Skip to content

GitLab

"auto_gptq/vscode:/vscode.git/clone" did not exist on "d76078ef0558a61791336266e30e23c183dc3f90"
Commit a1cd282e authored by Jing Zhang's avatar Jing Zhang
Browse files

clean

parent f6fdb74b
Show whitespace changes
Inline Side-by-side
Showing with 9 additions and 10 deletions
example/65_gemm_multiply_multiply/gemm_multiply_multiply_xdl_fp8.cpp
View file @ a1cd282e
...@@ -72,16 +72,15 @@ using CDEElementOp = MultiplyMultiply; ...@@ -72,16 +72,15 @@ using CDEElementOp = MultiplyMultiply;
static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNPadding; static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNPadding;
using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultiD_Xdl_CShuffle_V3 using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultiD_Xdl_CShuffle_V3
// clang-format off // clang-format off
< Row, Col, DsLayout, ELayout, ///######| ALayout| BLayout| DsLayout| ELayout| AData| BData| DsData| EData| AccData| CShuffle| A| B| CDE| GEMM| Block| MPer| NPer| KPer| AK1| BK1| MPer| NPer| MXdl| NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer|
A0DataType, B0DataType, DsDataType, EDataType, AccDataType, CShuffleDataType, ///######| | | | | Type| Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Spacialization| 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|
AElementOp, BElementOp, CDEElementOp, GemmSpec, ///######| | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
256, 256, 128, 64, ///######| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | S<C, D0, D1>|
16, 16, 32, 32, 4, 2, ///###### RRR
S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, ///< Row, Row, DsLayout, ELayout, A0DataType, B0DataType, DsDataType, EDataType, AccDataType, CShuffleDataType, AElementOp, BElementOp, CDEElementOp, GemmSpec, 256, 256, 128, 64, 16, 4, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 4, 0, 1, 1, S<1, 32, 1, 8>, S<8, 8, 1>, ck::BlockGemmPipelineScheduler::Interwave, ck::BlockGemmPipelineVersion::v1, FP8>;
S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, ///###### RCR
1, 1, S<1, 32, 1, 8>, S<8, 8, 1>, < Row, Col, DsLayout, ELayout, A0DataType, B0DataType, DsDataType, EDataType, AccDataType, CShuffleDataType, AElementOp, BElementOp, CDEElementOp, GemmSpec, 256, 256, 128, 64, 16, 16, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0, 1, 1, S<1, 32, 1, 8>, S<8, 8, 1>, ck::BlockGemmPipelineScheduler::Interwave, ck::BlockGemmPipelineVersion::v1, FP8>;
ck::BlockGemmPipelineScheduler::Interwave, ck::BlockGemmPipelineVersion::v1, FP8>;
// clang-format on // clang-format on
int main(int argc, char* argv[]) int main(int argc, char* argv[])
......
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