[PATCH] D38645: [NVPTX] Implemented wmma intrinsics and instructions.

[Artem Belevich via Phabricator via llvm-commits]

tra created this revision.
Herald added subscribers: hiraditya, sanjoy, jholewinski.

WMMA = "Warp Level Matrix Multiply-Accumulate".
These are the new instructions introduced in PTX6.0 and available
on sm_70 GPUs.

WMMA.MMA wins special medal for having 8 return values and 26 arguments. :-)


https://reviews.llvm.org/D38645

Files:
  llvm/include/llvm/IR/IntrinsicsNVVM.td
  llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
  llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.h
  llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
  llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
  llvm/test/CodeGen/NVPTX/wmma.py

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D38645.118071.patch
Type: text/x-patch
Size: 54134 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20171006/db86b8a0/attachment.bin>