[PATCH] D104847: [Clang][NVPTX] Add NVPTX intrinsics and builtins for CUDA PTX 6.5 and 7.0 WMMA and MMA instructions
Steffen Larsen via Phabricator via cfe-commits
cfe-commits at lists.llvm.org
Thu Jun 24 04:30:54 PDT 2021
steffenlarsen created this revision.
steffenlarsen added a reviewer: tra.
Herald added subscribers: hiraditya, yaxunl, jholewinski.
steffenlarsen requested review of this revision.
Herald added subscribers: llvm-commits, cfe-commits, jdoerfert.
Herald added projects: clang, LLVM.
Adds NVPTX builtins and intrinsics for the CUDA PTX `wmma.load`, `wmma.store`, `wmma.mma`, and `mma` instructions added in PTX 6.5 and 7.0.
PTX ISA description of
- `wmma.load`: https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-wmma-ld
- `wmma.store`: https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-wmma-st
- `wmma.mma`: https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-wmma-mma
- `mma`: https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-instructions-mma
Overview of `wmma.mma` and `mma` matrix shape/type combinations added with specific PTX versions: https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#warp-level-matrix-shape
Authored-by: Steffen Larsen <steffen.larsen at codeplay.com>
Co-Authored-by: Stuart Adams <stuart.adams at codeplay.com>
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D104847
Files:
clang/include/clang/Basic/BuiltinsNVPTX.def
clang/lib/CodeGen/CGBuiltin.cpp
clang/test/CodeGen/builtins-nvptx-mma.cu
clang/test/CodeGen/builtins-nvptx-mma.py
llvm/include/llvm/IR/IntrinsicsNVVM.td
llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
llvm/lib/Target/NVPTX/NVPTXInstrInfo.td
llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
llvm/test/CodeGen/NVPTX/lit.local.cfg
llvm/test/CodeGen/NVPTX/wmma.py
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D104847.354199.patch
Type: text/x-patch
Size: 99278 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20210624/06348610/attachment-0001.bin>
More information about the cfe-commits
mailing list