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
a2c75713
Commit
a2c75713
authored
Sep 20, 2022
by
Anthony Chang
Browse files
re-enable instances previously failed on 9110
parent
93c6e771
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
7 additions
and
7 deletions
+7
-7
library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
...xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
+4
-4
library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
...xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
+3
-3
No files found.
library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
View file @
a2c75713
...
@@ -36,10 +36,10 @@ using device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_inst
...
@@ -36,10 +36,10 @@ using device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_inst
//################################| | | | | | | | | | | Operation| Operation| Operation| Operation| Operation| | Stage| | Block| Block| Block| Block| Block| | | | | | Per| Per| Per| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | 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_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | |
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | |
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | |
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | |
//
DeviceBatchedGemmGemm_Xdl_CShuffle< Row, Col, Row, Row, F16, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, PassThrough, PassThrough, GemmDefault, 1, 256, 256, 128, 32, 64, 32, 8, 8, 2, 32, 32, 2, 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<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8>,
// failed validation on MI100
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Row
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
256
,
128
,
32
,
64
,
32
,
8
,
8
,
2
,
32
,
32
,
2
,
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
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
//
DeviceBatchedGemmGemm_Xdl_CShuffle< Row, Col, Row, Row, F16, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, PassThrough, PassThrough, GemmDefault, 1, 256, 256, 128, 32, 128, 32, 8, 8, 2, 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< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8>,
// failed validation on MI100
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Row
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
256
,
128
,
32
,
128
,
32
,
8
,
8
,
2
,
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
<
8
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
//
DeviceBatchedGemmGemm_Xdl_CShuffle< Row, Col, Row, Row, F16, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, PassThrough, PassThrough, GemmDefault, 1, 256, 128, 256, 32, 64, 32, 8, 8, 2, 32, 32, 1, 8, 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<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8>,
// failed validation on MI100
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Row
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
256
,
32
,
64
,
32
,
8
,
8
,
2
,
32
,
32
,
1
,
8
,
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
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
//
DeviceBatchedGemmGemm_Xdl_CShuffle< Row, Col, Row, Row, F16, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, PassThrough, PassThrough, GemmDefault, 1, 256, 128, 256, 32, 128, 32, 8, 8, 2, 32, 32, 1, 8, 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< 8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, false, 1, 2, S<1, 32, 1, 8>, 8>,
// failed validation on MI100
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Row
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
256
,
32
,
128
,
32
,
8
,
8
,
2
,
32
,
32
,
1
,
8
,
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
<
8
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Row
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
128
,
64
,
64
,
32
,
8
,
8
,
2
,
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
,
false
,
S
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Row
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
128
,
64
,
64
,
32
,
8
,
8
,
2
,
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
,
false
,
S
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Row
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
128
,
32
,
64
,
32
,
8
,
8
,
2
,
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
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Row
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
128
,
32
,
64
,
32
,
8
,
8
,
2
,
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
<
16
,
16
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Row
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
128
,
64
,
128
,
32
,
8
,
8
,
2
,
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
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Row
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
128
,
64
,
128
,
32
,
8
,
8
,
2
,
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
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
>
,
...
...
library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
View file @
a2c75713
...
@@ -36,10 +36,10 @@ using device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_inst
...
@@ -36,10 +36,10 @@ using device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_inst
//################################| | | | | | | | | | | Operation| Operation| Operation| Operation| Operation| | Stage| | Block| Block| Block| Block| Block| | | | | | Per| Per| Per| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | 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_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | |
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | |
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | |
//################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | Wave| Wave| Wave| | | | | | | | | | | | | | | | | | | | | | | | | |
//
DeviceBatchedGemmGemm_Xdl_CShuffle< Row, Col, Col, Row, F16, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, PassThrough, PassThrough, GemmDefault, 1, 256, 256, 128, 32, 64, 32, 8, 8, 4, 32, 32, 2, 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>,
// TODO: to enable; can trigger compiler crash in mainline #9110 but not in #10738
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
256
,
128
,
32
,
64
,
32
,
8
,
8
,
4
,
32
,
32
,
2
,
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
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
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
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
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
>
,
//
DeviceBatchedGemmGemm_Xdl_CShuffle< Row, Col, Col, Row, F16, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, PassThrough, PassThrough, GemmDefault, 1, 256, 128, 256, 32, 64, 32, 8, 8, 4, 32, 32, 1, 8, 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>,
// TODO: to enable; can cause validation error on MI100
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
256
,
32
,
64
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
8
,
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
>
,
//
DeviceBatchedGemmGemm_Xdl_CShuffle< Row, Col, Col, Row, F16, F16, F16, F16, F32, F16, PassThrough, PassThrough, PassThrough, PassThrough, PassThrough, GemmDefault, 1, 256, 128, 256, 32, 128, 32, 8, 8, 4, 32, 32, 1, 8, 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>,
// TODO: to enable; can cause validation error on MI100
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
256
,
32
,
128
,
32
,
8
,
8
,
4
,
32
,
32
,
1
,
8
,
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
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
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
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
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
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
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
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
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
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
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
>
,
DeviceBatchedGemmGemm_Xdl_CShuffle
<
Row
,
Col
,
Col
,
Row
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
PassThrough
,
GemmDefault
,
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
>
,
...
...
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