diff options
| author | Mészáros Gergely <gergely.meszaros@intel.com> | 2025-07-29 15:14:41 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-29 15:14:41 +0200 |
| commit | b5fe3eb2d17b711fded1a8c2fbd05a9e4dc06a7f (patch) | |
| tree | fa746f21874ad028d887fd1f48f74cec5a5df140 | |
| parent | 29e02d792b8cc1bf9017a9ca90b3d9f7cff56fb6 (diff) | |
| download | llvm-b5fe3eb2d17b711fded1a8c2fbd05a9e4dc06a7f.zip llvm-b5fe3eb2d17b711fded1a8c2fbd05a9e4dc06a7f.tar.gz llvm-b5fe3eb2d17b711fded1a8c2fbd05a9e4dc06a7f.tar.bz2 | |
[OpenCL] Add decls for cl_intel_bfloat16_conversions (#150393)
These map to SPIR-V instructions, which are long supported by the llvm
SPIR-V target [1] and the llvm-spirv translator [2].
Intel's offline compiler (ocloc) and OpenCL implementation trivially
supports these, by having these same declarations [3] and relying on
llvm-spirv to map calls to them to their corresponding SPIR-V
instructions.
[1]:
https://github.com/llvm/llvm-project/blob/531cf8298b08eacdf670bac8c28db97a5dc8cb01/llvm/lib/Target/SPIRV/SPIRVBuiltins.td#L1546C11-L1546C27
[2]:
https://github.com/KhronosGroup/SPIRV-LLVM-Translator/blob/10c7569b3c4cb456fbfdcc86c3de45d46c7f5fa8/lib/SPIRV/OCLUtil.h#L327
[3]:
https://github.com/intel/intel-graphics-compiler/blob/342c4fb729ff6a20a41e19adc8329ad18ba05660/IGC/BiFModule/Languages/OpenCL/opencl_cth_released.h#L6899
| -rw-r--r-- | clang/lib/Headers/opencl-c.h | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/clang/lib/Headers/opencl-c.h b/clang/lib/Headers/opencl-c.h index e1e0fde..f65b4b3 100644 --- a/clang/lib/Headers/opencl-c.h +++ b/clang/lib/Headers/opencl-c.h @@ -18410,6 +18410,22 @@ intel_sub_group_avc_mce_convert_to_sic_result( #pragma OPENCL EXTENSION cl_intel_device_side_avc_motion_estimation : end #endif // cl_intel_device_side_avc_motion_estimation +#if defined(cl_intel_bfloat16_conversions) +ushort __ovld intel_convert_bfloat16_as_ushort(float source); +ushort2 __ovld intel_convert_bfloat162_as_ushort2(float2 source); +ushort3 __ovld intel_convert_bfloat163_as_ushort3(float3 source); +ushort4 __ovld intel_convert_bfloat164_as_ushort4(float4 source); +ushort8 __ovld intel_convert_bfloat168_as_ushort8(float8 source); +ushort16 __ovld intel_convert_bfloat1616_as_ushort16(float16 source); + +float __ovld intel_convert_as_bfloat16_float(ushort source); +float2 __ovld intel_convert_as_bfloat162_float2(ushort2 source); +float3 __ovld intel_convert_as_bfloat163_float3(ushort3 source); +float4 __ovld intel_convert_as_bfloat164_float4(ushort4 source); +float8 __ovld intel_convert_as_bfloat168_float8(ushort8 source); +float16 __ovld intel_convert_as_bfloat1616_float16(ushort16 source); +#endif // cl_intel_bfloat16_conversions + #ifdef cl_amd_media_ops uint __ovld amd_bitalign(uint, uint, uint); uint2 __ovld amd_bitalign(uint2, uint2, uint2); |