projects / platform / upstream / tvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 8a63b7f) | patch
[CUDA] Fix codegen for warp shuffle intrinsics (#5606)
authorShizhi Tang <rd0x01@gmail.com>
Mon, 18 May 2020 02:55:05 +0000 (10:55 +0800)
committerGitHub <noreply@github.com>
Mon, 18 May 2020 02:55:05 +0000 (19:55 -0700)
commitcb7bd986cadea53d6f41143a6ce747224e25aefb
tree931e4af7d47eb6fec924d6843e8299a342cd32aftree | snapshot
parent8a63b7f37c64d04236e915a30f8df7e0e61ffefacommit | diff
[CUDA] Fix codegen for warp shuffle intrinsics (#5606)

* fix shfl intrin

* improve test_lower_warp_memory_cuda_half_a_warp
src/target/source/intrin_rule_cuda.cc diff | blob | history
tests/python/unittest/test_tir_transform_lower_warp_memory.py diff | blob | history
Domain: Machine Learning / ML Framework;