(X86Instruction.Movlhps,       IntrinsicType.Binary));
+            Add(Intrinsic.X86Movss,         new IntrinsicInfo(X86Instruction.Movss,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Mulpd,         new IntrinsicInfo(X86Instruction.Mulpd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Mulps,         new IntrinsicInfo(X86Instruction.Mulps,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Mulsd,         new IntrinsicInfo(X86Instruction.Mulsd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Mulss,         new IntrinsicInfo(X86Instruction.Mulss,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Mxcsrmb,       new IntrinsicInfo(X86Instruction.None,          IntrinsicType.Mxcsr)); // Mask bits.
+            Add(Intrinsic.X86Mxcsrub,       new IntrinsicInfo(X86Instruction.None,          IntrinsicType.Mxcsr)); // Unmask bits.
+            Add(Intrinsic.X86Paddb,         new IntrinsicInfo(X86Instruction.Paddb,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Paddd,         new IntrinsicInfo(X86Instruction.Paddd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Paddq,         new IntrinsicInfo(X86Instruction.Paddq,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Paddw,         new IntrinsicInfo(X86Instruction.Paddw,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Palignr,       new IntrinsicInfo(X86Instruction.Palignr,       IntrinsicType.TernaryImm));
+            Add(Intrinsic.X86Pand,          new IntrinsicInfo(X86Instruction.Pand,          IntrinsicType.Binary));
+            Add(Intrinsic.X86Pandn,         new IntrinsicInfo(X86Instruction.Pandn,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Pavgb,         new IntrinsicInfo(X86Instruction.Pavgb,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Pavgw,         new IntrinsicInfo(X86Instruction.Pavgw,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Pblendvb,      new IntrinsicInfo(X86Instruction.Pblendvb,      IntrinsicType.Ternary));
+            Add(Intrinsic.X86Pclmulqdq,     new IntrinsicInfo(X86Instruction.Pclmulqdq,     IntrinsicType.TernaryImm));
+            Add(Intrinsic.X86Pcmpeqb,       new IntrinsicInfo(X86Instruction.Pcmpeqb,       IntrinsicType.Binary));
+            Add(Intrinsic.X86Pcmpeqd,       new IntrinsicInfo(X86Instruction.Pcmpeqd,       IntrinsicType.Binary));
+            Add(Intrinsic.X86Pcmpeqq,       new IntrinsicInfo(X86Instruction.Pcmpeqq,       IntrinsicType.Binary));
+            Add(Intrinsic.X86Pcmpeqw,       new IntrinsicInfo(X86Instruction.Pcmpeqw,       IntrinsicType.Binary));
+            Add(Intrinsic.X86Pcmpgtb,       new IntrinsicInfo(X86Instruction.Pcmpgtb,       IntrinsicType.Binary));
+            Add(Intrinsic.X86Pcmpgtd,       new IntrinsicInfo(X86Instruction.Pcmpgtd,       IntrinsicType.Binary));
+            Add(Intrinsic.X86Pcmpgtq,       new IntrinsicInfo(X86Instruction.Pcmpgtq,       IntrinsicType.Binary));
+            Add(Intrinsic.X86Pcmpgtw,       new IntrinsicInfo(X86Instruction.Pcmpgtw,       IntrinsicType.Binary));
+            Add(Intrinsic.X86Pmaxsb,        new IntrinsicInfo(X86Instruction.Pmaxsb,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pmaxsd,        new IntrinsicInfo(X86Instruction.Pmaxsd,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pmaxsw,        new IntrinsicInfo(X86Instruction.Pmaxsw,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pmaxub,        new IntrinsicInfo(X86Instruction.Pmaxub,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pmaxud,        new IntrinsicInfo(X86Instruction.Pmaxud,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pmaxuw,        new IntrinsicInfo(X86Instruction.Pmaxuw,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pminsb,        new IntrinsicInfo(X86Instruction.Pminsb,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pminsd,        new IntrinsicInfo(X86Instruction.Pminsd,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pminsw,        new IntrinsicInfo(X86Instruction.Pminsw,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pminub,        new IntrinsicInfo(X86Instruction.Pminub,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pminud,        new IntrinsicInfo(X86Instruction.Pminud,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pminuw,        new IntrinsicInfo(X86Instruction.Pminuw,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pmovsxbw,      new IntrinsicInfo(X86Instruction.Pmovsxbw,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Pmovsxdq,      new IntrinsicInfo(X86Instruction.Pmovsxdq,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Pmovsxwd,      new IntrinsicInfo(X86Instruction.Pmovsxwd,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Pmovzxbw,      new IntrinsicInfo(X86Instruction.Pmovzxbw,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Pmovzxdq,      new IntrinsicInfo(X86Instruction.Pmovzxdq,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Pmovzxwd,      new IntrinsicInfo(X86Instruction.Pmovzxwd,      IntrinsicType.Unary));
+            Add(Intrinsic.X86Pmulld,        new IntrinsicInfo(X86Instruction.Pmulld,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pmullw,        new IntrinsicInfo(X86Instruction.Pmullw,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Popcnt,        new IntrinsicInfo(X86Instruction.Popcnt,        IntrinsicType.PopCount));
+            Add(Intrinsic.X86Por,           new IntrinsicInfo(X86Instruction.Por,           IntrinsicType.Binary));
+            Add(Intrinsic.X86Pshufb,        new IntrinsicInfo(X86Instruction.Pshufb,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Pshufd,        new IntrinsicInfo(X86Instruction.Pshufd,        IntrinsicType.BinaryImm));
+            Add(Intrinsic.X86Pslld,         new IntrinsicInfo(X86Instruction.Pslld,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Pslldq,        new IntrinsicInfo(X86Instruction.Pslldq,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Psllq,         new IntrinsicInfo(X86Instruction.Psllq,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Psllw,         new IntrinsicInfo(X86Instruction.Psllw,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Psrad,         new IntrinsicInfo(X86Instruction.Psrad,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Psraw,         new IntrinsicInfo(X86Instruction.Psraw,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Psrld,         new IntrinsicInfo(X86Instruction.Psrld,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Psrlq,         new IntrinsicInfo(X86Instruction.Psrlq,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Psrldq,        new IntrinsicInfo(X86Instruction.Psrldq,        IntrinsicType.Binary));
+            Add(Intrinsic.X86Psrlw,         new IntrinsicInfo(X86Instruction.Psrlw,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Psubb,         new IntrinsicInfo(X86Instruction.Psubb,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Psubd,         new IntrinsicInfo(X86Instruction.Psubd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Psubq,         new IntrinsicInfo(X86Instruction.Psubq,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Psubw,         new IntrinsicInfo(X86Instruction.Psubw,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Punpckhbw,     new IntrinsicInfo(X86Instruction.Punpckhbw,     IntrinsicType.Binary));
+            Add(Intrinsic.X86Punpckhdq,     new IntrinsicInfo(X86Instruction.Punpckhdq,     IntrinsicType.Binary));
+            Add(Intrinsic.X86Punpckhqdq,    new IntrinsicInfo(X86Instruction.Punpckhqdq,    IntrinsicType.Binary));
+            Add(Intrinsic.X86Punpckhwd,     new IntrinsicInfo(X86Instruction.Punpckhwd,     IntrinsicType.Binary));
+            Add(Intrinsic.X86Punpcklbw,     new IntrinsicInfo(X86Instruction.Punpcklbw,     IntrinsicType.Binary));
+            Add(Intrinsic.X86Punpckldq,     new IntrinsicInfo(X86Instruction.Punpckldq,     IntrinsicType.Binary));
+            Add(Intrinsic.X86Punpcklqdq,    new IntrinsicInfo(X86Instruction.Punpcklqdq,    IntrinsicType.Binary));
+            Add(Intrinsic.X86Punpcklwd,     new IntrinsicInfo(X86Instruction.Punpcklwd,     IntrinsicType.Binary));
+            Add(Intrinsic.X86Pxor,          new IntrinsicInfo(X86Instruction.Pxor,          IntrinsicType.Binary));
+            Add(Intrinsic.X86Rcpps,         new IntrinsicInfo(X86Instruction.Rcpps,         IntrinsicType.Unary));
+            Add(Intrinsic.X86Rcpss,         new IntrinsicInfo(X86Instruction.Rcpss,         IntrinsicType.Unary));
+            Add(Intrinsic.X86Roundpd,       new IntrinsicInfo(X86Instruction.Roundpd,       IntrinsicType.BinaryImm));
+            Add(Intrinsic.X86Roundps,       new IntrinsicInfo(X86Instruction.Roundps,       IntrinsicType.BinaryImm));
+            Add(Intrinsic.X86Roundsd,       new IntrinsicInfo(X86Instruction.Roundsd,       IntrinsicType.BinaryImm));
+            Add(Intrinsic.X86Roundss,       new IntrinsicInfo(X86Instruction.Roundss,       IntrinsicType.BinaryImm));
+            Add(Intrinsic.X86Rsqrtps,       new IntrinsicInfo(X86Instruction.Rsqrtps,       IntrinsicType.Unary));
+            Add(Intrinsic.X86Rsqrtss,       new IntrinsicInfo(X86Instruction.Rsqrtss,       IntrinsicType.Unary));
+            Add(Intrinsic.X86Sha256Msg1,    new IntrinsicInfo(X86Instruction.Sha256Msg1,    IntrinsicType.Binary));
+            Add(Intrinsic.X86Sha256Msg2,    new IntrinsicInfo(X86Instruction.Sha256Msg2,    IntrinsicType.Binary));
+            Add(Intrinsic.X86Sha256Rnds2,   new IntrinsicInfo(X86Instruction.Sha256Rnds2,   IntrinsicType.Ternary));
+            Add(Intrinsic.X86Shufpd,        new IntrinsicInfo(X86Instruction.Shufpd,        IntrinsicType.TernaryImm));
+            Add(Intrinsic.X86Shufps,        new IntrinsicInfo(X86Instruction.Shufps,        IntrinsicType.TernaryImm));
+            Add(Intrinsic.X86Sqrtpd,        new IntrinsicInfo(X86Instruction.Sqrtpd,        IntrinsicType.Unary));
+            Add(Intrinsic.X86Sqrtps,        new IntrinsicInfo(X86Instruction.Sqrtps,        IntrinsicType.Unary));
+            Add(Intrinsic.X86Sqrtsd,        new IntrinsicInfo(X86Instruction.Sqrtsd,        IntrinsicType.Unary));
+            Add(Intrinsic.X86Sqrtss,        new IntrinsicInfo(X86Instruction.Sqrtss,        IntrinsicType.Unary));
+            Add(Intrinsic.X86Subpd,         new IntrinsicInfo(X86Instruction.Subpd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Subps,         new IntrinsicInfo(X86Instruction.Subps,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Subsd,         new IntrinsicInfo(X86Instruction.Subsd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Subss,         new IntrinsicInfo(X86Instruction.Subss,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Unpckhpd,      new IntrinsicInfo(X86Instruction.Unpckhpd,      IntrinsicType.Binary));
+            Add(Intrinsic.X86Unpckhps,      new IntrinsicInfo(X86Instruction.Unpckhps,      IntrinsicType.Binary));
+            Add(Intrinsic.X86Unpcklpd,      new IntrinsicInfo(X86Instruction.Unpcklpd,      IntrinsicType.Binary));
+            Add(Intrinsic.X86Unpcklps,      new IntrinsicInfo(X86Instruction.Unpcklps,      IntrinsicType.Binary));
+            Add(Intrinsic.X86Vcvtph2ps,     new IntrinsicInfo(X86Instruction.Vcvtph2ps,     IntrinsicType.Unary));
+            Add(Intrinsic.X86Vcvtps2ph,     new IntrinsicInfo(X86Instruction.Vcvtps2ph,     IntrinsicType.BinaryImm));
+            Add(Intrinsic.X86Vfmadd231ps,   new IntrinsicInfo(X86Instruction.Vfmadd231ps,   IntrinsicType.Fma));
+            Add(Intrinsic.X86Vfmadd231sd,   new IntrinsicInfo(X86Instruction.Vfmadd231sd,   IntrinsicType.Fma));
+            Add(Intrinsic.X86Vfmadd231ss,   new IntrinsicInfo(X86Instruction.Vfmadd231ss,   IntrinsicType.Fma));
+            Add(Intrinsic.X86Vfmsub231sd,   new IntrinsicInfo(X86Instruction.Vfmsub231sd,   IntrinsicType.Fma));
+            Add(Intrinsic.X86Vfmsub231ss,   new IntrinsicInfo(X86Instruction.Vfmsub231ss,   IntrinsicType.Fma));
+            Add(Intrinsic.X86Vfnmadd231ps,  new IntrinsicInfo(X86Instruction.Vfnmadd231ps,  IntrinsicType.Fma));
+            Add(Intrinsic.X86Vfnmadd231sd,  new IntrinsicInfo(X86Instruction.Vfnmadd231sd,  IntrinsicType.Fma));
+            Add(Intrinsic.X86Vfnmadd231ss,  new IntrinsicInfo(X86Instruction.Vfnmadd231ss,  IntrinsicType.Fma));
+            Add(Intrinsic.X86Vfnmsub231sd,  new IntrinsicInfo(X86Instruction.Vfnmsub231sd,  IntrinsicType.Fma));
+            Add(Intrinsic.X86Vfnmsub231ss,  new IntrinsicInfo(X86Instruction.Vfnmsub231ss,  IntrinsicType.Fma));
+            Add(Intrinsic.X86Xorpd,         new IntrinsicInfo(X86Instruction.Xorpd,         IntrinsicType.Binary));
+            Add(Intrinsic.X86Xorps,         new IntrinsicInfo(X86Instruction.Xorps,         IntrinsicType.Binary));
         }
 
