projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 540e58a) | patch
Lower math.tan to __nv_tan[f] / __ocml_tan_f{32|64}
authorGoran Flegar <gflegar@google.com>
Wed, 11 Jan 2023 18:39:10 +0000 (19:39 +0100)
committerGoran Flegar <gflegar@google.com>
Thu, 12 Jan 2023 14:26:11 +0000 (15:26 +0100)
commitb7fe0d346b3049df6e3950159a5de74438d2737a
tree49ffd472ceeb0cea6d64a4f9bf02fa6722045c6etree | snapshot
parent540e58af6692bf373d9be4f99d320b4b0f753e3bcommit | diff
Lower math.tan to __nv_tan[f] / __ocml_tan_f{32|64}

At present math.tan fails to lower for NVVM and ROCDL.

Differential Revision: https://reviews.llvm.org/D141505
mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp diff | blob | history
mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp diff | blob | history
mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir diff | blob | history
mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl.mlir diff | blob | history
Domain: System / Toolchain;