forked from OSchip/llvm-project
b8d1994778
When sampling from images with coordinates that only have 16 bit accuracy, convert the image intrinsic call to use a16 or g16. This does only happen if the target hardware supports it. An alternative would be to always apply this combination, independent of the target hardware and extend 16 bit arguments to 32 bit arguments during legalization. To me, this sounds like an unnecessary roundtrip that could prevent some further InstCombine optimizations. Differential Revision: https://reviews.llvm.org/D85887 |
||
|---|---|---|
| .. | ||
| amdgcn-demanded-vector-elts.ll | ||
| amdgcn-intrinsics-gfx8.ll | ||
| amdgcn-intrinsics.ll | ||
| ldexp.ll | ||
| lit.local.cfg | ||
| memcpy-from-constant.ll | ||
| tan.ll | ||