         private static void Add(Intrinsic intrin, IntrinsicInfo info)

ARMeilleure/CodeGen/X86/PreAllocator.cs

@@ -2,19 +2,20 @@ using ARMeilleure.CodeGen.RegisterAllocators;
 using ARMeilleure.IntermediateRepresentation;
 using ARMeilleure.Translation;
 using System;
-using System.Collections.Generic;
 using System.Diagnostics;
 using static ARMeilleure.IntermediateRepresentation.Operand.Factory;
 using static ARMeilleure.IntermediateRepresentation.Operation.Factory;
 
 namespace ARMeilleure.CodeGen.X86
 {
-    static class PreAllocator
+    class PreAllocator
     {
         public static void RunPass(CompilerContext cctx, StackAllocator stackAlloc, out int maxCallArgs)
         {
             maxCallArgs = -1;
 
+            Span<Operation> buffer = default;
+
             CallConvName callConv = CallingConvention.GetCurrentCallConv();
 
             Operand[] preservedArgs = new Operand[CallingConvention.GetArgumentsOnRegsCount()];
@@ -32,9 +33,9 @@ namespace ARMeilleure.CodeGen.X86
                         continue;
                     }
 
-                    HandleConstantRegCopy(block.Operations, node);
-                    HandleDestructiveRegCopy(block.Operations, node);
-                    HandleConstrainedRegCopy(block.Operations, node);
+                    InsertConstantRegCopies(block.Operations, node);
+                    InsertDestructiveRegCopies(block.Operations, node);
+                    InsertConstrainedRegCopies(block.Operations, node);
 
                     switch (node.Instruction)
                     {
@@ -59,62 +60,62 @@ namespace ARMeilleure.CodeGen.X86
                             // being called, as mandated by the ABI.
                             if (callConv == CallConvName.Windows)
                             {
-                                HandleCallWindowsAbi(block.Operations, stackAlloc, node);
+                                PreAllocatorWindows.InsertCallCopies(block.Operations, stackAlloc, node);
                             }
                             else /* if (callConv == CallConvName.SystemV) */
                             {
-                                HandleCallSystemVAbi(block.Operations, node);
+                                PreAllocatorSystemV.InsertCallCopies(block.Operations, node);
                             }
                             break;
 
                         case Instruction.ConvertToFPUI:
-                            HandleConvertToFPUI(block.Operations, node);
+                            GenerateConvertToFPUI(block.Operations, node);
                             break;
 
                         case Instruction.LoadArgument:
                             if (callConv == CallConvName.Windows)
                             {
-                                nextNode = HandleLoadArgumentWindowsAbi(cctx, block.Operations, preservedArgs, node);
+                                nextNode = PreAllocatorWindows.InsertLoadArgumentCopy(cctx, ref buffer, block.Operations, preservedArgs, node);
                             }
                             else /* if (callConv == CallConvName.SystemV) */
                             {
-                                nextNode = HandleLoadArgumentSystemVAbi(cctx, block.Operations, preservedArgs, node);
+                                nextNode = PreAllocatorSystemV.InsertLoadArgumentCopy(cctx, ref buffer, block.Operations, preservedArgs, node);
                             }
                             break;
 
                         case Instruction.Negate:
                             if (!node.GetSource(0).Type.IsInteger())
                             {
-                                HandleNegate(block.Operations, node);
+                                GenerateNegate(block.Operations, node);
                             }
                             break;
 
                         case Instruction.Return:
                             if (callConv == CallConvName.Windows)
                             {
-                                HandleReturnWindowsAbi(cctx, block.Operations, preservedArgs, node);
+                                PreAllocatorWindows.InsertReturnCopy(cctx, block.Operations, preservedArgs, node);
                             }
                             else /* if (callConv == CallConvName.SystemV) */
                             {
-                                HandleReturnSystemVAbi(block.Operations, node);
+                                PreAllocatorSystemV.InsertReturnCopy(block.Operations, node);
                             }
                             break;
 
                         case Instruction.Tailcall:
                             if (callConv == CallConvName.Windows)
                             {
-                                HandleTailcallWindowsAbi(block.Operations, stackAlloc, node);
+                                PreAllocatorWindows.InsertTailcallCopies(block.Operations, stackAlloc, node);
                             }
                             else
                             {
-                                HandleTailcallSystemVAbi(block.Operations, stackAlloc, node);
+                                PreAllocatorSystemV.InsertTailcallCopies(block.Operations, stackAlloc, node);
                             }
                             break;
 
                         case Instruction.VectorInsert8:
                             if (!HardwareCapabilities.SupportsSse41)
                             {
-                                HandleVectorInsert8(block.Operations, node);
+                                GenerateVectorInsert8(block.Operations, node);
                             }
                             break;
 
@@ -131,7 +132,7 @@ namespace ARMeilleure.CodeGen.X86
             }
         }
 
-        private static void HandleConstantRegCopy(IntrusiveList<Operation> nodes, Operation node)
+        protected static void InsertConstantRegCopies(IntrusiveList<Operation> nodes, Operation node)
         {
             if (node.SourcesCount == 0 || IsXmmIntrinsic(node))
             {
@@ -212,7 +213,7 @@ namespace ARMeilleure.CodeGen.X86
             }
         }
 
-        private static void HandleConstrainedRegCopy(IntrusiveList<Operation> nodes, Operation node)
+        protected static void InsertConstrainedRegCopies(IntrusiveList<Operation> nodes, Operation node)
         {
             Operand dest = node.Destination;
 
@@ -308,11 +309,13 @@ namespace ARMeilleure.CodeGen.X86
 
                 case Instruction.Extended:
                 {
+                    bool isBlend = node.Intrinsic == Intrinsic.X86Blendvpd ||
+                                   node.Intrinsic == Intrinsic.X86Blendvps ||
+                                   node.Intrinsic == Intrinsic.X86Pblendvb;
+
                     // BLENDVPD, BLENDVPS, PBLENDVB last operand is always implied to be XMM0 when VEX is not supported.
-                    if ((node.Intrinsic == Intrinsic.X86Blendvpd ||
-                         node.Intrinsic == Intrinsic.X86Blendvps ||
-                         node.Intrinsic == Intrinsic.X86Pblendvb) &&
-                         !HardwareCapabilities.SupportsVexEncoding)
+                    // SHA256RNDS2 always has an implied XMM0 as a last operand.
+                    if ((isBlend && !HardwareCapabilities.SupportsVexEncoding) || node.Intrinsic == Intrinsic.X86Sha256Rnds2)
                     {
                         Operand xmm0 = Xmm(X86Register.Xmm0, OperandType.V128);
 
@@ -367,7 +370,7 @@ namespace ARMeilleure.CodeGen.X86
             }
         }
 
-        private static void HandleDestructiveRegCopy(IntrusiveList<Operation> nodes, Operation node)
+        protected static void InsertDestructiveRegCopies(IntrusiveList<Operation> nodes, Operation node)
         {
             if (node.Destination == default || node.SourcesCount == 0)
             {
@@ -445,7 +448,7 @@ namespace ARMeilleure.CodeGen.X86
             }
         }
 
-        private static void HandleConvertToFPUI(IntrusiveList<Operation> nodes, Operation node)
+        private static void GenerateConvertToFPUI(IntrusiveList<Operation> nodes, Operation node)
         {
             // Unsigned integer to FP conversions are not supported on X86.
             // We need to turn them into signed integer to FP conversions, and
@@ -499,7 +502,7 @@ namespace ARMeilleure.CodeGen.X86
             Delete(nodes, currentNode);
         }
 
-        private static void HandleNegate(IntrusiveList<Operation> nodes, Operation node)
+        private static void GenerateNegate(IntrusiveList<Operation> nodes, Operation node)
         {
             // There's no SSE FP negate instruction, so we need to transform that into
             // a XOR of the value to be negated with a mask with the highest bit set.
@@ -532,7 +535,7 @@ namespace ARMeilleure.CodeGen.X86
             Delete(nodes, currentNode);
         }
 
-        private static void HandleVectorInsert8(IntrusiveList<Operation> nodes, Operation node)
+        private static void GenerateVectorInsert8(IntrusiveList<Operation> nodes, Operation node)
         {
             // Handle vector insertion, when SSE 4.1 is not supported.
             Operand dest = node.Destination;
@@ -577,620 +580,7 @@ namespace ARMeilleure.CodeGen.X86
             Delete(nodes, currentNode);
         }
 
