From e3fe0319467546bae070137c58dcf8f9fbe93c79 Mon Sep 17 00:00:00 2001
From: jsmall-nvidia <jsmall@nvidia.com>
Date: Thu, 19 Dec 2019 11:23:14 -0500
Subject: 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.
---
 tests/cuda/compile-to-cuda.slang | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)
 create mode 100644 tests/cuda/compile-to-cuda.slang

(limited to 'tests/cuda')

diff --git a/tests/cuda/compile-to-cuda.slang b/tests/cuda/compile-to-cuda.slang
new file mode 100644
index 000000000..6166aaf0b
--- /dev/null
+++ b/tests/cuda/compile-to-cuda.slang
@@ -0,0 +1,29 @@
+//DISABLE_TEST(smoke):SIMPLE: -target ptx -entry computeMain -stage compute 
+
+//TEST_INPUT:ubuffer(data=[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0], stride=4):out,name=outputBuffer
+RWStructuredBuffer<int> outputBuffer : register(u0);
+
+int quantize(double value)
+{
+    return int(value * 256);
+}
+
+int quantize(float value)
+{
+    return int(value * 256);
+}
+
+[numthreads(4, 1, 1)]
+void computeMain(uint3 dispatchThreadID : SV_DispatchThreadID)
+{
+    float values[] = { -9, 9, -3, 3 };
+
+	int tid = int(dispatchThreadID.x);
+    float value = values[tid];
+    
+    outputBuffer[tid * 4] = quantize(sin(value));
+    outputBuffer[tid * 4 + 1] = quantize(cos(value));
+    
+    outputBuffer[tid * 4 + 2] = quantize(sin(double(value)));
+    outputBuffer[tid * 4 + 3] = quantize(cos(double(value)));
+}
-- 
cgit v1.2.3