diff options
| author | Jakub Chlanda <j.chlanda@gmail.com> | 2022-03-01 10:29:54 -0800 |
|---|---|---|
| committer | Artem Belevich <tra@google.com> | 2022-03-01 11:07:11 -0800 |
| commit | a8951823024b38c455e839d40656ad533b4aa8ff (patch) | |
| tree | 33bd337d54aac830cb980c3d6d8b760f3b2d08df /llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp | |
| parent | 7a6d692b3b11e80fd19e7c9b65e1e6f70035c676 (diff) | |
| download | llvm-a8951823024b38c455e839d40656ad533b4aa8ff.zip llvm-a8951823024b38c455e839d40656ad533b4aa8ff.tar.gz llvm-a8951823024b38c455e839d40656ad533b4aa8ff.tar.bz2 | |
[NVPTX] Add more FMA intriniscs/builtins
This patch adds builtins/intrinsics for the following variants of FMA:
NOTE: follow-up commit with the missing clang-side changes.
- f16, f16x2
- rn
- rn_ftz
- rn_sat
- rn_ftz_sat
- rn_relu
- rn_ftz_relu
- bf16, bf16x2
- rn
- rn_relu
ptxas (Cuda compilation tools, release 11.0, V11.0.194) is happy with the generated assembly.
Differential Revision: https://reviews.llvm.org/D118977
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp')
0 files changed, 0 insertions, 0 deletions