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_ROCM
Commits
0a763c3e
Commit
0a763c3e
authored
Jun 06, 2023
by
Alan Turner
Browse files
Merge remote-tracking branch 'origin/develop' into migx-jit-lib
parents
cb9ccccd
40365904
Changes
1000
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
20 additions
and
20 deletions
+20
-20
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
+1
-1
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
+1
-1
library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp
...xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp
...xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp
...xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp
...xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/device_batched_gemm_softmax_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
+1
-1
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
...cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
...xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
...cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
...xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_bf16_instance.cpp
...gpu/batchnorm/device_batchnorm_backward_bf16_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f16_instance.cpp
.../gpu/batchnorm/device_batchnorm_backward_f16_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f32_instance.cpp
.../gpu/batchnorm/device_batchnorm_backward_f32_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f64_instance.cpp
.../gpu/batchnorm/device_batchnorm_backward_f64_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_bf16_instance.cpp
.../gpu/batchnorm/device_batchnorm_forward_bf16_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f16_instance.cpp
...e/gpu/batchnorm/device_batchnorm_forward_f16_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f32_instance.cpp
...e/gpu/batchnorm/device_batchnorm_forward_f32_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f64_instance.cpp
...e/gpu/batchnorm/device_batchnorm_forward_f64_instance.cpp
+1
-1
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp
...ce/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp
+1
-1
No files found.
Too many changes to show.
To preserve performance only
1000 of 1000+
files are displayed.
Plain diff
Email patch
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 @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
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 @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/device_batched_gemm_softmax_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_bias_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_bf16_bf16_bf16_bf16_gmk_gnk_gno_gmo_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include <cstdlib>
...
...
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_bf16_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
...
...
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f16_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
...
...
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f32_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
...
...
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_backward_f64_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
...
...
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_bf16_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
...
...
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f16_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
...
...
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f32_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
...
...
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_forward_f64_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
...
...
library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp
View file @
0a763c3e
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-202
2
, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-202
3
, Advanced Micro Devices, Inc. All rights reserved.
#include "ck/ck.hpp"
#include "ck/utility/tuple.hpp"
...
...
Prev
1
…
32
33
34
35
36
37
38
39
40
…
50
Next
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