Use detected shader model in gfx/d3d12. (#1996)

* Use detected shader model in gfx/d3d12.

* Enable all d3d12 tests on Github.

* Improve d3d12 software device detection.

* Disable d3d12 tests on github for now.

Co-authored-by: Yong He <yhe@nvidia.com>

31 files changed, 416 insertions, 35 deletions

diff --git a/build/visual-studio/test-proxy/test-proxy.vcxproj b/build/visual-studio/test-proxy/test-proxy.vcxproj
new file mode 100644
index 000000000..3b7dfbb58
--- /dev/null
+++ b/build/visual-studio/test-proxy/test-proxy.vcxproj
@@ -0,0 +1,281 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup Label="ProjectConfigurations">
+    <ProjectConfiguration Include="Debug|Win32">
+      <Configuration>Debug</Configuration>
+      <Platform>Win32</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Debug|x64">
+      <Configuration>Debug</Configuration>
+      <Platform>x64</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Debug|ARM">
+      <Configuration>Debug</Configuration>
+      <Platform>ARM</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Debug aarch64|Win32">
+      <Configuration>Debug aarch64</Configuration>
+      <Platform>Win32</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Debug aarch64|x64">
+      <Configuration>Debug aarch64</Configuration>
+      <Platform>x64</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Debug aarch64|ARM">
+      <Configuration>Debug aarch64</Configuration>
+      <Platform>ARM</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release|Win32">
+      <Configuration>Release</Configuration>
+      <Platform>Win32</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release|x64">
+      <Configuration>Release</Configuration>
+      <Platform>x64</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release|ARM">
+      <Configuration>Release</Configuration>
+      <Platform>ARM</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release aarch64|Win32">
+      <Configuration>Release aarch64</Configuration>
+      <Platform>Win32</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release aarch64|x64">
+      <Configuration>Release aarch64</Configuration>
+      <Platform>x64</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release aarch64|ARM">
+      <Configuration>Release aarch64</Configuration>
+      <Platform>ARM</Platform>
+    </ProjectConfiguration>
+  </ItemGroup>
+  <PropertyGroup Label="Globals">
+    <ProjectGuid>{BE412850-4BB9-429A-877C-BFBC4B34186C}</ProjectGuid>
+    <IgnoreWarnCompileDuplicatedFilename>true</IgnoreWarnCompileDuplicatedFilename>
+    <Keyword>Win32Proj</Keyword>
+    <RootNamespace>test-proxy</RootNamespace>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>true</UseDebugLibraries>
+    <CharacterSet>Unicode</CharacterSet>
+    <PlatformToolset>v142</PlatformToolset>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>true</UseDebugLibraries>
+    <CharacterSet>Unicode</CharacterSet>
+    <PlatformToolset>v142</PlatformToolset>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug aarch64|ARM'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>true</UseDebugLibraries>
+    <CharacterSet>Unicode</CharacterSet>
+    <PlatformToolset>v142</PlatformToolset>
+    <WindowsSDKDesktopARMSupport>true</WindowsSDKDesktopARMSupport>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>false</UseDebugLibraries>
+    <CharacterSet>Unicode</CharacterSet>
+    <PlatformToolset>v142</PlatformToolset>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>false</UseDebugLibraries>
+    <CharacterSet>Unicode</CharacterSet>
+    <PlatformToolset>v142</PlatformToolset>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release aarch64|ARM'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>false</UseDebugLibraries>
+    <CharacterSet>Unicode</CharacterSet>
+    <PlatformToolset>v142</PlatformToolset>
+    <WindowsSDKDesktopARMSupport>true</WindowsSDKDesktopARMSupport>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+  <ImportGroup Label="ExtensionSettings">
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug aarch64|ARM'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release aarch64|ARM'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <PropertyGroup Label="UserMacros" />
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+    <LinkIncremental>true</LinkIncremental>
+    <OutDir>..\..\..\bin\windows-x86\debug\</OutDir>
+    <IntDir>..\..\..\intermediate\windows-x86\debug\test-proxy\</IntDir>
+    <TargetName>test-proxy</TargetName>
+    <TargetExt>.exe</TargetExt>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <LinkIncremental>true</LinkIncremental>
+    <OutDir>..\..\..\bin\windows-x64\debug\</OutDir>
+    <IntDir>..\..\..\intermediate\windows-x64\debug\test-proxy\</IntDir>
+    <TargetName>test-proxy</TargetName>
+    <TargetExt>.exe</TargetExt>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug aarch64|ARM'">
+    <LinkIncremental>true</LinkIncremental>
+    <OutDir>..\..\..\bin\windows-aarch64\debug\</OutDir>
+    <IntDir>..\..\..\intermediate\windows-aarch64\debug\test-proxy\</IntDir>
+    <TargetName>test-proxy</TargetName>
+    <TargetExt>.exe</TargetExt>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <LinkIncremental>false</LinkIncremental>
+    <OutDir>..\..\..\bin\windows-x86\release\</OutDir>
+    <IntDir>..\..\..\intermediate\windows-x86\release\test-proxy\</IntDir>
+    <TargetName>test-proxy</TargetName>
+    <TargetExt>.exe</TargetExt>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <LinkIncremental>false</LinkIncremental>
+    <OutDir>..\..\..\bin\windows-x64\release\</OutDir>
+    <IntDir>..\..\..\intermediate\windows-x64\release\test-proxy\</IntDir>
+    <TargetName>test-proxy</TargetName>
+    <TargetExt>.exe</TargetExt>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release aarch64|ARM'">
+    <LinkIncremental>false</LinkIncremental>
+    <OutDir>..\..\..\bin\windows-aarch64\release\</OutDir>
+    <IntDir>..\..\..\intermediate\windows-aarch64\release\test-proxy\</IntDir>
