WIP CUDA source emit (#1157)

* CPPCompiler -> DownstreamCompiler

* Added DownstreamCompileResult to start abstraction such that we don't need files.

* * Split out slang-blob.cpp
* Made CompileResult hold a DownstreamCompileResult - for access to binary or ISlangSharedLibrary

* Keep temporary files in scope.

* Add a hash to the hex dump stream.

* Move all file tracking into DownstreamCompiler.

* WIP support for nvrtc.

* WIP: Adding support for nvrtc compiler.
Adding enum types, wiring up the nvrtc into slang.

* Fix remaining CPPCompiler references.

* Fix order issue on target string matching.

* Use ISlangSharedLibrary for nvrtc.

* Use DownstreamCompiler for nvrtc.

* WIP first pass at compilation win nvrtc.

* Added testing if file is on file system into CommandLineDownstreamCompiler.
Added sourceContentsPath.

* Make test cuda-compile.cu work by just compiling not comparing output.

* Genearlize DownstreamCompiler usage.

* Fix warning on clang.

* Remove CompilerType from DownstreamCompiler.

* Use DownstreamCompiler interface for all compilers.

NOTE for FXC, DXC and GLSLANG this doesn't mean using 'compile' - it's still extracting functions from shared library.

* Replace DownstreamCompiler::SourceType -> SlangSourceLanguage

* Replace _canCompile with something data driven.

* Fix compiling on gcc/clang for DownstreamCompiler.

* Moved some text conversions into DownstreamCompiler.

* Fix problem on non-vc builds with not having return on locateCompilers for VS.

* Change so no warning for code not reachable on locateCompilers for vs.

* WIP: CUDA code generation - currently just using CPU layout and HLSL.

* emitXXXForEntryPoint -> emitEntryPointSource
emitSourceForEntryPoint -> emitEntryPointSourceFromIR
Fix up generating cuda to get PTX.

* WIP emitting cuda for IR.

* Small improvements to CUDA ouput.

* Disable the CUDA emit test, as output not currently compilable.

1 files changed, 113 insertions, 0 deletions

diff --git a/source/slang/slang-type-layout.cpp b/source/slang/slang-type-layout.cpp
index 88e62323b..772686163 100644
--- a/source/slang/slang-type-layout.cpp
+++ b/source/slang/slang-type-layout.cpp
@@ -398,6 +398,13 @@ struct CPULayoutRulesImpl : DefaultLayoutRulesImpl
     }
 };
 
+// TODO(JS): Most likely wrong. For layout for CUDA, we'll just do the default to get things up and running
+struct CUDALayoutRulesImpl : DefaultLayoutRulesImpl
+{
+    typedef DefaultLayoutRulesImpl Super;
+};
+
+
 struct HLSLStructuredBufferLayoutRulesImpl : DefaultLayoutRulesImpl
 {
     // HLSL structured buffers drop the restrictions added for constant buffers,
@@ -653,9 +660,29 @@ struct CPULayoutRulesFamilyImpl : LayoutRulesFamilyImpl
     LayoutRulesImpl* getStructuredBufferRules() override;
 };
 
+struct CUDALayoutRulesFamilyImpl : LayoutRulesFamilyImpl
+{
+    virtual LayoutRulesImpl* getConstantBufferRules() override;
+    virtual LayoutRulesImpl* getPushConstantBufferRules() override;
+    virtual LayoutRulesImpl* getTextureBufferRules() override;
+    virtual LayoutRulesImpl* getVaryingInputRules() override;
+    virtual LayoutRulesImpl* getVaryingOutputRules() override;
+    virtual LayoutRulesImpl* getSpecializationConstantRules() override;
+    virtual LayoutRulesImpl* getShaderStorageBufferRules() override;
+    virtual LayoutRulesImpl* getParameterBlockRules() override;
+
+    LayoutRulesImpl* getRayPayloadParameterRules()      override;
+    LayoutRulesImpl* getCallablePayloadParameterRules() override;
+    LayoutRulesImpl* getHitAttributesParameterRules()   override;
+
+    LayoutRulesImpl* getShaderRecordConstantBufferRules() override;
+    LayoutRulesImpl* getStructuredBufferRules() override;
+};
+
 GLSLLayoutRulesFamilyImpl kGLSLLayoutRulesFamilyImpl;
 HLSLLayoutRulesFamilyImpl kHLSLLayoutRulesFamilyImpl;
 CPULayoutRulesFamilyImpl kCPULayoutRulesFamilyImpl;
+CUDALayoutRulesFamilyImpl kCUDALayoutRulesFamilyImpl;
 
