projects / platform / upstream / tvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 45ee7b5) | patch
[CodeGen][CUDA] Enhance CUDA codegen for SelectNode (#4983)
authorWei Pan <60017475+wpan11nv@users.noreply.github.com>
Wed, 11 Mar 2020 02:16:59 +0000 (19:16 -0700)
committerGitHub <noreply@github.com>
Wed, 11 Mar 2020 02:16:59 +0000 (11:16 +0900)
commitafa84171e3c7edb49e16d454326d0da1aec2e38c
tree8ab98c8cbffb98549c0f9ad8db24c24c9dda2ff0tree | snapshot
parent45ee7b5fef67ef362538885802f68cbd034f1524commit | diff
[CodeGen][CUDA] Enhance CUDA codegen for SelectNode (#4983)

- This patch allows CUDA backend to emit correct code for
  selects with vector conditions, which may be produced
  by floordiv op lowering etc..

- This already works for llvm BE, as llvm select instruction
  supports vector conditions.

Signed-off-by: Wei Pan <weip@nvidia.com>
include/tvm/runtime/data_type.h diff | blob | history
src/target/source/codegen_cuda.cc diff | blob | history
src/target/source/codegen_cuda.h diff | blob | history
tests/python/unittest/test_codegen_cuda.py diff | blob | history
Domain: Machine Learning / ML Framework;