+    <TargetName>test-proxy</TargetName>
+    <TargetExt>.exe</TargetExt>
+  </PropertyGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+    <ClCompile>
+      <PrecompiledHeader>NotUsing</PrecompiledHeader>
+      <WarningLevel>Level3</WarningLevel>
+      <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <AdditionalIncludeDirectories>..\..\..;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+      <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+      <Optimization>Disabled</Optimization>
+      <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <ClCompile>
+      <PrecompiledHeader>NotUsing</PrecompiledHeader>
+      <WarningLevel>Level3</WarningLevel>
+      <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <AdditionalIncludeDirectories>..\..\..;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+      <DebugInformationFormat>EditAndContinue</DebugInformationFormat>
+      <Optimization>Disabled</Optimization>
+      <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug aarch64|ARM'">
+    <ClCompile>
+      <PrecompiledHeader>NotUsing</PrecompiledHeader>
+      <WarningLevel>Level3</WarningLevel>
+      <PreprocessorDefinitions>_DEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <AdditionalIncludeDirectories>..\..\..;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+      <DebugInformationFormat>ProgramDatabase</DebugInformationFormat>
+      <Optimization>Disabled</Optimization>
+      <RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <ClCompile>
+      <PrecompiledHeader>NotUsing</PrecompiledHeader>
+      <WarningLevel>Level3</WarningLevel>
+      <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <AdditionalIncludeDirectories>..\..\..;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+      <Optimization>Full</Optimization>
+      <FunctionLevelLinking>true</FunctionLevelLinking>
+      <IntrinsicFunctions>true</IntrinsicFunctions>
+      <MinimalRebuild>false</MinimalRebuild>
+      <StringPooling>true</StringPooling>
+      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <EnableCOMDATFolding>true</EnableCOMDATFolding>
+      <OptimizeReferences>true</OptimizeReferences>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <ClCompile>
+      <PrecompiledHeader>NotUsing</PrecompiledHeader>
+      <WarningLevel>Level3</WarningLevel>
+      <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <AdditionalIncludeDirectories>..\..\..;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+      <Optimization>Full</Optimization>
+      <FunctionLevelLinking>true</FunctionLevelLinking>
+      <IntrinsicFunctions>true</IntrinsicFunctions>
+      <MinimalRebuild>false</MinimalRebuild>
+      <StringPooling>true</StringPooling>
+      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <EnableCOMDATFolding>true</EnableCOMDATFolding>
+      <OptimizeReferences>true</OptimizeReferences>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release aarch64|ARM'">
+    <ClCompile>
+      <PrecompiledHeader>NotUsing</PrecompiledHeader>
+      <WarningLevel>Level3</WarningLevel>
+      <PreprocessorDefinitions>NDEBUG;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <AdditionalIncludeDirectories>..\..\..;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+      <Optimization>Full</Optimization>
+      <FunctionLevelLinking>true</FunctionLevelLinking>
+      <IntrinsicFunctions>true</IntrinsicFunctions>
+      <MinimalRebuild>false</MinimalRebuild>
+      <StringPooling>true</StringPooling>
+      <RuntimeLibrary>MultiThreaded</RuntimeLibrary>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <EnableCOMDATFolding>true</EnableCOMDATFolding>
+      <OptimizeReferences>true</OptimizeReferences>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemGroup>
+    <ClCompile Include="..\..\..\tools\test-proxy\test-proxy-main.cpp" />
+  </ItemGroup>
+  <ItemGroup>
+    <ProjectReference Include="..\compiler-core\compiler-core.vcxproj">
+      <Project>{12C1E89D-F5D0-41D3-8E8D-FB3F358F8126}</Project>
+    </ProjectReference>
+    <ProjectReference Include="..\core\core.vcxproj">
+      <Project>{F9BE7957-8399-899E-0C49-E714FDDD4B65}</Project>
+    </ProjectReference>
+    <ProjectReference Include="..\slang\slang.vcxproj">
+      <Project>{DB00DA62-0533-4AFD-B59F-A67D5B3A0808}</Project>
+    </ProjectReference>
+  </ItemGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+  <ImportGroup Label="ExtensionTargets">
+  </ImportGroup>
+</Project>
\ No newline at end of file
diff --git a/build/visual-studio/test-proxy/test-proxy.vcxproj.filters b/build/visual-studio/test-proxy/test-proxy.vcxproj.filters
new file mode 100644
index 000000000..965d73999
--- /dev/null
+++ b/build/visual-studio/test-proxy/test-proxy.vcxproj.filters
@@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup>
+    <Filter Include="Source Files">
+      <UniqueIdentifier>{E9C7FDCE-D52A-8D73-7EB0-C5296AF258F6}</UniqueIdentifier>
+    </Filter>
+  </ItemGroup>
+  <ItemGroup>
+    <ClCompile Include="..\..\..\tools\test-proxy\test-proxy-main.cpp">
+      <Filter>Source Files</Filter>
+    </ClCompile>
+  </ItemGroup>
+</Project>
\ No newline at end of file
diff --git a/tests/hlsl-intrinsic/literal-int64.slang b/tests/hlsl-intrinsic/literal-int64.slang
index 9dea6f72e..226a12155 100644
--- a/tests/hlsl-intrinsic/literal-int64.slang
+++ b/tests/hlsl-intrinsic/literal-int64.slang
@@ -3,7 +3,7 @@
 //DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -shaderobj
 // No support with Dx12 with dxbc. Needs SM6.0 + dxil
 //DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -shaderobj
-//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -profile cs_6_0 -dx12 -use-dxil -shaderobj
+//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -profile cs_6_0 -dx12 -use-dxil -shaderobj -render-feature hardware-device
 //TEST(compute, vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature int64
 //TEST(compute):COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
 
