Skip to content

GitLab

Commit 4b5d5792 authored by Adam Osewski's avatar Adam Osewski
Browse files

Remove duplicate instances

parent cfc2be07
Show whitespace changes
Inline Side-by-side
Showing with 0 additions and 5 deletions
library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_multiple_d/device_grouped_gemm_multiple_d_splitk_xdl_cshuffle_f16_f16_f16_mk_kn_mn_instance.hpp
View file @ 4b5d5792
......@@ -72,11 +72,6 @@ using device_ggemm_md_splitk_xdl_cshuffle_f16_f16_f16_mk_kn_mn_memory_instances
//#########################################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Spacialization| Prefetch| Size| Block| Block| Block| | | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector| | |
//#########################################| | | | | | | | | | | Operation| Operation| Operation| | Stage| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl| | |
//#########################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
// Latency friendly
DeviceGroupedGemmMultipleDSplitKXdlCShuffle< Row, Row, Empty_Tuple, Row, F16, F16, F32, F32, Empty_Tuple, F16, PassThrough, PassThrough, PassThrough, GemmSpec, NumPrefetch, 128, 32, 16, 64, 8, 4, 16, 16, 1, 1, S<8, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<16, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 4, 1, 1, 1, S<1, 16, 1, 8>, 2, Pipeline, Scheduler>,
DeviceGroupedGemmMultipleDSplitKXdlCShuffle< Row, Row, Empty_Tuple, Row, F16, F16, F32, F32, Empty_Tuple, F16, PassThrough, PassThrough, PassThrough, GemmSpec, NumPrefetch, 64, 16, 16, 128, 8, 4, 16, 16, 1, 1, S<16, 4, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<16, 4, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 4, 1, 1, 1, S<1, 16, 1, 4>, 4, Pipeline, Scheduler>,
DeviceGroupedGemmMultipleDSplitKXdlCShuffle< Row, Row, Empty_Tuple, Row, F16, F16, F32, F32, Empty_Tuple, F16, PassThrough, PassThrough, PassThrough, GemmSpec, NumPrefetch, 64, 16, 16, 64, 8, 4, 16, 16, 1, 1, S<8, 8, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<16, 4, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 4, 1, 1, 1, S<1, 16, 1, 4>, 4, Pipeline, Scheduler>,
DeviceGroupedGemmMultipleDSplitKXdlCShuffle< Row, Row, Empty_Tuple, Row, F16, F16, F32, F32, Empty_Tuple, F16, PassThrough, PassThrough, PassThrough, GemmSpec, NumPrefetch, 128, 16, 32, 64, 8, 4, 16, 16, 1, 1, S<8, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<16, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 4, 1, 1, 1, S<1, 16, 1, 8>, 4, Pipeline, Scheduler>,
// Memory friendly
DeviceGroupedGemmMultipleDSplitKXdlCShuffle< Row, Row, Empty_Tuple, Row, F16, F16, F32, F32, Empty_Tuple, F16, PassThrough, PassThrough, PassThrough, GemmSpec, NumPrefetch, 256, 256, 32, 64, 8, 2, 32, 32, 2, 1, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<32, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 1, 1, 1, S<1, 32, 1, 8>, 4, Pipeline, Scheduler>,
DeviceGroupedGemmMultipleDSplitKXdlCShuffle< Row, Row, Empty_Tuple, Row, F16, F16, F32, F32, Empty_Tuple, F16, PassThrough, PassThrough, PassThrough, GemmSpec, NumPrefetch, 256, 256, 16, 64, 8, 2, 16, 16, 4, 1, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<32, 8, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 2, 1, 1, 1, S<1, 32, 1, 8>, 2, Pipeline, Scheduler>,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment