Skip to content

GitLab

Commit b5b85620 authored by ltqin's avatar ltqin
Browse files

read for gridwise gemm

parent 71d974b5
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 1212 additions and 2 deletions
example/01_gemm/gemm_xdl_skip_lds_fp16.cpp
View file @ b5b85620
...@@ -11,7 +11,7 @@ ...@@ -11,7 +11,7 @@
#include "host_tensor.hpp" #include "host_tensor.hpp"
#include "host_tensor_generator.hpp" #include "host_tensor_generator.hpp"
#include "device_tensor.hpp" #include "device_tensor.hpp"
#include "device_gemm_xdl.hpp" #include "device_gemm_xdl_skip_lds.hpp"
#include "device_gemm_xdl_c_shuffle.hpp" #include "device_gemm_xdl_c_shuffle.hpp"
#include "device_gemm_xdl_cshuffle.hpp" #include "device_gemm_xdl_cshuffle.hpp"
#include "element_wise_operation.hpp" #include "element_wise_operation.hpp"
...@@ -45,7 +45,7 @@ using CElementOp = ck::tensor_operation::element_wise::PassThrough; ...@@ -45,7 +45,7 @@ using CElementOp = ck::tensor_operation::element_wise::PassThrough;
static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default; static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
// clang-format off // clang-format off
using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemmXdl using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemmXdlSkipLds
//###########| AData| BData| CData| AccData| ALayout| BLayout| CLayout| A| B| C| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MXdl| NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CThreadTransfer| CThreadTransfer| //###########| AData| BData| CData| AccData| ALayout| BLayout| CLayout| A| B| C| GEMM| Block| MPer| NPer| K0Per| K1| MPer| NPer| MXdl| NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CThreadTransfer| CThreadTransfer|
//###########| Type| Type| Type| Type| | | | 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| SrcDstVectorDim| DstScalar| //###########| Type| Type| Type| Type| | | | 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| SrcDstVectorDim| DstScalar|
//###########| | | | | | | | Operation| Operation| Operation| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | | PerVector| //###########| | | | | | | | Operation| Operation| Operation| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | | PerVector|
......
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