[PATCH] D153023: AMDGPU: Correctly lower llvm.log.f32 and llvm.log10.f32

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

In D153023#4425892 <https://reviews.llvm.org/D153023#4425892>, @rampitec wrote:

> Coding is fine. Does it pass OpenCL conformance?

I tested all the permutations on math_brute_force (the combinations of DAZ, fast fma, log/log2/log10, DAG/gisel) I don’t believe conformance covers the finite only cases though


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D153023/new/

https://reviews.llvm.org/D153023