diff options
| author | jsmall-nvidia <jsmall@nvidia.com> | 2022-11-10 18:38:19 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2022-11-10 15:38:19 -0800 |
| commit | 3e312b3062ab493c80d7d7eddf43c94ec59ecdb7 (patch) | |
| tree | b333332917f6095c39a10b176b8c57368679c214 /source/slang | |
| parent | 0b05fe33c82ee301c134f5b9a87a596aa47121c8 (diff) | |
Improvements to NVRTC diagnostic parsing (#2504)
* #include an absolute path didn't work - because paths were taken to always be relative.
* Float16 support for C++/CPU based targets with f16tof32 and f32tof16.
* Small correction around INF/NAN handling for f32tof16
* Small improvement to f16tof32
* Disable CUDA test for now.
* Improvements to NVRTC diagnostic parsing.
Handle compilerSpecificArgs.
Fix issue with terminating nul ending up in diagnostic string.
* Improved NVRTC error parsing.
f32tof16 and f16tof32 work in principal on CUDA.
* Small update to test, although they remain disabled.
* Work around SLANG_E_NOT_AVAILABLE being turned into ignored, when a legitimate error is found
* A more tightly constrained fallback NVRTC diagnostic parsing.
* Remove CharUtil, as not neeed.
Co-authored-by: Yong He <yonghe@outlook.com>
Diffstat (limited to 'source/slang')
| -rw-r--r-- | source/slang/hlsl.meta.slang | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/source/slang/hlsl.meta.slang b/source/slang/hlsl.meta.slang index ec2e6de95..1cff7d6f3 100644 --- a/source/slang/hlsl.meta.slang +++ b/source/slang/hlsl.meta.slang @@ -1742,6 +1742,8 @@ matrix<T,N,M> exp2(matrix<T,N,M> x) __target_intrinsic(glsl, "unpackHalf2x16($0).x") __glsl_version(420) __target_intrinsic(hlsl) +__cuda_sm_version(6.0) +__target_intrinsic(cuda, "__half2float(__short_as_half($0))") float f16tof32(uint value); __generic<let N : int> @@ -1757,6 +1759,8 @@ vector<float, N> f16tof32(vector<uint, N> value) __target_intrinsic(glsl, "packHalf2x16(vec2($0,0.0))") __glsl_version(420) __target_intrinsic(hlsl) +__cuda_sm_version(6.0) +__target_intrinsic(cuda, "__half_as_ushort(__float2half($0))") uint f32tof16(float value); __generic<let N : int> |