diff options
| author | Shilei Tian <i@tianshilei.me> | 2025-08-19 16:03:45 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-08-19 16:03:45 -0400 |
| commit | b170f17861a12e91e67e9fe5951e2118cd3db164 (patch) | |
| tree | 1a512d0f3221c8d983e4812d6adcdb3b64f439f9 /libc/src/math/bf16sub.h | |
| parent | b35b6297fd5193e10e0c57d3371f7326fbd40ae3 (diff) | |
| download | llvm-main.zip llvm-main.tar.gz llvm-main.tar.bz2 | |
[AMDGPU] Add support for safe bfloat16 fdiv on targets with bf16 trans instructions (#154373)HEADmain
Recent changes introduced custom lowering for bf16 fdiv on targets that
support bf16 trans instructions, but only covered the unsafe version.
This PR extends that support to the safe variant.
For the safe version, the op is lowered by converting to float,
performing the div in float, and converting the result back to bf16.
This matches the behavior on targets that don't support bf16 trans
instructions.
Fixes SWDEV-550381.
Diffstat (limited to 'libc/src/math/bf16sub.h')
0 files changed, 0 insertions, 0 deletions