diff --git a/tests/hlsl-intrinsic/matrix-double-reduced-intrinsic.slang b/tests/hlsl-intrinsic/matrix-double-reduced-intrinsic.slang
index 82f48399e..e5df09f61 100644
--- a/tests/hlsl-intrinsic/matrix-double-reduced-intrinsic.slang
+++ b/tests/hlsl-intrinsic/matrix-double-reduced-intrinsic.slang
@@ -4,7 +4,7 @@
 //TEST(compute):COMPARE_COMPUTE_EX:-cpu -compute -output-using-type -shaderobj
 //DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -output-using-type -shaderobj
 //DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -output-using-type -shaderobj
-//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -profile sm_6_0 -use-dxil -output-using-type -shaderobj
+//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -profile sm_6_0 -use-dxil -output-using-type -shaderobj -render-feature hardware-device
 //DISABLE_TEST(compute, vulkan):COMPARE_COMPUTE_EX:-vk -compute -output-using-type -shaderobj -render-feature double
 //TEST(compute):COMPARE_COMPUTE_EX:-cuda -compute -output-using-type -shaderobj
 
diff --git a/tests/hlsl-intrinsic/matrix-float.slang b/tests/hlsl-intrinsic/matrix-float.slang
index 7ad68e9e1..09848d5a6 100644
--- a/tests/hlsl-intrinsic/matrix-float.slang
+++ b/tests/hlsl-intrinsic/matrix-float.slang
@@ -3,7 +3,7 @@
 
