| commit | cbae883886be8913efb7cefc9abce5c3a88f689b | [log] [tgz] |
|---|---|---|
| author | Artem Belevich <tra@google.com> | Wed Apr 18 21:51:48 2018 +0000 |
| committer | Artem Belevich <tra@google.com> | Wed Apr 18 21:51:48 2018 +0000 |
| tree | ec13e7a5a4e299625726fda13fad96a2af650c9c | |
| parent | e6a7df8ac466353a0f446cad57c78f3baaf114e5 [diff] |
[NVPTX, CUDA] Added support for m8n32k16 and m32n8k16 variants of wmma instructions. The new instructions were added added for sm_70+ GPUs in CUDA-9.1. Differential Revision: https://reviews.llvm.org/D45068 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@330296 91177308-0d34-0410-b5e6-96231b3b80d8