 // CPU case
 
@@ -703,6 +730,12 @@ struct CPUObjectLayoutRulesImpl : ObjectLayoutRulesImpl
 };
 
 
+// TODO(JS): Most likely wrong! Use CPU layout for CUDA for now
+struct CUDAObjectLayoutRulesImpl : CPUObjectLayoutRulesImpl
+{
+    typedef CPUObjectLayoutRulesImpl Super;
+
+};
 
 static CPUObjectLayoutRulesImpl kCPUObjectLayoutRulesImpl;
 static CPULayoutRulesImpl kCPULayoutRulesImpl;
@@ -711,6 +744,16 @@ LayoutRulesImpl kCPULayoutRulesImpl_ = {
     &kCPULayoutRulesFamilyImpl, &kCPULayoutRulesImpl, &kCPUObjectLayoutRulesImpl,
 };
 
+// CUDA
+
+static CUDAObjectLayoutRulesImpl kCUDAObjectLayoutRulesImpl;
+static CUDALayoutRulesImpl kCUALayoutRulesImpl;
+
+LayoutRulesImpl kCUDALayoutRulesImpl_ = {
+    &kCPULayoutRulesFamilyImpl, &kCUALayoutRulesImpl, &kCUDAObjectLayoutRulesImpl,
+};
+
+
 // GLSL cases
 
 LayoutRulesImpl kStd140LayoutRulesImpl_ = {
@@ -986,6 +1029,69 @@ LayoutRulesImpl* CPULayoutRulesFamilyImpl::getStructuredBufferRules()
     return &kCPULayoutRulesImpl_;
 }
 
+// CUDA Family
+
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getConstantBufferRules()
+{
+    return &kCPULayoutRulesImpl_;
+}
+
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getPushConstantBufferRules()
+{
+    return &kCPULayoutRulesImpl_;
+}
+
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getTextureBufferRules()
+{
+    return nullptr;
+}
+
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getVaryingInputRules()
+{
+    return nullptr;
+}
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getVaryingOutputRules()
+{
+    return nullptr;
+}
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getSpecializationConstantRules()
+{
+    return nullptr;
+}
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getShaderStorageBufferRules()
+{
+    return nullptr;
+}
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getParameterBlockRules()
+{
+    // Not clear - just use similar to CPU 
+    return &kCUDALayoutRulesImpl_;
+}
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getRayPayloadParameterRules()
+{
+    return nullptr;
+}
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getCallablePayloadParameterRules()
+{
+    return nullptr;
+}
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getHitAttributesParameterRules()
+{
+    return nullptr;
+}
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getShaderRecordConstantBufferRules()
+{
+    // Just following HLSLs lead for the moment
+    return &kCUDALayoutRulesImpl_;
+}
+
+LayoutRulesImpl* CUDALayoutRulesFamilyImpl::getStructuredBufferRules()
+{
+    return &kCUDALayoutRulesImpl_;
+}
+
+
+
 LayoutRulesFamilyImpl* getDefaultLayoutRulesFamilyForTarget(TargetRequest* targetReq)
 {
     switch (targetReq->getTarget())
@@ -1019,6 +1125,13 @@ LayoutRulesFamilyImpl* getDefaultLayoutRulesFamilyForTarget(TargetRequest* targe
         return &kCPULayoutRulesFamilyImpl;
     }
 
+    case CodeGenTarget::PTX:
+    case CodeGenTarget::CUDASource:
+    {
+        return &kCUDALayoutRulesFamilyImpl;
+    }
+
+
     default:
         return nullptr;
     }