 //TEST(compute):COMPARE_COMPUTE_EX:-cpu -compute -output-using-type -shaderobj
 //TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -output-using-type -shaderobj
-//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -output-using-type -shaderobj
+//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -output-using-type -shaderobj -render-feature hardware-device
 //DISABLE_TEST(compute, vulkan):COMPARE_COMPUTE_EX:-vk -compute -output-using-type -shaderobj
 //TEST(compute, vulkan):COMPARE_COMPUTE_EX:-cuda -compute -output-using-type -shaderobj
 
diff --git a/tests/hlsl-intrinsic/scalar-double-d3d-intrinsic.slang b/tests/hlsl-intrinsic/scalar-double-d3d-intrinsic.slang
index 36f8ef130..5df6dce91 100644
--- a/tests/hlsl-intrinsic/scalar-double-d3d-intrinsic.slang
+++ b/tests/hlsl-intrinsic/scalar-double-d3d-intrinsic.slang
@@ -3,7 +3,7 @@
 //DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -output-using-type -shaderobj
 // This is disabled because Dx12/DXBC doing double writes to a structured buffer can fail
 //DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -output-using-type -shaderobj
-//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -profile sm_6_0 -use-dxil -output-using-type -shaderobj
+//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -profile sm_6_0 -use-dxil -output-using-type -shaderobj -render-feature hardware-device
 //TEST(compute, vulkan):COMPARE_COMPUTE_EX:-vk -compute -output-using-type -shaderobj -render-feature double
 //TEST(compute):COMPARE_COMPUTE_EX:-cuda -compute -output-using-type -shaderobj
 
diff --git a/tests/hlsl-intrinsic/scalar-int64.slang b/tests/hlsl-intrinsic/scalar-int64.slang
index 0fdc5a36d..17ab4a9f9 100644
--- a/tests/hlsl-intrinsic/scalar-int64.slang
+++ b/tests/hlsl-intrinsic/scalar-int64.slang
@@ -3,7 +3,7 @@
 //DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -shaderobj
 // No support with Dx12 with dxbc. Needs SM6.0 + dxil
 //DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -shaderobj
-//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -profile cs_6_0 -dx12 -use-dxil -shaderobj
+//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -profile cs_6_0 -dx12 -use-dxil -shaderobj -render-feature hardware-device
 //TEST(compute, vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature int64
 //TEST(compute):COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
 
diff --git a/tests/hlsl-intrinsic/scalar-uint64.slang b/tests/hlsl-intrinsic/scalar-uint64.slang
index 314e37b94..f195f17f2 100644
--- a/tests/hlsl-intrinsic/scalar-uint64.slang
+++ b/tests/hlsl-intrinsic/scalar-uint64.slang
@@ -4,7 +4,7 @@
 // No support for uint64_t on fxc - we need SM6.0 and dxil
 // https://docs.microsoft.com/en-us/windows/win32/direct3dhlsl/hlsl-shader-model-6-0-features-for-direct3d-12
 //DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -shaderobj
-//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -profile cs_6_0 -use-dxil -shaderobj
+//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -profile cs_6_0 -use-dxil -shaderobj -render-feature hardware-device
 //TEST(compute, vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature int64
 //TEST(compute, vulkan):COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
 
