From 47392bc72b826b4ad427b703391a77e697735a65 Mon Sep 17 00:00:00 2001 From: jsmall-nvidia Date: Tue, 21 Jan 2020 09:38:10 -0500 Subject: CUDA support improvements (#1168) * Add test result for compile-to-cuda * Add RAII for some CUDA types to simplify usage. * First pass handling of some instrinsics on CUDA (for example transcendentals) * CUDA working with built in intrinsics. * Add missing CUDA prelude intrinsics. * CUDA matches CPU output on simple-cross-compile.slang * First pass at hlsl-scalar-float-intrinsic.slang test. * Fix smoothstep impl on CUDA and CPU. * Fixed step intrinsic on CUDA/CPU. * Added operator[] to Matrix for C++, to allow row access. Needs a fix for CUDA. * Fixed warning on clang build. --- tests/cuda/compile-to-cuda.slang | 2 -- tests/cuda/compile-to-cuda.slang.expected.txt | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 2 deletions(-) create mode 100644 tests/cuda/compile-to-cuda.slang.expected.txt (limited to 'tests/cuda') diff --git a/tests/cuda/compile-to-cuda.slang b/tests/cuda/compile-to-cuda.slang index be7d775bd..d7399d469 100644 --- a/tests/cuda/compile-to-cuda.slang +++ b/tests/cuda/compile-to-cuda.slang @@ -8,12 +8,10 @@ RWStructuredBuffer outputBuffer : register(u0); [numthreads(4, 1, 1)] void computeMain(uint3 dispatchThreadID : SV_DispatchThreadID) { - int tid = int(dispatchThreadID.x); outputBuffer[tid * 4] = tid; outputBuffer[tid * 4 + 1] = tid + 1; outputBuffer[tid * 4 + 2] = tid + 2; outputBuffer[tid * 4 + 3] = tid + 3; - } diff --git a/tests/cuda/compile-to-cuda.slang.expected.txt b/tests/cuda/compile-to-cuda.slang.expected.txt new file mode 100644 index 000000000..27a9fcd89 --- /dev/null +++ b/tests/cuda/compile-to-cuda.slang.expected.txt @@ -0,0 +1,16 @@ +0 +1 +2 +3 +1 +2 +3 +4 +2 +3 +4 +5 +3 +4 +5 +6 -- cgit v1.2.3