gemm1 v3 perf optimization WIP. better than buf2vgpr now

This commit is contained in:
OscarXu
2025-06-27 03:28:31 -05:00
parent dbf5378a08
commit e809d445da
2 changed files with 17 additions and 14 deletions

View File

@@ -180,7 +180,7 @@ static constexpr ck::index_t MPerBlock = 64; using DeviceOpInstance = ck::tensor
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 1,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0,
4, 2, S<1, 32, 1, 8>, S<2, 1, 1, 1>,
ck::BlockGemmPipelineScheduler::Intrawave, ck::BlockGemmPipelineVersion::v1, ActOP, Nswizzle, true, MulRoutedWeight, int32_t, A0DataType>;
ck::BlockGemmPipelineScheduler::Intrawave, ck::BlockGemmPipelineVersion::v3, ActOP, Nswizzle, true, MulRoutedWeight, int32_t, A0DataType>;
#endif
// clang-format on