diff --git a/tests/hlsl-intrinsic/vector-double-reduced-intrinsic.slang b/tests/hlsl-intrinsic/vector-double-reduced-intrinsic.slang
index b75f5efc4..c2280a72c 100644
--- a/tests/hlsl-intrinsic/vector-double-reduced-intrinsic.slang
+++ b/tests/hlsl-intrinsic/vector-double-reduced-intrinsic.slang
@@ -2,7 +2,7 @@
 // TODO(JS):
 // On CI systems DX11 test failed, so disable for now
 //DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -output-using-type -shaderobj
-//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -output-using-type -shaderobj
+//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -output-using-type -shaderobj -render-feature hardware-device
 //TEST(compute, vulkan):COMPARE_COMPUTE_EX:-vk -compute -output-using-type -shaderobj -render-feature double
 //TEST(compute, vulkan):COMPARE_COMPUTE_EX:-cuda -compute -output-using-type -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-active-count-bits.slang b/tests/hlsl-intrinsic/wave-active-count-bits.slang
index 0782fee11..45fdd7e02 100644
--- a/tests/hlsl-intrinsic/wave-active-count-bits.slang
+++ b/tests/hlsl-intrinsic/wave-active-count-bits.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -render-features cuda_sm_7_0 -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-active-product.slang b/tests/hlsl-intrinsic/wave-active-product.slang
index 5d7b85026..a252b4d6d 100644
--- a/tests/hlsl-intrinsic/wave-active-product.slang
+++ b/tests/hlsl-intrinsic/wave-active-product.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -render-features cuda_sm_7_0 -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-is-first-lane.slang b/tests/hlsl-intrinsic/wave-is-first-lane.slang
index 300e78801..093bf4108 100644
--- a/tests/hlsl-intrinsic/wave-is-first-lane.slang
+++ b/tests/hlsl-intrinsic/wave-is-first-lane.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -render-features cuda_sm_7_0 -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-mask/wave-is-first-lane.slang b/tests/hlsl-intrinsic/wave-mask/wave-is-first-lane.slang
index 37c49d805..285c9c7af 100644
--- a/tests/hlsl-intrinsic/wave-mask/wave-is-first-lane.slang
+++ b/tests/hlsl-intrinsic/wave-mask/wave-is-first-lane.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave-mask, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-mask/wave-matrix.slang b/tests/hlsl-intrinsic/wave-mask/wave-matrix.slang
index 8082545fb..650671608 100644
--- a/tests/hlsl-intrinsic/wave-mask/wave-matrix.slang
+++ b/tests/hlsl-intrinsic/wave-mask/wave-matrix.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave-mask, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //DISABLE_TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-mask/wave-prefix-product.slang b/tests/hlsl-intrinsic/wave-mask/wave-prefix-product.slang
index 4ebd4e95f..b12e9c1b3 100644
--- a/tests/hlsl-intrinsic/wave-mask/wave-prefix-product.slang
+++ b/tests/hlsl-intrinsic/wave-mask/wave-prefix-product.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave-mask, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-mask/wave-prefix-sum.slang b/tests/hlsl-intrinsic/wave-mask/wave-prefix-sum.slang
index 7d7f76d6c..51e9b7600 100644
--- a/tests/hlsl-intrinsic/wave-mask/wave-prefix-sum.slang
+++ b/tests/hlsl-intrinsic/wave-mask/wave-prefix-sum.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave-mask, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-mask/wave-read-lane-at-vk.slang b/tests/hlsl-intrinsic/wave-mask/wave-read-lane-at-vk.slang
index d4ccbea27..ec6dfb6a1 100644
--- a/tests/hlsl-intrinsic/wave-mask/wave-read-lane-at-vk.slang
+++ b/tests/hlsl-intrinsic/wave-mask/wave-read-lane-at-vk.slang
@@ -2,7 +2,7 @@
 // We have this 'simple' test, because we can't do matrix (or imat) operations on GLSL/Vk target
 
 //TEST_CATEGORY(wave-mask, compute)
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj
 