-        private static void HandleCallWindowsAbi(IntrusiveList<Operation> nodes, StackAllocator stackAlloc, Operation node)
-        {
-            Operand dest = node.Destination;
-
-            // Handle struct arguments.
-            int retArgs = 0;
-            int stackAllocOffset = 0;
-
-            int AllocateOnStack(int size)
-            {
-                // We assume that the stack allocator is initially empty (TotalSize = 0).
-                // Taking that into account, we can reuse the space allocated for other
-                // calls by keeping track of our own allocated size (stackAllocOffset).
-                // If the space allocated is not big enough, then we just expand it.
-                int offset = stackAllocOffset;
-
-                if (stackAllocOffset + size > stackAlloc.TotalSize)
-                {
-                    stackAlloc.Allocate((stackAllocOffset + size) - stackAlloc.TotalSize);
-                }
-
-                stackAllocOffset += size;
-
-                return offset;
-            }
-
-            Operand arg0Reg = default;
-
-            if (dest != default && dest.Type == OperandType.V128)
-            {
-                int stackOffset = AllocateOnStack(dest.Type.GetSizeInBytes());
-
-                arg0Reg = Gpr(CallingConvention.GetIntArgumentRegister(0), OperandType.I64);
-
-                Operation allocOp = Operation(Instruction.StackAlloc, arg0Reg, Const(stackOffset));
-
-                nodes.AddBefore(node, allocOp);
-
-                retArgs = 1;
-            }
-
-            int argsCount = node.SourcesCount - 1;
-            int maxArgs = CallingConvention.GetArgumentsOnRegsCount() - retArgs;
-
-            if (argsCount > maxArgs)
-            {
-                argsCount = maxArgs;
-            }
-
-            Operand[] sources = new Operand[1 + retArgs + argsCount];
-
-            sources[0] = node.GetSource(0);
-
-            if (arg0Reg != default)
-            {
-                sources[1] = arg0Reg;
-            }
-
-            for (int index = 1; index < node.SourcesCount; index++)
-            {
-                Operand source = node.GetSource(index);
-
-                if (source.Type == OperandType.V128)
-                {
-                    Operand stackAddr = Local(OperandType.I64);
-
-                    int stackOffset = AllocateOnStack(source.Type.GetSizeInBytes());
-
-                    nodes.AddBefore(node, Operation(Instruction.StackAlloc, stackAddr, Const(stackOffset)));
-
-                    Operation storeOp = Operation(Instruction.Store, default, stackAddr, source);
-
-                    HandleConstantRegCopy(nodes, nodes.AddBefore(node, storeOp));
-
-                    node.SetSource(index, stackAddr);
-                }
-            }
-
-            // Handle arguments passed on registers.
-            for (int index = 0; index < argsCount; index++)
-            {
-                Operand source = node.GetSource(index + 1);
-                Operand argReg;
-
-                int argIndex = index + retArgs;
-
-                if (source.Type.IsInteger())
-                {
-                    argReg = Gpr(CallingConvention.GetIntArgumentRegister(argIndex), source.Type);
-                }
-                else
-                {
-                    argReg = Xmm(CallingConvention.GetVecArgumentRegister(argIndex), source.Type);
-                }
-
-                Operation copyOp = Operation(Instruction.Copy, argReg, source);
-
-                HandleConstantRegCopy(nodes, nodes.AddBefore(node, copyOp));
-
-                sources[1 + retArgs + index] = argReg;
-            }
-
-            // The remaining arguments (those that are not passed on registers)
-            // should be passed on the stack, we write them to the stack with "SpillArg".
-            for (int index = argsCount; index < node.SourcesCount - 1; index++)
-            {
-                Operand source = node.GetSource(index + 1);
-                Operand offset = Const((index + retArgs) * 8);
-
-                Operation spillOp = Operation(Instruction.SpillArg, default, offset, source);
-
-                HandleConstantRegCopy(nodes, nodes.AddBefore(node, spillOp));
-            }
-
-            if (dest != default)
-            {
-                if (dest.Type == OperandType.V128)
-                {
-                    Operand retValueAddr = Local(OperandType.I64);
-
-                    nodes.AddBefore(node, Operation(Instruction.Copy, retValueAddr, arg0Reg));
-
-                    Operation loadOp = Operation(Instruction.Load, dest, retValueAddr);
-
-                    nodes.AddAfter(node, loadOp);
-
-                    node.Destination = default;
-                }
-                else
-                {
-                    Operand retReg = dest.Type.IsInteger()
-                        ? Gpr(CallingConvention.GetIntReturnRegister(), dest.Type)
-                        : Xmm(CallingConvention.GetVecReturnRegister(), dest.Type);
-
-                    Operation copyOp = Operation(Instruction.Copy, dest, retReg);
-
-                    nodes.AddAfter(node, copyOp);
-
-                    node.Destination = retReg;
-                }
-            }
-
-            node.SetSources(sources);
-        }
-
-        private static void HandleCallSystemVAbi(IntrusiveList<Operation> nodes, Operation node)
-        {
-            Operand dest = node.Destination;
-
-            List<Operand> sources = new List<Operand>
-            {
-                node.GetSource(0)
-            };
-
-            int argsCount = node.SourcesCount - 1;
-
-            int intMax = CallingConvention.GetIntArgumentsOnRegsCount();
-            int vecMax = CallingConvention.GetVecArgumentsOnRegsCount();
-
-            int intCount = 0;
-            int vecCount = 0;
-
-            int stackOffset = 0;
-
-            for (int index = 0; index < argsCount; index++)
-            {
-                Operand source = node.GetSource(index + 1);
-
-                bool passOnReg;
-
-                if (source.Type.IsInteger())
-                {
-                    passOnReg = intCount < intMax;
-                }
-                else if (source.Type == OperandType.V128)
-                {
-                    passOnReg = intCount + 1 < intMax;
-                }
-                else
-                {
-                    passOnReg = vecCount < vecMax;
-                }
-
-                if (source.Type == OperandType.V128 && passOnReg)
-                {
-                    // V128 is a struct, we pass each half on a GPR if possible.
-                    Operand argReg  = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
-                    Operand argReg2 = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
-
-                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg,  source, Const(0)));
-                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg2, source, Const(1)));
-
-                    continue;
-                }
-
-                if (passOnReg)
-                {
-                    Operand argReg = source.Type.IsInteger()
-                        ? Gpr(CallingConvention.GetIntArgumentRegister(intCount++), source.Type)
-                        : Xmm(CallingConvention.GetVecArgumentRegister(vecCount++), source.Type);
-
-                    Operation copyOp = Operation(Instruction.Copy, argReg, source);
-
-                    HandleConstantRegCopy(nodes, nodes.AddBefore(node, copyOp));
-
-                    sources.Add(argReg);
-                }
-                else
-                {
-                    Operand offset = Const(stackOffset);
-
-                    Operation spillOp = Operation(Instruction.SpillArg, default, offset, source);
-
-                    HandleConstantRegCopy(nodes, nodes.AddBefore(node, spillOp));
-
-                    stackOffset += source.Type.GetSizeInBytes();
-                }
-            }
-
-            node.SetSources(sources.ToArray());
-
-            if (dest != default)
-            {
-                if (dest.Type == OperandType.V128)
-                {
-                    Operand retLReg = Gpr(CallingConvention.GetIntReturnRegister(),     OperandType.I64);
-                    Operand retHReg = Gpr(CallingConvention.GetIntReturnRegisterHigh(), OperandType.I64);
-
-                    Operation operation = node;
-
-                    node = nodes.AddAfter(node, Operation(Instruction.VectorCreateScalar, dest, retLReg));
-                    nodes.AddAfter(node, Operation(Instruction.VectorInsert, dest, dest, retHReg, Const(1)));
-
-                    operation.Destination = default;
-                }
-                else
-                {
-                    Operand retReg = dest.Type.IsInteger()
-                        ? Gpr(CallingConvention.GetIntReturnRegister(), dest.Type)
-                        : Xmm(CallingConvention.GetVecReturnRegister(), dest.Type);
-
-                    Operation copyOp = Operation(Instruction.Copy, dest, retReg);
-
-                    nodes.AddAfter(node, copyOp);
-
-                    node.Destination = retReg;
-                }
-            }
-        }
-
-        private static void HandleTailcallSystemVAbi(IntrusiveList<Operation> nodes, StackAllocator stackAlloc, Operation node)
-        {
-            List<Operand> sources = new List<Operand>
-            {
-                node.GetSource(0)
-            };
-
-            int argsCount = node.SourcesCount - 1;
-
-            int intMax = CallingConvention.GetIntArgumentsOnRegsCount();
-            int vecMax = CallingConvention.GetVecArgumentsOnRegsCount();
-
-            int intCount = 0;
-            int vecCount = 0;
-
-            // Handle arguments passed on registers.
-            for (int index = 0; index < argsCount; index++)
-            {
-                Operand source = node.GetSource(1 + index);
-
-                bool passOnReg;
-
-                if (source.Type.IsInteger())
-                {
-                    passOnReg = intCount + 1 < intMax;
-                }
-                else
-                {
-                    passOnReg = vecCount < vecMax;
-                }
-
-                if (source.Type == OperandType.V128 && passOnReg)
-                {
-                    // V128 is a struct, we pass each half on a GPR if possible.
-                    Operand argReg = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
-                    Operand argReg2 = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
-
-                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg, source, Const(0)));
-                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg2, source, Const(1)));
-
-                    continue;
-                }
-
-                if (passOnReg)
-                {
-                    Operand argReg = source.Type.IsInteger()
-                        ? Gpr(CallingConvention.GetIntArgumentRegister(intCount++), source.Type)
-                        : Xmm(CallingConvention.GetVecArgumentRegister(vecCount++), source.Type);
-
-                    Operation copyOp = Operation(Instruction.Copy, argReg, source);
-
-                    HandleConstantRegCopy(nodes, nodes.AddBefore(node, copyOp));
-
-                    sources.Add(argReg);
-                }
-                else
-                {
-                    throw new NotImplementedException("Spilling is not currently supported for tail calls. (too many arguments)");
-                }
-            }
-
-            // The target address must be on the return registers, since we
-            // don't return anything and it is guaranteed to not be a
-            // callee saved register (which would be trashed on the epilogue).
-            Operand retReg = Gpr(CallingConvention.GetIntReturnRegister(), OperandType.I64);
-
-            Operation addrCopyOp = Operation(Instruction.Copy, retReg, node.GetSource(0));
-
-            nodes.AddBefore(node, addrCopyOp);
-
-            sources[0] = retReg;
-
-            node.SetSources(sources.ToArray());
-        }
-
-        private static void HandleTailcallWindowsAbi(IntrusiveList<Operation> nodes, StackAllocator stackAlloc, Operation node)
-        {
-            int argsCount = node.SourcesCount - 1;
-            int maxArgs = CallingConvention.GetArgumentsOnRegsCount();
-
-            if (argsCount > maxArgs)
-            {
-                throw new NotImplementedException("Spilling is not currently supported for tail calls. (too many arguments)");
-            }
-
-            Operand[] sources = new Operand[1 + argsCount];
-
-            // Handle arguments passed on registers.
-            for (int index = 0; index < argsCount; index++)
-            {
-                Operand source = node.GetSource(1 + index);
-                Operand argReg = source.Type.IsInteger()
-                    ? Gpr(CallingConvention.GetIntArgumentRegister(index), source.Type)
-                    : Xmm(CallingConvention.GetVecArgumentRegister(index), source.Type);
-
-                Operation copyOp = Operation(Instruction.Copy, argReg, source);
-
-                HandleConstantRegCopy(nodes, nodes.AddBefore(node, copyOp));
-
-                sources[1 + index] = argReg;
-            }
-
-            // The target address must be on the return registers, since we
-            // don't return anything and it is guaranteed to not be a
-            // callee saved register (which would be trashed on the epilogue).
-            Operand retReg = Gpr(CallingConvention.GetIntReturnRegister(), OperandType.I64);
-
-            Operation addrCopyOp = Operation(Instruction.Copy, retReg, node.GetSource(0));
-
-            nodes.AddBefore(node, addrCopyOp);
-
-            sources[0] = retReg;
-
-            node.SetSources(sources);
-        }
-
-        private static Operation HandleLoadArgumentWindowsAbi(
-            CompilerContext cctx,
-            IntrusiveList<Operation> nodes,
-            Operand[] preservedArgs,
-            Operation node)
-        {
-            Operand source = node.GetSource(0);
-
-            Debug.Assert(source.Kind == OperandKind.Constant, "Non-constant LoadArgument source kind.");
-
-            int retArgs = cctx.FuncReturnType == OperandType.V128 ? 1 : 0;
-
-            int index = source.AsInt32() + retArgs;
-
-            if (index < CallingConvention.GetArgumentsOnRegsCount())
-            {
-                Operand dest = node.Destination;
-
-                if (preservedArgs[index] == default)
-                {
-                    Operand argReg, pArg;
-
-                    if (dest.Type.IsInteger())
-                    {
-                        argReg = Gpr(CallingConvention.GetIntArgumentRegister(index), dest.Type);
-                        pArg = Local(dest.Type);
-                    }
-                    else if (dest.Type == OperandType.V128)
-                    {
-                        argReg = Gpr(CallingConvention.GetIntArgumentRegister(index), OperandType.I64);
-                        pArg = Local(OperandType.I64);
-                    }
-                    else
-                    {
-                        argReg = Xmm(CallingConvention.GetVecArgumentRegister(index), dest.Type);
-                        pArg = Local(dest.Type);
-                    }
-
-                    Operation copyOp = Operation(Instruction.Copy, pArg, argReg);
-
-                    cctx.Cfg.Entry.Operations.AddFirst(copyOp);
-
-                    preservedArgs[index] = pArg;
-                }
-
-                Operation argCopyOp = Operation(dest.Type == OperandType.V128
-                    ? Instruction.Load
-                    : Instruction.Copy, dest, preservedArgs[index]);
-
-                Operation newNode = nodes.AddBefore(node, argCopyOp);
-
-                Delete(nodes, node);
-
-                return newNode;
-            }
-            else
-            {
-                // TODO: Pass on stack.
-                return node;
-            }
-        }
-
-        private static Operation HandleLoadArgumentSystemVAbi(
-            CompilerContext cctx,
-            IntrusiveList<Operation> nodes,
-            Operand[] preservedArgs,
-            Operation node)
-        {
-            Operand source = node.GetSource(0);
-
-            Debug.Assert(source.Kind == OperandKind.Constant, "Non-constant LoadArgument source kind.");
-
-            int index = source.AsInt32();
-
-            int intCount = 0;
-            int vecCount = 0;
-
-            for (int cIndex = 0; cIndex < index; cIndex++)
-            {
-                OperandType argType = cctx.FuncArgTypes[cIndex];
-
-                if (argType.IsInteger())
-                {
-                    intCount++;
-                }
-                else if (argType == OperandType.V128)
-                {
-                    intCount += 2;
-                }
-                else
-                {
-                    vecCount++;
-                }
-            }
-
-            bool passOnReg;
-
-            if (source.Type.IsInteger())
-            {
-                passOnReg = intCount < CallingConvention.GetIntArgumentsOnRegsCount();
-            }
-            else if (source.Type == OperandType.V128)
-            {
-                passOnReg = intCount + 1 < CallingConvention.GetIntArgumentsOnRegsCount();
-            }
-            else
-            {
-                passOnReg = vecCount < CallingConvention.GetVecArgumentsOnRegsCount();
-            }
-
-            if (passOnReg)
-            {
-                Operand dest = node.Destination;
-
-                if (preservedArgs[index] == default)
-                {
-                    if (dest.Type == OperandType.V128)
-                    {
-                        // V128 is a struct, we pass each half on a GPR if possible.
-                        Operand pArg = Local(OperandType.V128);
-
-                        Operand argLReg = Gpr(CallingConvention.GetIntArgumentRegister(intCount),     OperandType.I64);
-                        Operand argHReg = Gpr(CallingConvention.GetIntArgumentRegister(intCount + 1), OperandType.I64);
-
-                        Operation copyL = Operation(Instruction.VectorCreateScalar, pArg, argLReg);
-                        Operation copyH = Operation(Instruction.VectorInsert,       pArg, pArg, argHReg, Const(1));
-
-                        cctx.Cfg.Entry.Operations.AddFirst(copyH);
-                        cctx.Cfg.Entry.Operations.AddFirst(copyL);
-
-                        preservedArgs[index] = pArg;
-                    }
-                    else
-                    {
-                        Operand pArg = Local(dest.Type);
-
-                        Operand argReg = dest.Type.IsInteger()
-                            ? Gpr(CallingConvention.GetIntArgumentRegister(intCount), dest.Type)
-                            : Xmm(CallingConvention.GetVecArgumentRegister(vecCount), dest.Type);
-
-                        Operation copyOp = Operation(Instruction.Copy, pArg, argReg);
-
-                        cctx.Cfg.Entry.Operations.AddFirst(copyOp);
-
-                        preservedArgs[index] = pArg;
-                    }
-                }
-
-                Operation argCopyOp = Operation(Instruction.Copy, dest, preservedArgs[index]);
-
-                Operation newNode = nodes.AddBefore(node, argCopyOp);
-
-                Delete(nodes, node);
-
-                return newNode;
-            }
-            else
-            {
-                // TODO: Pass on stack.
-                return node;
-            }
-        }
-
-        private static void HandleReturnWindowsAbi(
-            CompilerContext cctx,
-            IntrusiveList<Operation> nodes,
-            Operand[] preservedArgs,
-            Operation node)
-        {
-            if (node.SourcesCount == 0)
-            {
-                return;
-            }
-
-            Operand source = node.GetSource(0);
-            Operand retReg;
-
-            if (source.Type.IsInteger())
-            {
-                retReg = Gpr(CallingConvention.GetIntReturnRegister(), source.Type);
-            }
-            else if (source.Type == OperandType.V128)
-            {
-                if (preservedArgs[0] == default)
-                {
-                    Operand preservedArg = Local(OperandType.I64);
-                    Operand arg0 = Gpr(CallingConvention.GetIntArgumentRegister(0), OperandType.I64);
-
-                    Operation copyOp = Operation(Instruction.Copy, preservedArg, arg0);
-
-                    cctx.Cfg.Entry.Operations.AddFirst(copyOp);
-
-                    preservedArgs[0] = preservedArg;
-                }
-
-                retReg = preservedArgs[0];
-            }
-            else
-            {
-                retReg = Xmm(CallingConvention.GetVecReturnRegister(), source.Type);
-            }
-
-            if (source.Type == OperandType.V128)
-            {
-                Operation retStoreOp = Operation(Instruction.Store, default, retReg, source);
-
-                nodes.AddBefore(node, retStoreOp);
-            }
-            else
-            {
-                Operation retCopyOp = Operation(Instruction.Copy, retReg, source);
-
-                nodes.AddBefore(node, retCopyOp);
-            }
-
-            node.SetSources(Array.Empty<Operand>());
-        }
-
-        private static void HandleReturnSystemVAbi(IntrusiveList<Operation> nodes, Operation node)
-        {
-            if (node.SourcesCount == 0)
-            {
-                return;
-            }
-
-            Operand source = node.GetSource(0);
-
-            if (source.Type == OperandType.V128)
-            {
-                Operand retLReg = Gpr(CallingConvention.GetIntReturnRegister(),     OperandType.I64);
-                Operand retHReg = Gpr(CallingConvention.GetIntReturnRegisterHigh(), OperandType.I64);
-
-                nodes.AddBefore(node, Operation(Instruction.VectorExtract, retLReg, source, Const(0)));
-                nodes.AddBefore(node, Operation(Instruction.VectorExtract, retHReg, source, Const(1)));
-            }
-            else
-            {
-                Operand retReg = source.Type.IsInteger()
-                    ? Gpr(CallingConvention.GetIntReturnRegister(), source.Type)
-                    : Xmm(CallingConvention.GetVecReturnRegister(), source.Type);
-
-                Operation retCopyOp = Operation(Instruction.Copy, retReg, source);
-
-                nodes.AddBefore(node, retCopyOp);
-            }
-        }
-
-        private static Operand AddXmmCopy(IntrusiveList<Operation> nodes, Operation node, Operand source)
+        protected static Operand AddXmmCopy(IntrusiveList<Operation> nodes, Operation node, Operand source)
         {
             Operand temp = Local(source.Type);
             Operand intConst = AddCopy(nodes, node, GetIntConst(source));
@@ -1202,7 +592,7 @@ namespace ARMeilleure.CodeGen.X86
             return temp;
         }
 
