Apparently the spec has overloads for fmin/fmax and ldexp with one of
the operands as scalar. We need to broadcast the scalars to the vector
type.
Details
Details
Diff Detail
Diff Detail
Paths
| Differential D158077
AMDGPU: Fix verifier error on splatted opencl fmin/fmax and ldexp calls ClosedPublic Authored by arsenm on Aug 16 2023, 6:35 AM.
Details
Diff Detail
Revision Contents
Diff 550728 llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-fmax-splat.ll
llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-fmin-splat.ll
llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-ldexp-splat.ll
|