 //TEST_INPUT:ubuffer(data=[0 0 0 0], stride=4):out,name outputBuffer
diff --git a/tests/hlsl-intrinsic/wave-mask/wave-read-lane-at.slang b/tests/hlsl-intrinsic/wave-mask/wave-read-lane-at.slang
index 954d05559..b98bc65ba 100644
--- a/tests/hlsl-intrinsic/wave-mask/wave-read-lane-at.slang
+++ b/tests/hlsl-intrinsic/wave-mask/wave-read-lane-at.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave-mask, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 // Disabled on VK because glsl can't do WaveReadLaneAt on matrix. 
 //DISABLE_TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
diff --git a/tests/hlsl-intrinsic/wave-mask/wave-vector.slang b/tests/hlsl-intrinsic/wave-mask/wave-vector.slang
index d51fbc6a3..0585bae53 100644
--- a/tests/hlsl-intrinsic/wave-mask/wave-vector.slang
+++ b/tests/hlsl-intrinsic/wave-mask/wave-vector.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave-mask, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-mask/wave.slang b/tests/hlsl-intrinsic/wave-mask/wave.slang
index 5718dbcf1..4e2534cb6 100644
--- a/tests/hlsl-intrinsic/wave-mask/wave.slang
+++ b/tests/hlsl-intrinsic/wave-mask/wave.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave-mask, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-matrix.slang b/tests/hlsl-intrinsic/wave-matrix.slang
index a3fe0b2e9..da6665eb6 100644
--- a/tests/hlsl-intrinsic/wave-matrix.slang
+++ b/tests/hlsl-intrinsic/wave-matrix.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //DISABLE_TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -render-features cuda_sm_7_0 -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-prefix-count-bits.slang b/tests/hlsl-intrinsic/wave-prefix-count-bits.slang
index 0c726e549..b0e2464de 100644
--- a/tests/hlsl-intrinsic/wave-prefix-count-bits.slang
+++ b/tests/hlsl-intrinsic/wave-prefix-count-bits.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -render-features cuda_sm_7_0 -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-prefix-product.slang b/tests/hlsl-intrinsic/wave-prefix-product.slang
index 4c412fe9f..a092de065 100644
--- a/tests/hlsl-intrinsic/wave-prefix-product.slang
+++ b/tests/hlsl-intrinsic/wave-prefix-product.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -render-features cuda_sm_7_0 -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-prefix-sum.slang b/tests/hlsl-intrinsic/wave-prefix-sum.slang
index a90051d4e..c72ce82be 100644
--- a/tests/hlsl-intrinsic/wave-prefix-sum.slang
+++ b/tests/hlsl-intrinsic/wave-prefix-sum.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -render-features cuda_sm_7_0 -shaderobj
 
diff --git a/tests/hlsl-intrinsic/wave-read-lane-at-vk.slang b/tests/hlsl-intrinsic/wave-read-lane-at-vk.slang
index 4fb80ac0a..b01694003 100644
--- a/tests/hlsl-intrinsic/wave-read-lane-at-vk.slang
+++ b/tests/hlsl-intrinsic/wave-read-lane-at-vk.slang
@@ -1,7 +1,7 @@
 // This is similar to wave-lane-at.slang but tests more limited supported types for vk.
 // We have this 'simple' test, because we can't do matrix (or imat) operations on GLSL/Vk target
 //TEST_CATEGORY(wave, compute)
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj
 
 //TEST_INPUT:ubuffer(data=[0 0 0 0], stride=4):out,name outputBuffer
diff --git a/tests/hlsl-intrinsic/wave-read-lane-at.slang b/tests/hlsl-intrinsic/wave-read-lane-at.slang
index 44976fad8..bae063209 100644
--- a/tests/hlsl-intrinsic/wave-read-lane-at.slang
+++ b/tests/hlsl-intrinsic/wave-read-lane-at.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 // Disabled on VK because glsl can't do WaveReadLaneAt on matrix. 
 //DISABLE_TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -render-features cuda_sm_7_0 -shaderobj
diff --git a/tests/hlsl-intrinsic/wave-vector.slang b/tests/hlsl-intrinsic/wave-vector.slang
index a87aa1ebb..cc39c7767 100644
--- a/tests/hlsl-intrinsic/wave-vector.slang
+++ b/tests/hlsl-intrinsic/wave-vector.slang
@@ -1,7 +1,7 @@
 //TEST_CATEGORY(wave, compute)
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
 //DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
-//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj
+//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile cs_6_0 -shaderobj -render-feature hardware-device
 //TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj -render-feature hardware-device
 //TEST:COMPARE_COMPUTE_EX:-cuda -compute -render-features cuda_sm_7_0 -shaderobj
 
diff --git a/tools/gfx/d3d/d3d-util.cpp b/tools/gfx/d3d/d3d-util.cpp
index d73b3f519..84b5de844 100644
--- a/tools/gfx/d3d/d3d-util.cpp
+++ b/tools/gfx/d3d/d3d-util.cpp
@@ -609,6 +609,31 @@ bool D3DUtil::isUAVBinding(slang::BindingType bindingType)
     }
 }
 