-        private static Operand AddCopy(IntrusiveList<Operation> nodes, Operation node, Operand source)
+        protected static Operand AddCopy(IntrusiveList<Operation> nodes, Operation node, Operand source)
         {
             Operand temp = Local(source.Type);
 
@@ -1227,7 +617,7 @@ namespace ARMeilleure.CodeGen.X86
             return value;
         }
 
-        private static void Delete(IntrusiveList<Operation> nodes, Operation node)
+        protected static void Delete(IntrusiveList<Operation> nodes, Operation node)
         {
             node.Destination = default;
 
@@ -1239,12 +629,12 @@ namespace ARMeilleure.CodeGen.X86
             nodes.Remove(node);
         }
 
-        private static Operand Gpr(X86Register register, OperandType type)
+        protected static Operand Gpr(X86Register register, OperandType type)
         {
             return Register((int)register, RegisterType.Integer, type);
         }
 
-        private static Operand Xmm(X86Register register, OperandType type)
+        protected static Operand Xmm(X86Register register, OperandType type)
         {
             return Register((int)register, RegisterType.Vector, type);
         }
@@ -1297,11 +687,15 @@ namespace ARMeilleure.CodeGen.X86
         {
             if (IsIntrinsic(operation.Instruction))
             {
+                IntrinsicInfo info = IntrinsicTable.GetInfo(operation.Intrinsic);
+
+                bool hasVex = HardwareCapabilities.SupportsVexEncoding && Assembler.SupportsVexPrefix(info.Inst);
+
                 bool isUnary = operation.SourcesCount < 2;
 
                 bool hasVecDest = operation.Destination != default && operation.Destination.Type == OperandType.V128;
 
-                return !HardwareCapabilities.SupportsVexEncoding && !isUnary && hasVecDest;
+                return !hasVex && !isUnary && hasVecDest;
             }
 
             return false;

