From 731f1fc6b26659dc8f62fbc1969c076b78ada24f Mon Sep 17 00:00:00 2001 From: jsmall-nvidia Date: Tue, 4 May 2021 16:24:51 -0400 Subject: CUDA half comparison support (#1834) * #include an absolute path didn't work - because paths were taken to always be relative. * Split out StringEscapeUtil. * Added StringEscapeUtil. * Fix typo in unix quoting type. * Small comment improvements. * Try to fix linux linking issue. * Fix typo. * Attempt to fix linux link issue. * Update VS proj even though nothing really changed. * Fix another typo issue. * Fix for windows issue. Fixed bug. * Make separate Utils for escaping. * Fix typo. * Split out into StringEscapeHandler. * Windows shell does handle removing quotes (so remove code to remove them). * Handle unescaping if not initiating using the shell. * Slight improvement around shell like decoding. * Simplify command extraction. * Add shared-library category type. * Fix bug in command extraction. * Typo in transcendental category. * Enable unit-test on in smoke test category. * Make parsing failing output as a failing test. * Fixes for transcendental tests. Disable tests that do not work. * Changed category parsing. * Removed the TestResult parameter from _gatherTestsForFile. Made testsList only output. * Remove testing if all tests were disabled. * Make args of CommandLine always unescaped. * Add category. * Don't need escaping on unix/linux. * Remove some no longer used functions. * Add requireSMVersion to CUDAExtensionTracker. * half-calc.slang now works for CUDA. * bit-cast-16-bit works on CUDA. * WIP handling of CUDA vector types. * Half swizzle CUDA. * Half vector test. * Fix swizzle half bug. * Fix compilation issue with narrowing to Index. * Add unary ops. * Add some vector scalar maths ops. * Add half vector conversions for CUDA. * Fix erroneous comment. * Support for half comparisons. * First pass test for half compare. * Fix bug in CUDA specialized emit control. Updated tests to have pre and post inc/dec. * Removed unneeded parts of the cuda prelude. * Half structured buffer works on CUDA. Co-authored-by: Tim Foley --- source/slang/slang-emit-cpp.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'source/slang/slang-emit-cpp.h') diff --git a/source/slang/slang-emit-cpp.h b/source/slang/slang-emit-cpp.h index 2ff922421..5ba509e7d 100644 --- a/source/slang/slang-emit-cpp.h +++ b/source/slang/slang-emit-cpp.h @@ -33,6 +33,7 @@ public: { bool isScalar() const { return rowCount <= 1 && colCount <= 1; } + BaseType elemType; int rowCount; int colCount; }; @@ -74,11 +75,15 @@ protected: virtual void emitLoopControlDecorationImpl(IRLoopControlDecoration* decl) SLANG_OVERRIDE; + virtual const UnownedStringSlice* getVectorElementNames(BaseType elemType, Index elemCount); + // Replaceable for classes derived from CPPSourceEmitter virtual SlangResult calcTypeName(IRType* type, CodeGenTarget target, StringBuilder& out); virtual SlangResult calcFuncName(const HLSLIntrinsic* specOp, StringBuilder& out); virtual SlangResult calcScalarFuncName(HLSLIntrinsic::Op op, IRBasicType* type, StringBuilder& outBuilder); + const UnownedStringSlice* getVectorElementNames(IRVectorType* vectorType); + void _maybeEmitSpecializedOperationDefinition(const HLSLIntrinsic* specOp); void _emitForwardDeclarations(const List& actions); @@ -96,10 +101,12 @@ protected: void _emitInOutParamType(IRType* type, String const& name, IRType* valueType); + UnownedStringSlice _getAndEmitSpecializedOperationDefinition(HLSLIntrinsic::Op op, IRType*const* argTypes, Int argCount, IRType* retType); static TypeDimension _getTypeDimension(IRType* type, bool vecSwap); - static void _emitAccess(const UnownedStringSlice& name, const TypeDimension& dimension, int row, int col, SourceWriter* writer); + + void _emitAccess(const UnownedStringSlice& name, const TypeDimension& dimension, int row, int col, SourceWriter* writer); UnownedStringSlice _getScalarFuncName(HLSLIntrinsic::Op operation, IRBasicType* scalarType); -- cgit v1.2.3