+int D3DUtil::getShaderModelFromProfileName(const char* name)
+{
+    UnownedStringSlice nameSlice(name);
+
+    if (nameSlice.endsWith("5_1"))
+        return D3D_SHADER_MODEL_5_1;
+    if (nameSlice.endsWith("6_0"))
+        return D3D_SHADER_MODEL_6_0;
+    if (nameSlice.endsWith("6_1"))
+        return D3D_SHADER_MODEL_6_1;
+    if (nameSlice.endsWith("6_2"))
+        return D3D_SHADER_MODEL_6_2;
+    if (nameSlice.endsWith("6_3"))
+        return D3D_SHADER_MODEL_6_3;
+    if (nameSlice.endsWith("6_4"))
+        return D3D_SHADER_MODEL_6_4;
+    if (nameSlice.endsWith("6_5"))
+        return D3D_SHADER_MODEL_6_5;
+    if (nameSlice.endsWith("6_6"))
+        return D3D_SHADER_MODEL_6_6;
+    if (nameSlice.endsWith("6_7"))
+        return 0x67;
+    return 0;
+}
+
 /* static */SlangResult D3DUtil::findAdapters(DeviceCheckFlags flags, const UnownedStringSlice& adapterName, IDXGIFactory* dxgiFactory, List<ComPtr<IDXGIAdapter>>& outDxgiAdapters)
 {
     Slang::String lowerAdapterName = Slang::String(adapterName).toLower();
diff --git a/tools/gfx/d3d/d3d-util.h b/tools/gfx/d3d/d3d-util.h
index e570c6ff6..4bca89612 100644
--- a/tools/gfx/d3d/d3d-util.h
+++ b/tools/gfx/d3d/d3d-util.h
@@ -94,6 +94,8 @@ class D3DUtil
 
     static bool isUAVBinding(slang::BindingType bindingType);
 
+    static int getShaderModelFromProfileName(const char* profile);
+
 };
 
 #if SLANG_GFX_HAS_DXR_SUPPORT
diff --git a/tools/gfx/d3d12/render-d3d12.cpp b/tools/gfx/d3d12/render-d3d12.cpp
index aa945fd85..d296e1edb 100644
--- a/tools/gfx/d3d12/render-d3d12.cpp
+++ b/tools/gfx/d3d12/render-d3d12.cpp
@@ -182,9 +182,11 @@ public:
             m_desc = {}; 
             m_desc1 = {};
             m_isWarp = false;
+            m_isSoftware = false;
         }
 
         bool m_isWarp;
+        bool m_isSoftware;
         ComPtr<IDXGIFactory> m_dxgiFactory;
         ComPtr<ID3D12Device> m_device;
         ComPtr<ID3D12Device5> m_device5;
@@ -4232,6 +4234,8 @@ Result D3D12Device::_createDevice(DeviceCheckFlags deviceCheckFlags, const Unown
     outDeviceInfo.m_dxgiFactory = dxgiFactory;
     outDeviceInfo.m_adapter = adapter;
     outDeviceInfo.m_isWarp = D3DUtil::isWarp(dxgiFactory, adapter);
+    outDeviceInfo.m_isSoftware = outDeviceInfo.m_isWarp || ((outDeviceInfo.m_desc1.Flags & DXGI_ADAPTER_FLAG_SOFTWARE) != 0)
+        || outDeviceInfo.m_desc.VendorId == 5140;
 
     return SLANG_OK;
 }
@@ -4354,6 +4358,15 @@ Result D3D12Device::initialize(const Desc& desc)
     // Set the device
     m_device = m_deviceInfo.m_device;
 
+    if (m_deviceInfo.m_isSoftware)
+    {
+        m_features.add("software-device");
+    }
+    else
+    {
+        m_features.add("hardware-device");
+    }
+
     // NVAPI
     if (desc.nvapiExtnSlot >= 0)
     {
@@ -4387,30 +4400,31 @@ Result D3D12Device::initialize(const Desc& desc)
 
     }
 
+    D3D12_FEATURE_DATA_SHADER_MODEL shaderModelData = {};
+    shaderModelData.HighestShaderModel = D3D_SHADER_MODEL_6_6;
+
     // Find what features are supported
     {
         // Check this is how this is laid out...
         SLANG_COMPILE_TIME_ASSERT(D3D_SHADER_MODEL_6_0 == 0x60);
 