ARMeilleure/CodeGen/X86/PreAllocatorSystemV.cs

@@ -0,0 +1,334 @@
+using ARMeilleure.CodeGen.RegisterAllocators;
+using ARMeilleure.IntermediateRepresentation;
+using ARMeilleure.Translation;
+using System;
+using System.Collections.Generic;
+using System.Diagnostics;
+using static ARMeilleure.IntermediateRepresentation.Operand.Factory;
+using static ARMeilleure.IntermediateRepresentation.Operation.Factory;
+
+namespace ARMeilleure.CodeGen.X86
+{
+    class PreAllocatorSystemV : PreAllocator
+    {
+        public static void InsertCallCopies(IntrusiveList<Operation> nodes, Operation node)
+        {
+            Operand dest = node.Destination;
+
+            List<Operand> sources = new List<Operand>
+            {
+                node.GetSource(0)
+            };
+
+            int argsCount = node.SourcesCount - 1;
+
+            int intMax = CallingConvention.GetIntArgumentsOnRegsCount();
+            int vecMax = CallingConvention.GetVecArgumentsOnRegsCount();
+
+            int intCount = 0;
+            int vecCount = 0;
+
+            int stackOffset = 0;
+
+            for (int index = 0; index < argsCount; index++)
+            {
+                Operand source = node.GetSource(index + 1);
+
+                bool passOnReg;
+
+                if (source.Type.IsInteger())
+                {
+                    passOnReg = intCount < intMax;
+                }
+                else if (source.Type == OperandType.V128)
+                {
+                    passOnReg = intCount + 1 < intMax;
+                }
+                else
+                {
+                    passOnReg = vecCount < vecMax;
+                }
+
+                if (source.Type == OperandType.V128 && passOnReg)
+                {
+                    // V128 is a struct, we pass each half on a GPR if possible.
+                    Operand argReg  = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
+                    Operand argReg2 = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
+
+                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg,  source, Const(0)));
+                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg2, source, Const(1)));
+
+                    continue;
+                }
+
+                if (passOnReg)
+                {
+                    Operand argReg = source.Type.IsInteger()
+                        ? Gpr(CallingConvention.GetIntArgumentRegister(intCount++), source.Type)
+                        : Xmm(CallingConvention.GetVecArgumentRegister(vecCount++), source.Type);
+
+                    Operation copyOp = Operation(Instruction.Copy, argReg, source);
+
+                    InsertConstantRegCopies(nodes, nodes.AddBefore(node, copyOp));
+
+                    sources.Add(argReg);
+                }
+                else
+                {
+                    Operand offset = Const(stackOffset);
+
+                    Operation spillOp = Operation(Instruction.SpillArg, default, offset, source);
+
+                    InsertConstantRegCopies(nodes, nodes.AddBefore(node, spillOp));
+
+                    stackOffset += source.Type.GetSizeInBytes();
+                }
+            }
+
+            node.SetSources(sources.ToArray());
+
+            if (dest != default)
+            {
+                if (dest.Type == OperandType.V128)
+                {
+                    Operand retLReg = Gpr(CallingConvention.GetIntReturnRegister(),     OperandType.I64);
+                    Operand retHReg = Gpr(CallingConvention.GetIntReturnRegisterHigh(), OperandType.I64);
+
+                    Operation operation = node;
+
+                    node = nodes.AddAfter(node, Operation(Instruction.VectorCreateScalar, dest, retLReg));
+                    nodes.AddAfter(node, Operation(Instruction.VectorInsert, dest, dest, retHReg, Const(1)));
+
+                    operation.Destination = default;
+                }
+                else
+                {
+                    Operand retReg = dest.Type.IsInteger()
+                        ? Gpr(CallingConvention.GetIntReturnRegister(), dest.Type)
+                        : Xmm(CallingConvention.GetVecReturnRegister(), dest.Type);
+
+                    Operation copyOp = Operation(Instruction.Copy, dest, retReg);
+
+                    nodes.AddAfter(node, copyOp);
+
+                    node.Destination = retReg;
+                }
+            }
+        }
+
+        public static void InsertTailcallCopies(IntrusiveList<Operation> nodes, StackAllocator stackAlloc, Operation node)
+        {
+            List<Operand> sources = new List<Operand>
+            {
+                node.GetSource(0)
+            };
+
+            int argsCount = node.SourcesCount - 1;
+
+            int intMax = CallingConvention.GetIntArgumentsOnRegsCount();
+            int vecMax = CallingConvention.GetVecArgumentsOnRegsCount();
+
+            int intCount = 0;
+            int vecCount = 0;
+
+            // Handle arguments passed on registers.
+            for (int index = 0; index < argsCount; index++)
+            {
+                Operand source = node.GetSource(1 + index);
+
+                bool passOnReg;
+
+                if (source.Type.IsInteger())
+                {
+                    passOnReg = intCount + 1 < intMax;
+                }
+                else
+                {
+                    passOnReg = vecCount < vecMax;
+                }
+
+                if (source.Type == OperandType.V128 && passOnReg)
+                {
+                    // V128 is a struct, we pass each half on a GPR if possible.
+                    Operand argReg = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
+                    Operand argReg2 = Gpr(CallingConvention.GetIntArgumentRegister(intCount++), OperandType.I64);
+
+                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg, source, Const(0)));
+                    nodes.AddBefore(node, Operation(Instruction.VectorExtract, argReg2, source, Const(1)));
+
+                    continue;
+                }
+
+                if (passOnReg)
+                {
+                    Operand argReg = source.Type.IsInteger()
+                        ? Gpr(CallingConvention.GetIntArgumentRegister(intCount++), source.Type)
+                        : Xmm(CallingConvention.GetVecArgumentRegister(vecCount++), source.Type);
+
+                    Operation copyOp = Operation(Instruction.Copy, argReg, source);
+
+                    InsertConstantRegCopies(nodes, nodes.AddBefore(node, copyOp));
+
+                    sources.Add(argReg);
+                }
+                else
+                {
+                    throw new NotImplementedException("Spilling is not currently supported for tail calls. (too many arguments)");
+                }
+            }
+
+            // The target address must be on the return registers, since we
+            // don't return anything and it is guaranteed to not be a
+            // callee saved register (which would be trashed on the epilogue).
+            Operand retReg = Gpr(CallingConvention.GetIntReturnRegister(), OperandType.I64);
+
+            Operation addrCopyOp = Operation(Instruction.Copy, retReg, node.GetSource(0));
+
+            nodes.AddBefore(node, addrCopyOp);
+
+            sources[0] = retReg;
+
+            node.SetSources(sources.ToArray());
+        }
+
+        public static Operation InsertLoadArgumentCopy(
+            CompilerContext cctx,
+            ref Span<Operation> buffer,
+            IntrusiveList<Operation> nodes,
+            Operand[] preservedArgs,
+            Operation node)
+        {
+            Operand source = node.GetSource(0);
+
+            Debug.Assert(source.Kind == OperandKind.Constant, "Non-constant LoadArgument source kind.");
+
+            int index = source.AsInt32();
+
+            int intCount = 0;
+            int vecCount = 0;
+
+            for (int cIndex = 0; cIndex < index; cIndex++)
+            {
+                OperandType argType = cctx.FuncArgTypes[cIndex];
+
+                if (argType.IsInteger())
+                {
+                    intCount++;
+                }
+                else if (argType == OperandType.V128)
+                {
+                    intCount += 2;
+                }
+                else
+                {
+                    vecCount++;
+                }
+            }
+
+            bool passOnReg;
+
+            if (source.Type.IsInteger())
+            {
+                passOnReg = intCount < CallingConvention.GetIntArgumentsOnRegsCount();
+            }
+            else if (source.Type == OperandType.V128)
+            {
+                passOnReg = intCount + 1 < CallingConvention.GetIntArgumentsOnRegsCount();
+            }
+            else
+            {
+                passOnReg = vecCount < CallingConvention.GetVecArgumentsOnRegsCount();
+            }
+
+            if (passOnReg)
+            {
+                Operand dest = node.Destination;
+
+                if (preservedArgs[index] == default)
+                {
+                    if (dest.Type == OperandType.V128)
+                    {
+                        // V128 is a struct, we pass each half on a GPR if possible.
+                        Operand pArg = Local(OperandType.V128);
+
+                        Operand argLReg = Gpr(CallingConvention.GetIntArgumentRegister(intCount),     OperandType.I64);
+                        Operand argHReg = Gpr(CallingConvention.GetIntArgumentRegister(intCount + 1), OperandType.I64);
+
+                        Operation copyL = Operation(Instruction.VectorCreateScalar, pArg, argLReg);
+                        Operation copyH = Operation(Instruction.VectorInsert,       pArg, pArg, argHReg, Const(1));
+
+                        cctx.Cfg.Entry.Operations.AddFirst(copyH);
+                        cctx.Cfg.Entry.Operations.AddFirst(copyL);
+
+                        preservedArgs[index] = pArg;
+                    }
+                    else
+                    {
+                        Operand pArg = Local(dest.Type);
+
+                        Operand argReg = dest.Type.IsInteger()
+                            ? Gpr(CallingConvention.GetIntArgumentRegister(intCount), dest.Type)
+                            : Xmm(CallingConvention.GetVecArgumentRegister(vecCount), dest.Type);
+
+                        Operation copyOp = Operation(Instruction.Copy, pArg, argReg);
+
+                        cctx.Cfg.Entry.Operations.AddFirst(copyOp);
+
+                        preservedArgs[index] = pArg;
+                    }
+                }
+
+                Operation nextNode;
+
+                if (dest.AssignmentsCount == 1)
+                {
+                    // Let's propagate the argument if we can to avoid copies.
+                    PreAllocatorCommon.Propagate(ref buffer, dest, preservedArgs[index]);
+                    nextNode = node.ListNext;
+                }
+                else
+                {
+                    Operation argCopyOp = Operation(Instruction.Copy, dest, preservedArgs[index]);
+                    nextNode = nodes.AddBefore(node, argCopyOp);
+                }
+
+                Delete(nodes, node);
+                return nextNode;
+            }
+            else
+            {
+                // TODO: Pass on stack.
+                return node;
+            }
+        }
+
+        public static void InsertReturnCopy(IntrusiveList<Operation> nodes, Operation node)
+        {
+            if (node.SourcesCount == 0)
+            {
+                return;
+            }
+
+            Operand source = node.GetSource(0);
+
+            if (source.Type == OperandType.V128)
+            {
+                Operand retLReg = Gpr(CallingConvention.GetIntReturnRegister(),     OperandType.I64);
+                Operand retHReg = Gpr(CallingConvention.GetIntReturnRegisterHigh(), OperandType.I64);
+
+                nodes.AddBefore(node, Operation(Instruction.VectorExtract, retLReg, source, Const(0)));
+                nodes.AddBefore(node, Operation(Instruction.VectorExtract, retHReg, source, Const(1)));
+            }
+            else
+            {
+                Operand retReg = source.Type.IsInteger()
+                    ? Gpr(CallingConvention.GetIntReturnRegister(), source.Type)
+                    : Xmm(CallingConvention.GetVecReturnRegister(), source.Type);
+
+                Operation retCopyOp = Operation(Instruction.Copy, retReg, source);
+
+                nodes.AddBefore(node, retCopyOp);
+            }
+        }
+    }
+}

