1 Commits

Author SHA1 Message Date
Matt Arsenault
66ee794064 AMDGPU: Fix verifier error on splatted opencl fmin/fmax and ldexp calls
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.

https://reviews.llvm.org/D158077
2023-08-16 09:42:26 -04:00