         {
-            D3D12_FEATURE_DATA_SHADER_MODEL featureShaderModel;
-            featureShaderModel.HighestShaderModel = D3D_SHADER_MODEL(0x62);
-
             // TODO: Currently warp causes a crash when using half, so disable for now
-            if (SLANG_SUCCEEDED(m_device->CheckFeatureSupport(D3D12_FEATURE_SHADER_MODEL, &featureShaderModel, sizeof(featureShaderModel))) &&
+            if (SLANG_SUCCEEDED(m_device->CheckFeatureSupport(D3D12_FEATURE_SHADER_MODEL, &shaderModelData, sizeof(shaderModelData))) &&
                 m_deviceInfo.m_isWarp == false &&
-                featureShaderModel.HighestShaderModel >= 0x62)
+                shaderModelData.HighestShaderModel >= 0x62)
             {
                 // With sm_6_2 we have half
                 m_features.add("half");
             }
         }
-        // Check what min precision support we have
+        // Check double precision support
         {
             D3D12_FEATURE_DATA_D3D12_OPTIONS options;
             if (SLANG_SUCCEEDED(m_device->CheckFeatureSupport(D3D12_FEATURE_D3D12_OPTIONS, &options, sizeof(options))))
             {
-                auto minPrecisionSupport = options.MinPrecisionSupport;
+                if (options.DoublePrecisionFloatShaderOps)
+                    m_features.add("double");
             }
         }
         // Check ray tracing support
@@ -4474,10 +4488,56 @@ Result D3D12Device::initialize(const Desc& desc)
     m_device->QueryInterface<ID3D12Device5>(m_deviceInfo.m_device5.writeRef());
     m_device5 = m_deviceInfo.m_device5.get();
 #endif
+    // Check shader model version.
+    SlangCompileTarget compileTarget = SLANG_DXBC;
+    const char* profileName = "sm_5_1";
+    switch (shaderModelData.HighestShaderModel)
+    {
+    case D3D_SHADER_MODEL_5_1:
+        compileTarget = SLANG_DXBC;
+        profileName = "sm_5_1";
+        break;
+    case D3D_SHADER_MODEL_6_0:
+        compileTarget = SLANG_DXIL;
+        profileName = "sm_6_0";
+        break;
+    case D3D_SHADER_MODEL_6_1:
+        compileTarget = SLANG_DXIL;
+        profileName = "sm_6_1";
+        break;
+    case D3D_SHADER_MODEL_6_2:
+        compileTarget = SLANG_DXIL;
+        profileName = "sm_6_2";
+        break;
+    case D3D_SHADER_MODEL_6_3:
+        compileTarget = SLANG_DXIL;
+        profileName = "sm_6_3";
+        break;
+    case D3D_SHADER_MODEL_6_4:
+        compileTarget = SLANG_DXIL;
+        profileName = "sm_6_4";
+        break;
+    case D3D_SHADER_MODEL_6_5:
+        compileTarget = SLANG_DXIL;
+        profileName = "sm_6_5";
+        break;
+    default:
+        compileTarget = SLANG_DXIL;
+        profileName = "sm_6_6";
+        break;
+    }
+    // If user specified a higher shader model than what the system supports, return failure.
+    int userSpecifiedShaderModel = D3DUtil::getShaderModelFromProfileName(desc.slang.targetProfile);
+    if (userSpecifiedShaderModel > shaderModelData.HighestShaderModel)
+    {
+        getDebugCallback()->handleMessage(gfx::DebugMessageType::Error, gfx::DebugMessageSource::Layer,
+            "The requested shader model is not supported by the system.");
+        return SLANG_E_NOT_AVAILABLE;
+    }
     SLANG_RETURN_ON_FAIL(slangContext.initialize(
         desc.slang,
-        m_device5 ? SLANG_DXIL : SLANG_DXBC,
-        m_device5 ? "sm_6_5" : "sm_5_1",
+        compileTarget,
+        profileName,
         makeArray(slang::PreprocessorMacroDesc{"__D3D12__", "1"}).getView()));
 
     m_isInitialized = true;
diff --git a/tools/render-test/render-test-main.cpp b/tools/render-test/render-test-main.cpp
index 3f26f6d9b..689794cef 100644
--- a/tools/render-test/render-test-main.cpp
+++ b/tools/render-test/render-test-main.cpp
@@ -1358,7 +1358,7 @@ static SlangResult _innerMain(Slang::StdWriters* stdWriters, SlangSession* sessi
         
         desc.nvapiExtnSlot = int(nvapiExtnSlot);
         desc.slang.slangGlobalSession = session;
-
+        desc.slang.targetProfile = options.profileName.getBuffer();
         {
             SlangResult res = gfxCreateDevice(&desc, device.writeRef());
             if (SLANG_FAILED(res))