ARMeilleure/CodeGen/X86/PreAllocatorWindows.cs

@@ -0,0 +1,327 @@
+using ARMeilleure.CodeGen.RegisterAllocators;
+using ARMeilleure.IntermediateRepresentation;
+using ARMeilleure.Translation;
+using System;
+using System.Diagnostics;
+using static ARMeilleure.IntermediateRepresentation.Operand.Factory;
+using static ARMeilleure.IntermediateRepresentation.Operation.Factory;
+
+namespace ARMeilleure.CodeGen.X86
+{
+    class PreAllocatorWindows : PreAllocator
+    {
+        public static void InsertCallCopies(IntrusiveList<Operation> nodes, StackAllocator stackAlloc, Operation node)
+        {
+            Operand dest = node.Destination;
+
+            // Handle struct arguments.
+            int retArgs = 0;
+            int stackAllocOffset = 0;
+
+            int AllocateOnStack(int size)
+            {
+                // We assume that the stack allocator is initially empty (TotalSize = 0).
+                // Taking that into account, we can reuse the space allocated for other
+                // calls by keeping track of our own allocated size (stackAllocOffset).
+                // If the space allocated is not big enough, then we just expand it.
+                int offset = stackAllocOffset;
+
+                if (stackAllocOffset + size > stackAlloc.TotalSize)
+                {
+                    stackAlloc.Allocate((stackAllocOffset + size) - stackAlloc.TotalSize);
+                }
+
+                stackAllocOffset += size;
+
+                return offset;
+            }
+
+            Operand arg0Reg = default;
+
+            if (dest != default && dest.Type == OperandType.V128)
+            {
+                int stackOffset = AllocateOnStack(dest.Type.GetSizeInBytes());
+
+                arg0Reg = Gpr(CallingConvention.GetIntArgumentRegister(0), OperandType.I64);
+
+                Operation allocOp = Operation(Instruction.StackAlloc, arg0Reg, Const(stackOffset));
+
+                nodes.AddBefore(node, allocOp);
+
+                retArgs = 1;
+            }
+
+            int argsCount = node.SourcesCount - 1;
+            int maxArgs = CallingConvention.GetArgumentsOnRegsCount() - retArgs;
+
+            if (argsCount > maxArgs)
+            {
+                argsCount = maxArgs;
+            }
+
+            Operand[] sources = new Operand[1 + retArgs + argsCount];
+
+            sources[0] = node.GetSource(0);
+
+            if (arg0Reg != default)
+            {
+                sources[1] = arg0Reg;
+            }
+
+            for (int index = 1; index < node.SourcesCount; index++)
+            {
+                Operand source = node.GetSource(index);
+
+                if (source.Type == OperandType.V128)
+                {
+                    Operand stackAddr = Local(OperandType.I64);
+
+                    int stackOffset = AllocateOnStack(source.Type.GetSizeInBytes());
+
+                    nodes.AddBefore(node, Operation(Instruction.StackAlloc, stackAddr, Const(stackOffset)));
+
+                    Operation storeOp = Operation(Instruction.Store, default, stackAddr, source);
+
+                    InsertConstantRegCopies(nodes, nodes.AddBefore(node, storeOp));
+
+                    node.SetSource(index, stackAddr);
+                }
+            }
+
+            // Handle arguments passed on registers.
+            for (int index = 0; index < argsCount; index++)
+            {
+                Operand source = node.GetSource(index + 1);
+                Operand argReg;
+
+                int argIndex = index + retArgs;
+
+                if (source.Type.IsInteger())
+                {
+                    argReg = Gpr(CallingConvention.GetIntArgumentRegister(argIndex), source.Type);
+                }
+                else
+                {
+                    argReg = Xmm(CallingConvention.GetVecArgumentRegister(argIndex), source.Type);
+                }
+
+                Operation copyOp = Operation(Instruction.Copy, argReg, source);
+
+                InsertConstantRegCopies(nodes, nodes.AddBefore(node, copyOp));
+
+                sources[1 + retArgs + index] = argReg;
+            }
+
+            // The remaining arguments (those that are not passed on registers)
+            // should be passed on the stack, we write them to the stack with "SpillArg".
+            for (int index = argsCount; index < node.SourcesCount - 1; index++)
+            {
+                Operand source = node.GetSource(index + 1);
+                Operand offset = Const((index + retArgs) * 8);
+
+                Operation spillOp = Operation(Instruction.SpillArg, default, offset, source);
+
+                InsertConstantRegCopies(nodes, nodes.AddBefore(node, spillOp));
+            }
+
+            if (dest != default)
+            {
+                if (dest.Type == OperandType.V128)
+                {
+                    Operand retValueAddr = Local(OperandType.I64);
+
+                    nodes.AddBefore(node, Operation(Instruction.Copy, retValueAddr, arg0Reg));
+
+                    Operation loadOp = Operation(Instruction.Load, dest, retValueAddr);
+
+                    nodes.AddAfter(node, loadOp);
+
+                    node.Destination = default;
+                }
+                else
+                {
+                    Operand retReg = dest.Type.IsInteger()
+                        ? Gpr(CallingConvention.GetIntReturnRegister(), dest.Type)
+                        : Xmm(CallingConvention.GetVecReturnRegister(), dest.Type);
+
+                    Operation copyOp = Operation(Instruction.Copy, dest, retReg);
+
+                    nodes.AddAfter(node, copyOp);
+
+                    node.Destination = retReg;
+                }
+            }
+
+            node.SetSources(sources);
+        }
+
+        public static void InsertTailcallCopies(IntrusiveList<Operation> nodes, StackAllocator stackAlloc, Operation node)
+        {
+            int argsCount = node.SourcesCount - 1;
+            int maxArgs = CallingConvention.GetArgumentsOnRegsCount();
+
+            if (argsCount > maxArgs)
+            {
+                throw new NotImplementedException("Spilling is not currently supported for tail calls. (too many arguments)");
+            }
+
+            Operand[] sources = new Operand[1 + argsCount];
+
+            // Handle arguments passed on registers.
+            for (int index = 0; index < argsCount; index++)
+            {
+                Operand source = node.GetSource(1 + index);
+                Operand argReg = source.Type.IsInteger()
+                    ? Gpr(CallingConvention.GetIntArgumentRegister(index), source.Type)
+                    : Xmm(CallingConvention.GetVecArgumentRegister(index), source.Type);
+
+                Operation copyOp = Operation(Instruction.Copy, argReg, source);
+
+                InsertConstantRegCopies(nodes, nodes.AddBefore(node, copyOp));
+
+                sources[1 + index] = argReg;
+            }
+
+            // The target address must be on the return registers, since we
+            // don't return anything and it is guaranteed to not be a
+            // callee saved register (which would be trashed on the epilogue).
+            Operand retReg = Gpr(CallingConvention.GetIntReturnRegister(), OperandType.I64);
+
+            Operation addrCopyOp = Operation(Instruction.Copy, retReg, node.GetSource(0));
+
+            nodes.AddBefore(node, addrCopyOp);
+
+            sources[0] = retReg;
+
+            node.SetSources(sources);
+        }
+
+        public static Operation InsertLoadArgumentCopy(
+            CompilerContext cctx,
+            ref Span<Operation> buffer,
+            IntrusiveList<Operation> nodes,
+            Operand[] preservedArgs,
+            Operation node)
+        {
+            Operand source = node.GetSource(0);
+
+            Debug.Assert(source.Kind == OperandKind.Constant, "Non-constant LoadArgument source kind.");
+
+            int retArgs = cctx.FuncReturnType == OperandType.V128 ? 1 : 0;
+
+            int index = source.AsInt32() + retArgs;
+
+            if (index < CallingConvention.GetArgumentsOnRegsCount())
+            {
+                Operand dest = node.Destination;
+
+                if (preservedArgs[index] == default)
+                {
+                    Operand argReg, pArg;
+
+                    if (dest.Type.IsInteger())
+                    {
+                        argReg = Gpr(CallingConvention.GetIntArgumentRegister(index), dest.Type);
+                        pArg = Local(dest.Type);
+                    }
+                    else if (dest.Type == OperandType.V128)
+                    {
+                        argReg = Gpr(CallingConvention.GetIntArgumentRegister(index), OperandType.I64);
+                        pArg = Local(OperandType.I64);
+                    }
+                    else
+                    {
+                        argReg = Xmm(CallingConvention.GetVecArgumentRegister(index), dest.Type);
+                        pArg = Local(dest.Type);
+                    }
+
+                    Operation copyOp = Operation(Instruction.Copy, pArg, argReg);
+
+                    cctx.Cfg.Entry.Operations.AddFirst(copyOp);
+
+                    preservedArgs[index] = pArg;
+                }
+
+                Operation nextNode;
+
+                if (dest.Type != OperandType.V128 && dest.AssignmentsCount == 1)
+                {
+                    // Let's propagate the argument if we can to avoid copies.
+                    PreAllocatorCommon.Propagate(ref buffer, dest, preservedArgs[index]);
+                    nextNode = node.ListNext;
+                }
+                else
+                {
+                    Operation argCopyOp = Operation(dest.Type == OperandType.V128
+                        ? Instruction.Load
+                        : Instruction.Copy, dest, preservedArgs[index]);
+
+                    nextNode = nodes.AddBefore(node, argCopyOp);
+                }
+
+                Delete(nodes, node);
+                return nextNode;
+            }
+            else
+            {
+                // TODO: Pass on stack.
+                return node;
+            }
+        }
+
+        public static void InsertReturnCopy(
+            CompilerContext cctx,
+            IntrusiveList<Operation> nodes,
+            Operand[] preservedArgs,
+            Operation node)
+        {
+            if (node.SourcesCount == 0)
+            {
+                return;
+            }
+
+            Operand source = node.GetSource(0);
+            Operand retReg;
+
+            if (source.Type.IsInteger())
+            {
+                retReg = Gpr(CallingConvention.GetIntReturnRegister(), source.Type);
+            }
+            else if (source.Type == OperandType.V128)
+            {
+                if (preservedArgs[0] == default)
+                {
+                    Operand preservedArg = Local(OperandType.I64);
+                    Operand arg0 = Gpr(CallingConvention.GetIntArgumentRegister(0), OperandType.I64);
+
+                    Operation copyOp = Operation(Instruction.Copy, preservedArg, arg0);
+
+                    cctx.Cfg.Entry.Operations.AddFirst(copyOp);
+
+                    preservedArgs[0] = preservedArg;
+                }
+
+                retReg = preservedArgs[0];
+            }
+            else
+            {
+                retReg = Xmm(CallingConvention.GetVecReturnRegister(), source.Type);
+            }
+
+            if (source.Type == OperandType.V128)
+            {
+                Operation retStoreOp = Operation(Instruction.Store, default, retReg, source);
+
+                nodes.AddBefore(node, retStoreOp);
+            }
+            else
+            {
+                Operation retCopyOp = Operation(Instruction.Copy, retReg, source);
+
+                nodes.AddBefore(node, retCopyOp);
+            }
+
+            node.SetSources(Array.Empty<Operand>());
+        }
+    }
+}

ARMeilleure/CodeGen/X86/X86Instruction.cs

@@ -54,6 +54,7 @@ namespace ARMeilleure.CodeGen.X86
         Divps,
         Divsd,
         Divss,
+        Gf2p8affineqb,
         Haddpd,
         Haddps,
         Idiv,
@@ -98,6 +99,7 @@ namespace ARMeilleure.CodeGen.X86
         Paddd,
         Paddq,
         Paddw,
+        Palignr,
         Pand,
         Pandn,
         Pavgb,
@@ -180,6 +182,9 @@ namespace ARMeilleure.CodeGen.X86
         Rsqrtss,
         Sar,
         Setcc,
+        Sha256Msg1,
+        Sha256Msg2,
+        Sha256Rnds2,
         Shl,
         Shr,
         Shufpd,

ARMeilleure/Common/AddressTable.cs

@@ -1,4 +1,4 @@
-using ARMeilleure.Diagnostics.EventSources;
+using ARMeilleure.Diagnostics;
 using System;
 using System.Collections.Generic;
 using System.Runtime.InteropServices;
@@ -80,10 +80,7 @@ namespace ARMeilleure.Common
         {
             get
             {
-                if (_disposed)
-                {
-                    throw new ObjectDisposedException(null);
-                }
+                ObjectDisposedException.ThrowIf(_disposed, this);
 
                 lock (_pages)
                 {
@@ -100,10 +97,7 @@ namespace ARMeilleure.Common
         /// <exception cref="ArgumentException">Length of <paramref name="levels"/> is less than 2</exception>
         public AddressTable(Level[] levels)
         {
-            if (levels == null)
-            {
-                throw new ArgumentNullException(nameof(levels));
-            }
+            ArgumentNullException.ThrowIfNull(levels);
 
             if (levels.Length < 2)
             {
@@ -141,10 +135,7 @@ namespace ARMeilleure.Common
         /// <exception cref="ArgumentException"><paramref name="address"/> is not mapped</exception>
         public ref TEntry GetValue(ulong address)
         {
-            if (_disposed)
-            {
-                throw new ObjectDisposedException(null);
-            }
+            ObjectDisposedException.ThrowIf(_disposed, this);
 
             if (!IsValid(address))
             {
@@ -206,7 +197,7 @@ namespace ARMeilleure.Common
         /// <typeparam name="T">Type of elements</typeparam>
         /// <param name="length">Number of elements</param>
         /// <param name="fill">Fill value</param>
-        /// <param name="leaf"><see langword="true"/> if leaf; otherwise <see langword=""="false"/></param>
+        /// <param name="leaf"><see langword="true"/> if leaf; otherwise <see langword="false"/></param>
         /// <returns>Allocated block</returns>
         private IntPtr Allocate<T>(int length, T fill, bool leaf) where T : unmanaged
         {
@@ -218,7 +209,7 @@ namespace ARMeilleure.Common
 
             _pages.Add(page);
 
-            AddressTableEventSource.Log.Allocated(size, leaf);
+            TranslatorEventSource.Log.AddressTableAllocated(size, leaf);
 
             return page;
         }

ARMeilleure/Common/ArenaAllocator.cs

@@ -1,7 +1,6 @@
 using System;
 using System.Collections.Generic;
 using System.Runtime.CompilerServices;
-using System.Threading;
 
 namespace ARMeilleure.Common
 {

ARMeilleure/Common/BitUtils.cs

@@ -1,15 +1,11 @@
+using System;
 using System.Numerics;
 
 namespace ARMeilleure.Common
 {
     static class BitUtils
     {
-        private static readonly sbyte[] HbsNibbleLut;
-
-        static BitUtils()
-        {
-            HbsNibbleLut = new sbyte[] { -1, 0, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3 };
-        }
+        private static ReadOnlySpan<sbyte> HbsNibbleLut => new sbyte[] { -1, 0, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3 };
 
         public static long FillWithOnes(int bits)
         {

ARMeilleure/Common/Counter.cs

@@ -9,6 +9,9 @@ namespace ARMeilleure.Common
     class Counter<T> : IDisposable where T : unmanaged
     {
         private bool _disposed;
+        /// <summary>
+        /// Index in the <see cref="EntryTable{T}"/>
+        /// </summary>
         private readonly int _index;
         private readonly EntryTable<T> _countTable;
 
@@ -17,7 +20,6 @@ namespace ARMeilleure.Common
         /// <see cref="EntryTable{T}"/> instance and index.
         /// </summary>
         /// <param name="countTable"><see cref="EntryTable{T}"/> instance</param>
-        /// <param name="index">Index in the <see cref="EntryTable{T}"/></param>
         /// <exception cref="ArgumentNullException"><paramref name="countTable"/> is <see langword="null"/></exception>
         /// <exception cref="ArgumentException"><typeparamref name="T"/> is unsupported</exception>
         public Counter(EntryTable<T> countTable)
@@ -47,10 +49,7 @@ namespace ARMeilleure.Common
         {
             get
             {
-                if (_disposed)
-                {
-                    throw new ObjectDisposedException(null);
-                }
+                ObjectDisposedException.ThrowIf(_disposed, this);
 
                 return ref _countTable.GetValue(_index);
             }
@@ -68,7 +67,7 @@ namespace ARMeilleure.Common
         /// <summary>
         /// Releases all unmanaged and optionally managed resources used by the <see cref="Counter{T}"/> instance.
         /// </summary>
-        /// <param name="disposing"><see langword="true"/> to dispose managed resources also; otherwise just unmanaged resouces</param>
+        /// <param name="disposing"><see langword="true"/> to dispose managed resources also; otherwise just unmanaged resources</param>
         protected virtual void Dispose(bool disposing)
         {
             if (!_disposed)

