DXIL ByteAddressBuffer doesn't support float4x4 in templated load

[Jasper-Bekkers]

struct PSInput
{
	float4 color : COLOR;
};

ByteAddressBuffer g_stuff;

float4 PSMain(PSInput input) : SV_TARGET
{
	return mul(g_stuff.Load<float4x4>(0), input.color);
}

Output:

C:\Users\Jasper\>dxc -Tps_6_5 -EPSMain test.hlsl

C:\Users\Jasper\>echo %ERRORLEVEL%
-1073741819

However,

struct PSInput
{
	float4 color : COLOR;
};

ByteAddressBuffer g_stuff;

struct Mat4x4Wrapper {
    float4x4 internal;
};

float4 PSMain(PSInput input) : SV_TARGET
{
	return mul(g_stuff.Load<Mat4x4Wrapper>(0).internal, input.color);
}

Run the same way, does result in correct DXIL output.

[Jasper-Bekkers]

Callstack:

 	dxcompiler.dll!llvm::Type::getScalarType() Line 46	C++
 	[Inline Frame] dxcompiler.dll!llvm::Type::isFPOrFPVectorTy() Line 183	C++
 	[Inline Frame] dxcompiler.dll!llvm::FPMathOperator::classof(const llvm::Instruction *) Line 317	C++
 	[Inline Frame] dxcompiler.dll!llvm::isa_impl<llvm::FPMathOperator,llvm::Instruction,void>::doit(const llvm::Instruction &) Line 56	C++
 	[Inline Frame] dxcompiler.dll!llvm::isa_impl_cl<llvm::FPMathOperator,llvm::Instruction *>::doit(const llvm::Instruction *) Line 82	C++
 	[Inline Frame] dxcompiler.dll!llvm::isa_impl_wrap<llvm::FPMathOperator,llvm::Instruction *,llvm::Instruction *>::doit(llvm::Instruction * const &) Line 122	C++
 	[Inline Frame] dxcompiler.dll!llvm::isa_impl_wrap<llvm::FPMathOperator,llvm::ilist_iterator<llvm::Instruction> const ,llvm::Instruction *>::doit(const llvm::ilist_iterator<llvm::Instruction> &) Line 112	C++
 	[Inline Frame] dxcompiler.dll!llvm::isa(const llvm::ilist_iterator<llvm::Instruction> &) Line 133	C++
 	[Inline Frame] dxcompiler.dll!llvm::dyn_cast(llvm::ilist_iterator<llvm::Instruction> &) Line 293	C++
 	dxcompiler.dll!TranslatePreciseAttributeOnFunction(llvm::Function & F, llvm::Module & M) Line 638	C++
 	dxcompiler.dll!`anonymous namespace'::DxilGenerationPass::TranslatePreciseAttribute() Line 684	C++
 	dxcompiler.dll!`anonymous namespace'::DxilGenerationPass::runOnModule(llvm::Module & M) Line 274	C++
 	dxcompiler.dll!`anonymous namespace'::MPPassManager::runOnModule(llvm::Module & M) Line 1643	C++
 	[Inline Frame] dxcompiler.dll!llvm::legacy::PassManagerImpl::run(llvm::Module &) Line 1745	C++
 	dxcompiler.dll!llvm::legacy::PassManager::run(llvm::Module & M) Line 1785	C++
 	dxcompiler.dll!`anonymous namespace'::EmitAssemblyHelper::EmitAssembly(clang::BackendAction Action, llvm::raw_pwrite_stream * OS) Line 739	C++
 	dxcompiler.dll!clang::EmitBackendOutput(clang::DiagnosticsEngine & Diags, const clang::CodeGenOptions & CGOpts, const clang::TargetOptions & TOpts, const clang::LangOptions & LOpts, llvm::StringRef TDesc, llvm::Module * M, clang::BackendAction Action, llvm::raw_pwrite_stream * OS) Line 760	C++
 	dxcompiler.dll!clang::BackendConsumer::HandleTranslationUnit(clang::ASTContext & C) Line 195	C++
 	dxcompiler.dll!clang::ParseAST(clang::Sema & S, bool PrintStats, bool SkipFunctionBodies) Line 162	C++
 	dxcompiler.dll!clang::ASTFrontendAction::ExecuteAction() Line 554	C++
 	dxcompiler.dll!clang::CodeGenAction::ExecuteAction() Line 804	C++
 	dxcompiler.dll!clang::FrontendAction::Execute() Line 469	C++
 	dxcompiler.dll!DxcCompiler::Compile(const DxcBuffer * pSource, const wchar_t * * pArguments, unsigned int argCount, IDxcIncludeHandler * pIncludeHandler, const _GUID & riid, void * * ppResult) Line 785	C++
 	dxcompiler.dll!hlsl::DxcCompilerAdapter::WrapCompile(int bPreprocess, IDxcBlob * pSource, const wchar_t * pSourceName, const wchar_t * pEntryPoint, const wchar_t * pTargetProfile, const wchar_t * * pArguments, unsigned int argCount, const DxcDefine * pDefines, unsigned int defineCount, IDxcIncludeHandler * pIncludeHandler, IDxcOperationResult * * ppResult, wchar_t * * ppDebugBlobName, IDxcBlob * * ppDebugBlob) Line 1418	C++
 	dxcompiler.dll!hlsl::DxcCompilerAdapter::CompileWithDebug(IDxcBlob * pSource, const wchar_t * pSourceName, const wchar_t * pEntryPoint, const wchar_t * pTargetProfile, const wchar_t * * pArguments, unsigned int argCount, const DxcDefine * pDefines, unsigned int defineCount, IDxcIncludeHandler * pIncludeHandler, IDxcOperationResult * * ppResult, wchar_t * * ppDebugBlobName, IDxcBlob * * ppDebugBlob) Line 1324	C++
 	dxcompiler.dll!hlsl::DxcCompilerAdapter::Compile(IDxcBlob * pSource, const wchar_t * pSourceName, const wchar_t * pEntryPoint, const wchar_t * pTargetProfile, const wchar_t * * pArguments, unsigned int argCount, const DxcDefine * pDefines, unsigned int defineCount, IDxcIncludeHandler * pIncludeHandler, IDxcOperationResult * * ppResult) Line 72	C++
 	dxc.exe!DxcContext::Compile() Line 868	C++
 	dxc.exe!dxc::main(int argc, const wchar_t * * argv_) Line 1323	C++
>	[Inline Frame] dxc.exe!invoke_main() Line 90	C++
 	dxc.exe!__scrt_common_main_seh() Line 288	C++
 	kernel32.dll!00007ff9dd9353fe()	Unknown
 	ntdll.dll!00007ff9de1c590b()	Unknown