Google Git
Sign in
llvm / llvm-project / mlir / f5a12a501e77431d094340f9532e1199f634e38e
commitf5a12a501e77431d094340f9532e1199f634e38e[log] [tgz]
authorThomas Raoux <thomasraoux@google.com>Wed Nov 10 14:32:15 2021 -0800
committerCopybara-Service <copybara-worker@google.com>Thu Nov 11 13:16:15 2021 -0800
tree677efbdec9586121447678b0fee5854b0b20aaf6
parentff1800773f1235c3fc9f8f7d67bc2a401f582a2e [diff]
[mlir][VectorToGPU] Support more cases in conversion to MMA ops

Support load with broadcast, elementwise divf op and remove the
hardcoded restriction on the vector size. Picking the right size should
be enfored by user and will fail conversion to llvm/spirv if it is not
supported.

Differential Revision: https://reviews.llvm.org/D113618

GitOrigin-RevId: e7969240dce5e064f11abd44d7553ba9e9f27210
4 files changed
tree: 677efbdec9586121447678b0fee5854b0b20aaf6
  1. cmake/
  2. docs/
  3. examples/
  4. include/
  5. lib/
  6. python/
  7. test/
  8. tools/
  9. unittests/
  10. utils/
  11. .clang-format
  12. .clang-tidy
  13. CMakeLists.txt
  14. LICENSE.TXT
  15. README.md
README.md

Multi-Level Intermediate Representation

See https://mlir.llvm.org/ for more information.