ARMeilleure/Common/EntryTable.cs

@@ -53,10 +53,7 @@ namespace ARMeilleure.Common
         /// <exception cref="ObjectDisposedException"><see cref="EntryTable{TEntry}"/> instance was disposed</exception>
         public int Allocate()
         {
-            if (_disposed)
-            {
-                throw new ObjectDisposedException(null);
-            }
+            ObjectDisposedException.ThrowIf(_disposed, this);
 
             lock (_allocated)
             {
@@ -83,10 +80,7 @@ namespace ARMeilleure.Common
         /// <exception cref="ObjectDisposedException"><see cref="EntryTable{TEntry}"/> instance was disposed</exception>
         public void Free(int index)
         {
-            if (_disposed)
-            {
-                throw new ObjectDisposedException(null);
-            }
+            ObjectDisposedException.ThrowIf(_disposed, this);
 
             lock (_allocated)
             {
@@ -108,10 +102,7 @@ namespace ARMeilleure.Common
         /// <exception cref="ArgumentException">Entry at <paramref name="index"/> is not allocated</exception>
         public ref TEntry GetValue(int index)
         {
-            if (_disposed)
-            {
-                throw new ObjectDisposedException(null);
-            }
+            ObjectDisposedException.ThrowIf(_disposed, this);
 
             lock (_allocated)
             {

ARMeilleure/Decoders/Decoder.cs

@@ -251,6 +251,13 @@ namespace ARMeilleure.Decoders
                 return false;
             }
 
+            // Compare and branch instructions are always conditional.
+            if (opCode.Instruction.Name == InstName.Cbz ||
+                opCode.Instruction.Name == InstName.Cbnz)
+            {
+                return false;
+            }
+
             // Note: On ARM32, most instructions have conditional execution,
             // so there's no "Always" (unconditional) branch like on ARM64.
             // We need to check if the condition is "Always" instead.

ARMeilleure/Decoders/DecoderHelper.cs

@@ -17,7 +17,7 @@ namespace ARMeilleure.Decoders
         {
             uint[] tbl = new uint[256];
 
-            for (int idx = 0; idx < 256; idx++)
+            for (int idx = 0; idx < tbl.Length; idx++)
             {
                 tbl[idx] = ExpandImm8ToFP32((uint)idx);
             }
@@ -29,7 +29,7 @@ namespace ARMeilleure.Decoders
         {
             ulong[] tbl = new ulong[256];
 
-            for (int idx = 0; idx < 256; idx++)
+            for (int idx = 0; idx < tbl.Length; idx++)
             {
                 tbl[idx] = ExpandImm8ToFP64((ulong)idx);
             }
@@ -151,7 +151,7 @@ namespace ARMeilleure.Decoders
 
         public static bool VectorArgumentsInvalid(bool q, params int[] args)
         {
-            if (q) 
+            if (q)
             {
                 for (int i = 0; i < args.Length; i++)
                 {

ARMeilleure/Decoders/IOpCode32AluBf.cs

@@ -7,5 +7,8 @@
 
         int Msb { get; }
         int Lsb { get; }
+
+        int SourceMask => (int)(0xFFFFFFFF >> (31 - Msb));
+        int DestMask => SourceMask & (int)(0xFFFFFFFF << Lsb);
     }
 }

ARMeilleure/Decoders/IOpCode32AluImm16.cs

@@ -0,0 +1,7 @@
+namespace ARMeilleure.Decoders
+{
+    interface IOpCode32AluImm16 : IOpCode32Alu
+    {
+        int Immediate { get; }
+    }
+}

ARMeilleure/Decoders/IOpCode32AluMla.cs

@@ -0,0 +1,11 @@
+namespace ARMeilleure.Decoders
+{
+    interface IOpCode32AluMla : IOpCode32AluReg
+    {
+        int Ra { get; }
+
+        bool NHigh { get; }
+        bool MHigh { get; }
+        bool R { get; }
+    }
+}

ARMeilleure/Decoders/IOpCode32AluUmull.cs

@@ -0,0 +1,13 @@
+namespace ARMeilleure.Decoders
+{
+    interface IOpCode32AluUmull : IOpCode32, IOpCode32HasSetFlags
+    {
+        int RdLo { get; }
+        int RdHi { get; }
+        int Rn { get; }
+        int Rm { get; }
+
+        bool NHigh { get; }
+        bool MHigh { get; }
+    }
+}

ARMeilleure/Decoders/IOpCode32Mem.cs

@@ -3,6 +3,7 @@ namespace ARMeilleure.Decoders
     interface IOpCode32Mem : IOpCode32
     {
         int Rt { get; }
+        int Rt2 => Rt | 1;
         int Rn { get; }
 
         bool WBack { get; }

ARMeilleure/Decoders/IOpCode32MemRsImm.cs

@@ -0,0 +1,8 @@
+namespace ARMeilleure.Decoders
+{
+    interface IOpCode32MemRsImm : IOpCode32Mem
+    {
+        int Rm { get; }
+        ShiftType ShiftType { get; }
+    }
+}

ARMeilleure/Decoders/InstDescriptor.cs

@@ -2,7 +2,7 @@ using ARMeilleure.Instructions;
 
 namespace ARMeilleure.Decoders
 {
-    struct InstDescriptor
+    readonly struct InstDescriptor
     {
         public static InstDescriptor Undefined => new InstDescriptor(InstName.Und, InstEmit.Und);
 

ARMeilleure/Decoders/OpCode32.cs

@@ -13,16 +13,13 @@ namespace ARMeilleure.Decoders
             Cond = (Condition)((uint)opCode >> 28);
         }
 
-        public bool IsThumb()
-        {
-            return this is OpCodeT16 || this is OpCodeT32;
-        }
+        public bool IsThumb { get; protected init; } = false;
 
         public uint GetPc()
         {
             // Due to backwards compatibility and legacy behavior of ARMv4 CPUs pipeline,
             // the PC actually points 2 instructions ahead.
-            if (IsThumb())
+            if (IsThumb)
             {
                 // PC is ahead by 4 in thumb mode whether or not the current instruction
                 // is 16 or 32 bit.

ARMeilleure/Decoders/OpCode32AluBf.cs

@@ -6,12 +6,8 @@
         public int Rn { get; }
 
         public int Msb { get; }
-
         public int Lsb { get; }
 
-        public int SourceMask => (int)(0xFFFFFFFF >> (31 - Msb));
-        public int DestMask => SourceMask & (int)(0xFFFFFFFF << Lsb);
-
         public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32AluBf(inst, address, opCode);
 
         public OpCode32AluBf(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)

ARMeilleure/Decoders/OpCode32AluImm16.cs

@@ -1,6 +1,6 @@
 namespace ARMeilleure.Decoders
 {
-    class OpCode32AluImm16 : OpCode32Alu
+    class OpCode32AluImm16 : OpCode32Alu, IOpCode32AluImm16
     {
         public int Immediate { get; }
 

ARMeilleure/Decoders/OpCode32AluMla.cs

@@ -1,6 +1,6 @@
 namespace ARMeilleure.Decoders
 {
-    class OpCode32AluMla : OpCode32, IOpCode32AluReg
+    class OpCode32AluMla : OpCode32, IOpCode32AluMla
     {
         public int Rn { get; }
         public int Rm { get; }

ARMeilleure/Decoders/OpCode32AluUmull.cs

@@ -1,6 +1,6 @@
 namespace ARMeilleure.Decoders
 {
-    class OpCode32AluUmull : OpCode32, IOpCode32HasSetFlags
+    class OpCode32AluUmull : OpCode32, IOpCode32AluUmull
     {
         public int RdLo { get; }
         public int RdHi { get; }
@@ -11,7 +11,6 @@
         public bool MHigh { get; }
 
         public bool? SetFlags { get; }
-        public DataOp DataOp { get; }
 
         public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32AluUmull(inst, address, opCode);
 
@@ -26,7 +25,6 @@
             MHigh = ((opCode >> 6) & 0x1) == 1;
 
             SetFlags = ((opCode >> 20) & 0x1) != 0;
-            DataOp = DataOp.Arithmetic;
         }
     }
 }

ARMeilleure/Decoders/OpCode32MemMult.cs

@@ -1,3 +1,5 @@
+using System.Numerics;
+
 namespace ARMeilleure.Decoders
 {
     class OpCode32MemMult : OpCode32, IOpCode32MemMult
@@ -23,14 +25,7 @@ namespace ARMeilleure.Decoders
 
             RegisterMask = opCode & 0xffff;
 
-            int regsSize = 0;
-
-            for (int index = 0; index < 16; index++)
-            {
-                regsSize += (RegisterMask >> index) & 1;
-            }
-
-            regsSize *= 4;
+            int regsSize = BitOperations.PopCount((uint)RegisterMask) * 4;
 
             if (!u)
             {

ARMeilleure/Decoders/OpCode32MemRsImm.cs

@@ -1,6 +1,6 @@
 namespace ARMeilleure.Decoders
 {
-    class OpCode32MemRsImm : OpCode32Mem
+    class OpCode32MemRsImm : OpCode32Mem, IOpCode32MemRsImm
     {
         public int Rm { get; }
         public ShiftType ShiftType { get; }

ARMeilleure/Decoders/OpCode32Mrs.cs

@@ -0,0 +1,16 @@
+namespace ARMeilleure.Decoders
+{
+    class OpCode32Mrs : OpCode32
+    {
+        public bool R  { get; }
+        public int  Rd { get; }
+
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32Mrs(inst, address, opCode);
+
+        public OpCode32Mrs(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        {
+            R = ((opCode >> 22) & 1) != 0;
+            Rd = (opCode >> 12) & 0xf;
+        }
+    }
+}

ARMeilleure/Decoders/OpCode32Simd.cs

@@ -7,14 +7,15 @@
         public bool F { get; protected set; }
         public bool U { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32Simd(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32Simd(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32Simd(inst, address, opCode, true);
 
-        public OpCode32Simd(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32Simd(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
         {
             Size = (opCode >> 20) & 0x3;
             Q = ((opCode >> 6) & 0x1) != 0;
             F = ((opCode >> 10) & 0x1) != 0;
-            U = ((opCode >> 24) & 0x1) != 0;
+            U = ((opCode >> (isThumb ? 28 : 24)) & 0x1) != 0;
             Opc = (opCode >> 7) & 0x3;
 
             RegisterSize = Q ? RegisterSize.Simd128 : RegisterSize.Simd64;

ARMeilleure/Decoders/OpCode32SimdBase.cs

@@ -47,6 +47,9 @@ namespace ARMeilleure.Decoders
             throw new InvalidOperationException();
         }
 
-        public OpCode32SimdBase(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode) { }
+        protected OpCode32SimdBase(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
+        {
+            IsThumb = isThumb;
+        }
     }
 }

ARMeilleure/Decoders/OpCode32SimdBinary.cs

@@ -5,9 +5,10 @@
     /// </summary>
     class OpCode32SimdBinary : OpCode32SimdReg
     {
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdBinary(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdBinary(inst, address, opCode, false);
+        public new static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdBinary(inst, address, opCode, true);
 
-        public OpCode32SimdBinary(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdBinary(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
         {
             Size = 3;
 

