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
4bda6db0
Commit
4bda6db0
authored
Jun 09, 2022
by
wangshaojie6
Browse files
add NN splitk example
parent
3f192c3d
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
4 additions
and
2 deletions
+4
-2
example/01_gemm/gemm_xdl_fp16_splitk.cpp
example/01_gemm/gemm_xdl_fp16_splitk.cpp
+4
-2
No files found.
example/01_gemm/gemm_xdl_fp16_splitk.cpp
View file @
4bda6db0
...
...
@@ -34,7 +34,7 @@ using CDataType = ck::half_t;
using
AccDataType
=
float
;
using
ALayout
=
ck
::
tensor_layout
::
gemm
::
RowMajor
;
using
BLayout
=
ck
::
tensor_layout
::
gemm
::
Column
Major
;
using
BLayout
=
ck
::
tensor_layout
::
gemm
::
Row
Major
;
using
CLayout
=
ck
::
tensor_layout
::
gemm
::
RowMajor
;
using
AElementOp
=
ck
::
tensor_operation
::
element_wise
::
PassThrough
;
...
...
@@ -49,8 +49,10 @@ using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemmXdlSplitKCShu
//#########################| 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| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector|
//#########################| | | | | | | | Operation| Operation| Operation| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl| _NWaveNPerXdl|
//#########################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
<
F16
,
F16
,
F16
,
F32
,
Row
,
Row
,
Row
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
256
,
16
,
128
,
4
,
8
,
16
,
16
,
1
,
2
,
S
<
1
,
4
,
16
,
4
>
,
S
<
0
,
2
,
1
,
3
>
,
S
<
0
,
2
,
1
,
3
>
,
3
,
2
,
2
,
true
,
S
<
1
,
4
,
64
,
1
>
,
S
<
0
,
1
,
3
,
2
>
,
S
<
0
,
1
,
3
,
2
>
,
2
,
2
,
8
,
true
,
1
,
1
,
S
<
1
,
16
,
1
,
16
>
,
2
>
;
//< F16, F16, F16, F32, Row, Col, Row, PassThrough, PassThrough, PassThrough, GemmDefault, 64, 16, 16, 4, 8, 16, 16, 1, 1, S<1, 4, 16, 1>, S<0, 2, 1, 3>, S<0, 2, 1, 3>, 3, 8, 8, true, S<1, 4, 16, 1>, S<0, 1, 3, 2>, S<0, 1, 3, 2>, 3, 8, 8, true, 1, 1, S<1, 16, 1, 4>, 4>;
<
F16
,
F16
,
F16
,
F32
,
Row
,
Col
,
Row
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
256
,
16
,
128
,
4
,
8
,
16
,
16
,
1
,
2
,
S
<
1
,
4
,
16
,
4
>
,
S
<
0
,
2
,
1
,
3
>
,
S
<
0
,
2
,
1
,
3
>
,
3
,
2
,
2
,
true
,
S
<
1
,
4
,
64
,
1
>
,
S
<
0
,
1
,
3
,
2
>
,
S
<
0
,
1
,
3
,
2
>
,
3
,
8
,
8
,
true
,
1
,
1
,
S
<
1
,
16
,
1
,
16
>
,
2
>
;
//
< F16, F16, F16, F32, Row, Col, Row, PassThrough, PassThrough, PassThrough, GemmDefault, 256, 16, 128, 4, 8, 16, 16, 1, 2, S<1, 4, 16, 4>, S<0, 2, 1, 3>, S<0, 2, 1, 3>, 3, 2, 2, true, S<1, 4, 64, 1>, S<0, 1, 3, 2>, S<0, 1, 3, 2>, 3, 8, 8, true, 1, 1, S<1, 16, 1, 16>, 2>;
// clang-format on
...
...
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