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
fc50b641
Commit
fc50b641
authored
Jul 12, 2023
by
ltqin
Browse files
changse toinstance
parent
0a753c83
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
17 additions
and
15 deletions
+17
-15
library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
...xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
+17
-15
No files found.
library/src/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add/device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
View file @
fc50b641
...
@@ -31,23 +31,25 @@ using CDE1ElementOp = ck::tensor_operation::element_wise::Add;
...
@@ -31,23 +31,25 @@ using CDE1ElementOp = ck::tensor_operation::element_wise::Add;
using
device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instances
=
using
device_batched_gemm_add_relu_gemm_add_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instances
=
std
::
tuple
<
std
::
tuple
<
// clang-format off
// clang-format off
//##################################################| A0Layout| B0Layout| D0Layout| B1Layout| D1sLayout| E1Layout| A0Data| B0Data| Acc0DataType| D0DataType| B1Data| Acc1CData| CShuffle| D1sData| E1Data| A0| B0| CDE0| B1| CDE1| PadGemm0M| PadGemm0N| PadGemm0K| PadGemm1N| PadGemm1K| NumGemm0K| Block| Gemm0| Gemm0| Gemm0| Gemm1| Gemm1| A0K1| B0K1|B1K1| MPer| NPer| Gemm0| Gemm0| Gemm1| A0BlockTransfer|A0BlockTransfer|A0BlockTransfer|A0BlockTransfer|A0BlockTransfer|A0BlockTransfer|A0BlockLds| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockLds| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockLds| C1Shuffle| C1Shuffle| CDE1BlockTransferClusterLengths| CDE1BlockTransfer|
//##################################################| A0Layout| B0Layout| D0Layout| B1Layout| D1sLayout| E1Layout| A0Data| B0Data| Acc0DataType| D0DataType| B1Data| Acc1CData| CShuffle| D1sData| E1Data| A0| B0| CDE0| B1| CDE1| PadGemm0M| PadGemm0N| PadGemm0K| PadGemm1N| PadGemm1K| NumGemm0K| Block| Gemm0| Gemm0| Gemm0| Gemm1| Gemm1| A0K1| B0K1|B1K1| MPer| NPer| Gemm0| Gemm0| Gemm1| A0BlockTransfer|A0BlockTransfer|A0BlockTransfer|A0BlockTransfer|A0BlockTransfer|A0BlockTransfer|A0BlockLds| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockTransfer| B0BlockLds| CDE0BlockTransfer| CDE0BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockTransfer| B1BlockLds| C1Shuffle| C1Shuffle| CDE1BlockTransferClusterLengths| CDE1BlockTransfer|
//##################################################| | | | | | | Type| Type| Type| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Elementwise| Elementwise| | | | | | Prefetch| Size| MPer| NPer| KPer| NPer| KPer| | | | XDL| XDL| MXdl| NXdl| NXdl| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//##################################################| | | | | | | Type| Type| Type| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Elementwise| Elementwise| | | | | | Prefetch| Size| MPer| NPer| KPer| NPer| KPer| | | | XDL| XDL| MXdl| NXdl| NXdl| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| SrcVectorDim| SrcScalar| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
//##################################################| | | | | | | | | | | | | | | | Operation| Operation| Operation| Operation| Operation| | | | | | Stage| | Block| Block| Block| Block| Block| | | | | | Per| Per| Per| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_AK1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//##################################################| | | | | | | | | | | | | | | | Operation| Operation| Operation| Operation| Operation| | | | | | Stage| | Block| Block| Block| Block| Block| | | | | | Per| Per| Per| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_AK1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | | PerVector| Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//##################################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | |
//##################################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | | | |
//generic
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
true
,
true
,
true
,
true
,
true
,
1
,
256
,
128
,
64
,
32
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
2
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
1
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
// no padding
// no padding
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
256
,
128
,
32
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
2
,
4
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
256
,
128
,
32
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
2
,
4
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
128
,
128
,
64
,
64
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
4
,
2
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
false
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
128
,
128
,
64
,
64
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
4
,
2
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
false
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
128
,
128
,
32
,
64
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
4
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
128
,
128
,
32
,
64
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
4
,
2
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
128
,
128
,
64
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
4
,
4
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
false
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
128
,
128
,
64
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
4
,
4
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
false
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
4
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
128
,
128
,
32
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
4
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
128
,
128
,
32
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
4
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
64
,
256
,
32
,
128
,
32
,
8
,
8
,
4
,
16
,
16
,
1
,
16
,
8
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
8
,
S
<
1
,
16
,
1
,
16
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
64
,
256
,
32
,
128
,
32
,
8
,
8
,
4
,
16
,
16
,
1
,
16
,
8
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
8
,
S
<
1
,
16
,
1
,
16
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
64
,
256
,
32
,
64
,
32
,
8
,
8
,
4
,
16
,
16
,
1
,
16
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
4
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
64
,
256
,
32
,
64
,
32
,
8
,
8
,
4
,
16
,
16
,
1
,
16
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
4
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
64
,
256
,
64
,
128
,
32
,
8
,
8
,
4
,
16
,
16
,
1
,
16
,
8
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
8
,
S
<
1
,
16
,
1
,
16
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
64
,
256
,
64
,
128
,
32
,
8
,
8
,
4
,
16
,
16
,
1
,
16
,
8
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
4
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
8
,
S
<
1
,
16
,
1
,
16
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
64
,
256
,
64
,
64
,
32
,
8
,
8
,
4
,
16
,
16
,
1
,
16
,
4
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
4
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
false
,
false
,
false
,
false
,
false
,
1
,
256
,
64
,
256
,
64
,
64
,
32
,
8
,
8
,
4
,
16
,
16
,
1
,
16
,
4
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
4
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
4
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
// Padded fallback kernel
// Padded fallback kernel
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
true
,
true
,
true
,
true
,
true
,
1
,
256
,
128
,
128
,
64
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
4
,
4
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
false
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
false
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
true
,
true
,
true
,
true
,
true
,
1
,
256
,
128
,
128
,
64
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
4
,
4
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
false
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
false
,
9
,
4
,
S
<
8
,
32
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
true
,
true
,
true
,
true
,
true
,
1
,
256
,
128
,
64
,
32
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
2
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
DeviceBatchedGemmMultipleDGemmMultipleD_Xdl_CShuffle
<
Row
,
Col
,
ck
::
Tuple
<
Row
>
,
Col
,
ck
::
Tuple
<
Row
>
,
Row
,
F16
,
F16
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
F32
,
F32
,
ck
::
Tuple
<
F16
>
,
F16
,
PassThrough
,
PassThrough
,
CDE0ElementOp
,
PassThrough
,
CDE1ElementOp
,
true
,
true
,
true
,
true
,
true
,
1
,
256
,
128
,
64
,
32
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
2
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
8
,
8
,
true
,
9
,
4
,
S
<
4
,
64
,
1
>
,
S
<
1
,
0
,
2
>
,
S
<
1
,
0
,
2
>
,
2
,
4
,
4
,
true
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
// clang-format on
// 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