ARMeilleure/Decoders/OpCode32SimdCmpZ.cs

@@ -2,9 +2,10 @@
 {
     class OpCode32SimdCmpZ : OpCode32Simd
     {
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdCmpZ(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdCmpZ(inst, address, opCode, false);
+        public new static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdCmpZ(inst, address, opCode, true);
 
-        public OpCode32SimdCmpZ(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdCmpZ(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
         {
             Size = (opCode >> 18) & 0x3;
 

ARMeilleure/Decoders/OpCode32SimdCvtFI.cs

@@ -2,9 +2,10 @@
 {
     class OpCode32SimdCvtFI : OpCode32SimdS
     {
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdCvtFI(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdCvtFI(inst, address, opCode, false);
+        public new static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdCvtFI(inst, address, opCode, true);
 
-        public OpCode32SimdCvtFI(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdCvtFI(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
         {
             Opc = (opCode >> 7) & 0x1;
 

ARMeilleure/Decoders/OpCode32SimdCvtTB.cs

@@ -0,0 +1,44 @@
+namespace ARMeilleure.Decoders
+{
+    class OpCode32SimdCvtTB : OpCode32, IOpCode32Simd
+    {
+        public int Vd { get; }
+        public int Vm { get; }
+        public bool Op { get; } // Convert to Half / Convert from Half
+        public bool T { get; } // Top / Bottom
+        public int Size { get; } // Double / Single
+
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdCvtTB(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdCvtTB(inst, address, opCode, true);
+
+        public OpCode32SimdCvtTB(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
+        {
+            IsThumb = isThumb;
+
+            Op   = ((opCode >> 16) & 0x1) != 0;
+            T    = ((opCode >> 7) & 0x1) != 0;
+            Size = ((opCode >> 8) & 0x1);
+
+            RegisterSize = Size == 1 ? RegisterSize.Int64 : RegisterSize.Int32;
+
+            if (Size == 1)
+            {
+                if (Op)
+                {
+                    Vm = ((opCode >> 1) & 0x10) | ((opCode >> 0) & 0xf);
+                    Vd = ((opCode >> 22) & 0x1) | ((opCode >> 11) & 0x1e);
+                }
+                else
+                {
+                    Vm = ((opCode >> 5) & 0x1) | ((opCode << 1) & 0x1e);
+                    Vd = ((opCode >> 18) & 0x10) | ((opCode >> 12) & 0xf);
+                }
+            }
+            else
+            {
+                Vm = ((opCode >> 5) & 0x1) | ((opCode << 1) & 0x1e);
+                Vd = ((opCode >> 22) & 0x1) | ((opCode >> 11) & 0x1e);
+            }
+        }
+    }
+}

ARMeilleure/Decoders/OpCode32SimdDupElem.cs

@@ -4,9 +4,10 @@
     {
         public int Index { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdDupElem(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdDupElem(inst, address, opCode, false);
+        public new static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdDupElem(inst, address, opCode, true);
 
-        public OpCode32SimdDupElem(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdDupElem(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
         {
             var opc = (opCode >> 16) & 0xf;
 

ARMeilleure/Decoders/OpCode32SimdDupGP.cs

@@ -7,10 +7,13 @@
         public int Rt { get; }
         public bool Q { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdDupGP(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdDupGP(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdDupGP(inst, address, opCode, true);
 
-        public OpCode32SimdDupGP(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdDupGP(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
         {
+            IsThumb = isThumb;
+
             Size = 2 - (((opCode >> 21) & 0x2) | ((opCode >> 5) & 0x1)); // B:E - 0 for 32, 16 then 8.
             if (Size == -1)
             {

ARMeilleure/Decoders/OpCode32SimdExt.cs

@@ -4,9 +4,10 @@
     {
         public int Immediate { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdExt(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdExt(inst, address, opCode, false);
+        public new static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdExt(inst, address, opCode, true);
 
-        public OpCode32SimdExt(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdExt(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
         {
             Immediate = (opCode >> 8) & 0xf;
             Size = 0;

ARMeilleure/Decoders/OpCode32SimdImm.cs

@@ -6,9 +6,10 @@
         public long Immediate { get; }
         public int Elems => GetBytesCount() >> Size;
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdImm(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdImm(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdImm(inst, address, opCode, true);
 
-        public OpCode32SimdImm(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdImm(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
         {
             Vd = (opCode >> 12) & 0xf;
             Vd |= (opCode >> 18) & 0x10;
@@ -22,7 +23,7 @@
 
             imm = ((uint)opCode >> 0) & 0xf;
             imm |= ((uint)opCode >> 12) & 0x70;
-            imm |= ((uint)opCode >> 17) & 0x80;
+            imm |= ((uint)opCode >> (isThumb ? 21 : 17)) & 0x80;
 
             (Immediate, Size) = OpCodeSimdHelper.GetSimdImmediateAndSize(cMode, op, imm);
 

ARMeilleure/Decoders/OpCode32SimdImm44.cs

@@ -7,10 +7,13 @@
         public int Size { get; }
         public int Elems { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdImm44(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdImm44(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdImm44(inst, address, opCode, true);
 
-        public OpCode32SimdImm44(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdImm44(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
         {
+            IsThumb = isThumb;
+
             Size = (opCode >> 8) & 0x3;
 
             bool single = Size != 3;

ARMeilleure/Decoders/OpCode32SimdLong.cs

@@ -4,9 +4,10 @@
     {
         public bool U { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdLong(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdLong(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdLong(inst, address, opCode, true);
 
-        public OpCode32SimdLong(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdLong(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
         {
             int imm3h = (opCode >> 19) & 0x7;
 
@@ -18,7 +19,7 @@
                 case 4: Size = 2; break;
             }
 
-            U = ((opCode >> 24) & 0x1) != 0;
+            U = ((opCode >> (isThumb ? 28 : 24)) & 0x1) != 0;
 
             RegisterSize = RegisterSize.Simd64;
 

ARMeilleure/Decoders/OpCode32SimdMemImm.cs

@@ -8,10 +8,13 @@
         public bool Add { get; }
         public int Immediate { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemImm(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemImm(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemImm(inst, address, opCode, true);
 
-        public OpCode32SimdMemImm(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdMemImm(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
         {
+            IsThumb = isThumb;
+
             Immediate = opCode & 0xff;
 
             Rn = (opCode >> 16) & 0xf;

ARMeilleure/Decoders/OpCode32SimdMemMult.cs

@@ -12,10 +12,13 @@
         public bool DoubleWidth { get; }
         public bool Add { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemMult(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemMult(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemMult(inst, address, opCode, true);
 
-        public OpCode32SimdMemMult(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdMemMult(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
         {
+            IsThumb = isThumb;
+
             Rn = (opCode >> 16) & 0xf;
 
             bool isLoad = (opCode & (1 << 20)) != 0;

ARMeilleure/Decoders/OpCode32SimdMemPair.cs

@@ -1,11 +1,10 @@
 using ARMeilleure.State;
-using System;
 
 namespace ARMeilleure.Decoders
 {
     class OpCode32SimdMemPair : OpCode32, IOpCode32Simd
     {
-        private static int[] RegsMap =
+        private static int[] _regsMap =
         {
             1, 1, 4, 2,
             1, 1, 3, 1,
@@ -24,10 +23,13 @@ namespace ARMeilleure.Decoders
         public int Regs { get; }
         public int Increment { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemPair(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemPair(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemPair(inst, address, opCode, true);
 
-        public OpCode32SimdMemPair(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdMemPair(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
         {
+            IsThumb = isThumb;
+
             Vd = (opCode >> 12) & 0xf;
             Vd |= (opCode >> 18) & 0x10;
 
@@ -40,9 +42,9 @@ namespace ARMeilleure.Decoders
             WBack = Rm != RegisterAlias.Aarch32Pc;
             RegisterIndex = Rm != RegisterAlias.Aarch32Pc && Rm != RegisterAlias.Aarch32Sp;
 
-            Regs = RegsMap[(opCode >> 8) & 0xf];
+            Regs = _regsMap[(opCode >> 8) & 0xf];
 
-            Increment = Math.Min(Regs, ((opCode >> 8) & 0x1) + 1);
+            Increment = ((opCode >> 8) & 0x1) + 1;
         }
     }
 }

ARMeilleure/Decoders/OpCode32SimdMemSingle.cs

@@ -15,10 +15,13 @@ namespace ARMeilleure.Decoders
         public bool Replicate { get; }
         public int Increment { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemSingle(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemSingle(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMemSingle(inst, address, opCode, true);
 
-        public OpCode32SimdMemSingle(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdMemSingle(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
         {
+            IsThumb = isThumb;
+
             Vd = (opCode >> 12) & 0xf;
             Vd |= (opCode >> 18) & 0x10;
 

ARMeilleure/Decoders/OpCode32SimdMovGp.cs

@@ -11,10 +11,13 @@
         public int Opc1 { get; }
         public int Opc2 { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovGp(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovGp(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovGp(inst, address, opCode, true);
 
-        public OpCode32SimdMovGp(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdMovGp(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
         {
+            IsThumb = isThumb;
+
             // Which one is used is instruction dependant.
             Op = (opCode >> 20) & 0x1;
 

ARMeilleure/Decoders/OpCode32SimdMovGpDouble.cs

@@ -9,10 +9,13 @@
         public int Rt2 { get; }
         public int Op { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovGpDouble(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovGpDouble(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovGpDouble(inst, address, opCode, true);
 
-        public OpCode32SimdMovGpDouble(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdMovGpDouble(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
         {
+            IsThumb = isThumb;
+
             // Which one is used is instruction dependant.
             Op = (opCode >> 20) & 0x1;
 

ARMeilleure/Decoders/OpCode32SimdMovGpElem.cs

@@ -11,10 +11,13 @@
 
         public int Index { get; }
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovGpElem(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovGpElem(inst, address, opCode, false);
+        public static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovGpElem(inst, address, opCode, true);
 
-        public OpCode32SimdMovGpElem(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdMovGpElem(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode)
         {
+            IsThumb = isThumb;
+
             Op = (opCode >> 20) & 0x1;
             U = ((opCode >> 23) & 1) != 0;
 

ARMeilleure/Decoders/OpCode32SimdMovn.cs

@@ -0,0 +1,13 @@
+namespace ARMeilleure.Decoders
+{
+    class OpCode32SimdMovn : OpCode32Simd
+    {
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovn(inst, address, opCode, false);
+        public new static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdMovn(inst, address, opCode, true);
+
+        public OpCode32SimdMovn(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
+        {
+            Size = (opCode >> 18) & 0x3;
+        }
+    }
+}

ARMeilleure/Decoders/OpCode32SimdReg.cs

@@ -8,9 +8,10 @@
         public int In => GetQuadwordSubindex(Vn) << (3 - Size);
         public int Fn => GetQuadwordSubindex(Vn) << (1 - (Size & 1));
 
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdReg(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdReg(inst, address, opCode, false);
+        public new static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdReg(inst, address, opCode, true);
 
-        public OpCode32SimdReg(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdReg(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
         {
             Vn = ((opCode >> 3) & 0x10) | ((opCode >> 16) & 0xf);
 

ARMeilleure/Decoders/OpCode32SimdRegElem.cs

@@ -2,11 +2,12 @@
 {
     class OpCode32SimdRegElem : OpCode32SimdReg
     {
-        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdRegElem(inst, address, opCode);
+        public new static OpCode Create(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdRegElem(inst, address, opCode, false);
+        public new static OpCode CreateT32(InstDescriptor inst, ulong address, int opCode) => new OpCode32SimdRegElem(inst, address, opCode, true);
 
-        public OpCode32SimdRegElem(InstDescriptor inst, ulong address, int opCode) : base(inst, address, opCode)
+        public OpCode32SimdRegElem(InstDescriptor inst, ulong address, int opCode, bool isThumb) : base(inst, address, opCode, isThumb)
         {
-            Q = ((opCode >> 24) & 0x1) != 0;
+            Q = ((opCode >> (isThumb ? 28 : 24)) & 0x1) != 0;
             F = ((opCode >> 8) & 0x1) != 0;
             Size = (opCode >> 20) & 0x3;