Skip to content
GitLab
Menu
Projects
Groups
Snippets
Help
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
liyinrong
composable_kernel
Commits
7f036e57
Commit
7f036e57
authored
2 years ago
by
shaojiewang
Browse files
Options
Download
Email Patches
Plain Diff
comment out 2 instance which trigger clang13 compiler error
parent
12e7df12
att_lower_triangle
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
library/src/tensor_operation_instance/gpu/batched_gemm_masking_scale_softmax_gemm_permute/device_batched_gemm_masking_scale_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
+3
-1
...xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
with
3 additions
and
1 deletion
+3
-1
library/src/tensor_operation_instance/gpu/batched_gemm_masking_scale_softmax_gemm_permute/device_batched_gemm_masking_scale_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
View file @
7f036e57
...
...
@@ -44,9 +44,11 @@ using device_batched_gemm_masking_scale_softmax_gemm_permute_xdl_cshuffle_f16_f1
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
<
Row
,
Col
,
Row
,
CPermuteNumDims_G_M_O
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
Scale
,
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
,
true
>
,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
<
Row
,
Col
,
Row
,
CPermuteNumDims_G_M_O
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
Scale
,
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
,
true
>
,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
<
Row
,
Col
,
Row
,
CPermuteNumDims_G_M_O
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
Scale
,
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
,
true
>
,
#if !CK_WORKAROUND_SWDEV_XXXXXX_ATTN_KERNEL_CLANG_CANNOT_SCAVENGE_REGISTER // these 2 instances triger CI's compiler error
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
<
Row
,
Col
,
Row
,
CPermuteNumDims_G_M_O
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
Scale
,
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
,
true
>
,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
<
Row
,
Col
,
Row
,
CPermuteNumDims_G_M_O
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
Scale
,
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
,
true
>
,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
<
Row
,
Col
,
Row
,
CPermuteNumDims_G_M_O
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
Scale
,
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
,
true
>
,
#endif
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
<
Row
,
Col
,
Row
,
CPermuteNumDims_G_M_O
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
Scale
,
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
,
true
>
,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
<
Row
,
Col
,
Row
,
CPermuteNumDims_G_M_O
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
Scale
,
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
,
true
>
,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
<
Row
,
Col
,
Row
,
CPermuteNumDims_G_M_O
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
Scale
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
128
,
128
,
32
,
128
,
32
,
8
,
8
,
2
,
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
<
8
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
2
,
S
<
1
,
32
,
1
,
8
>
,
8
,
true
>
,
DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
<
Row
,
Col
,
Row
,
CPermuteNumDims_G_M_O
,
F16
,
F16
,
F16
,
F16
,
F32
,
F16
,
PassThrough
,
PassThrough
,
Scale
,
PassThrough
,
PassThrough
,
GemmDefault
,
1
,
256
,
64
,
256
,
32
,
128
,
32
,
8
,
8
,
2
,
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
<
8
,
32
,
1
>
,
S
<
0
,
2
,
1
>
,
S
<
0
,
2
,
1
>
,
1
,
4
,
2
,
false
,
1
,
8
,
S
<
1
,
16
,
1
,
16
>
,
8
,
true
>
,
...
...
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
Menu
Projects
Groups
Snippets
Help