Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
composable_kernel
Commits
b5b85620
Commit
b5b85620
authored
May 07, 2022
by
ltqin
Browse files
read for gridwise gemm
parent
71d974b5
Changes
3
Expand all
Show whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
1212 additions
and
2 deletions
+1212
-2
example/01_gemm/gemm_xdl_skip_lds_fp16.cpp
example/01_gemm/gemm_xdl_skip_lds_fp16.cpp
+2
-2
include/ck/tensor_operation/gpu/device/device_gemm_xdl_skip_lds.hpp
.../tensor_operation/gpu/device/device_gemm_xdl_skip_lds.hpp
+515
-0
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_skip_lds_v2r3.hpp
...operation/gpu/grid/gridwise_gemm_xdlops_skip_lds_v2r3.hpp
+695
-0
No files found.
example/01_gemm/gemm_xdl_skip_lds_fp16.cpp
View file @
b5b85620
...
...
@@ -11,7 +11,7 @@
#include "host_tensor.hpp"
#include "host_tensor_generator.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_cshuffle.hpp"
#include "element_wise_operation.hpp"
...
...
@@ -45,7 +45,7 @@ using CElementOp = ck::tensor_operation::element_wise::PassThrough;
static
constexpr
auto
GemmDefault
=
ck
::
tensor_operation
::
device
::
GemmSpecialization
::
Default
;
// clang-format off
using
DeviceGemmInstance
=
ck
::
tensor_operation
::
device
::
DeviceGemmXdl
using
DeviceGemmInstance
=
ck
::
tensor_operation
::
device
::
DeviceGemmXdl
SkipLds
//###########| 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|
//###########| | | | | | | | Operation| Operation| Operation| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | | PerVector|
...
...
include/ck/tensor_operation/gpu/device/device_gemm_xdl_skip_lds.hpp
0 → 100644
View file @
b5b85620
This diff is collapsed.
Click to expand it.
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_skip_lds_v2r3.hpp
0 → 100644
View file @
b5b85620
This diff is collapsed.
Click to expand it.
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment