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
fa906b64
Commit
fa906b64
authored
Feb 08, 2023
by
Adam Osewski
Browse files
Adding more bigger tiles.
parent
afdfef74
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
17 additions
and
11 deletions
+17
-11
library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
...device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
+9
-6
library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
...device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
+8
-5
No files found.
library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
View file @
fa906b64
...
...
@@ -64,16 +64,19 @@ using device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_irregular_tile_instances = st
//###################| 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|
//###################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
64
,
16
,
16
,
32
,
8
,
8
,
16
,
16
,
1
,
1
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
1
,
8
,
1
,
S
<
4
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
1
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
4
>
,
1
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
16
,
64
,
32
,
8
,
8
,
16
,
16
,
1
,
1
,
S
<
4
,
16
,
4
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
1
,
2
,
1
,
S
<
4
,
64
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
1
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
4
>
,
1
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
128
,
256
,
32
,
8
,
8
,
32
,
32
,
2
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
1
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
128
,
128
,
32
,
8
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
1
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
128
,
64
,
32
,
8
,
2
,
32
,
32
,
2
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
128
,
64
,
32
,
8
,
8
,
32
,
32
,
2
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
1
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
64
,
128
,
32
,
8
,
2
,
32
,
32
,
1
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
8
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
64
,
128
,
32
,
8
,
8
,
32
,
32
,
1
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
2
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
128
,
128
,
32
,
8
,
8
,
32
,
32
,
4
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
2
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
4
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
128
,
64
,
32
,
8
,
2
,
32
,
32
,
2
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
8
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
4
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
128
,
64
,
32
,
8
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
2
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
4
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
64
,
128
,
32
,
8
,
2
,
32
,
32
,
2
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
0
,
1
,
1
,
S
<
1
,
16
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
64
,
128
,
32
,
8
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
128
,
64
,
32
,
8
,
2
,
32
,
32
,
2
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
128
,
64
,
32
,
8
,
8
,
32
,
32
,
2
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
1
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
64
,
128
,
32
,
8
,
2
,
32
,
32
,
1
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
8
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
0
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
64
,
128
,
32
,
8
,
8
,
32
,
32
,
1
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
2
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
32
,
128
,
32
,
8
,
8
,
32
,
32
,
1
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Row
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
32
,
256
,
32
,
8
,
8
,
32
,
32
,
1
,
4
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
8
>
,
8
>
// clang-format on
>
;
...
...
library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
View file @
fa906b64
...
...
@@ -61,15 +61,18 @@ using device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_irregular_tile_instances = st
//###################| 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|
//###################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
64
,
16
,
16
,
32
,
8
,
8
,
16
,
16
,
1
,
1
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
1
,
8
,
1
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
1
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
4
>
,
1
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
16
,
64
,
32
,
8
,
8
,
16
,
16
,
1
,
1
,
S
<
4
,
16
,
4
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
1
,
2
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
1
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
4
>
,
1
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
128
,
64
,
32
,
8
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
4
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
64
,
128
,
32
,
8
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
64
,
64
,
64
,
32
,
8
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
4
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
128
,
256
,
32
,
8
,
8
,
32
,
32
,
2
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
128
,
128
,
32
,
8
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
128
,
64
,
32
,
8
,
8
,
32
,
32
,
2
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
64
,
128
,
32
,
8
,
8
,
32
,
32
,
1
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
256
,
32
,
256
,
32
,
8
,
8
,
32
,
32
,
1
,
2
,
S
<
4
,
32
,
2
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
128
,
128
,
32
,
8
,
8
,
32
,
32
,
4
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
128
,
64
,
32
,
8
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
4
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
64
,
128
,
32
,
8
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
128
,
32
,
32
,
8
,
8
,
32
,
32
,
2
,
1
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
32
,
1
,
4
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
32
,
128
,
32
,
8
,
8
,
32
,
32
,
1
,
2
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
128
,
32
,
256
,
32
,
8
,
8
,
32
,
32
,
1
,
4
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
8
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
64
,
64
,
64
,
32
,
8
,
8
,
32
,
32
,
2
,
2
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
4
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
64
,
64
,
32
,
32
,
8
,
8
,
32
,
32
,
2
,
1
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
4
>
,
8
>
,
DeviceGroupedGemm_Xdl
<
Row
,
Col
,
Empty_Tuple
,
Row
,
F16
,
F16
,
F32
,
F16
,
Empty_Tuple
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmMNKPadding
,
1
,
64
,
32
,
64
,
32
,
8
,
8
,
32
,
32
,
1
,
2
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
S
<
4
,
16
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
1
,
1
,
1
,
S
<
1
,
16
,
1
,
4
>
,
8
>
// 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