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
a7342032
Unverified
Commit
a7342032
authored
Jun 16, 2023
by
Rostyslav Geyyer
Committed by
GitHub
Jun 16, 2023
Browse files
Merge branch 'develop' into lwpck-726
parents
2ee1c0a7
027e46ee
Changes
1000
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
41 additions
and
25 deletions
+41
-25
example/40_conv2d_fwd_quantization/run_conv2d_fwd_perlayer_quantization_example.inc
...tization/run_conv2d_fwd_perlayer_quantization_example.inc
+1
-1
example/41_grouped_conv_conv_fwd/CMakeLists.txt
example/41_grouped_conv_conv_fwd/CMakeLists.txt
+16
-5
example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp
..._grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp
+1
-1
example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp
..._grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp
+1
-1
example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp
..._grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp
+1
-1
example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp
..._grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp
+1
-1
example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp
..._grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp
+1
-1
example/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc
...ouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc
+1
-1
example/42_groupnorm/common.hpp
example/42_groupnorm/common.hpp
+1
-1
example/42_groupnorm/groupnorm_sigmoid_mul_fp16.cpp
example/42_groupnorm/groupnorm_sigmoid_mul_fp16.cpp
+1
-1
example/42_groupnorm/groupnorm_splitk_fp16.cpp
example/42_groupnorm/groupnorm_splitk_fp16.cpp
+1
-1
example/42_groupnorm/groupnorm_swish_fp16.cpp
example/42_groupnorm/groupnorm_swish_fp16.cpp
+1
-1
example/42_groupnorm/run_groupnorm_example.inc
example/42_groupnorm/run_groupnorm_example.inc
+1
-1
example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp16.cpp
...mm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp16.cpp
+1
-1
example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp32.cpp
...mm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp32.cpp
+1
-1
example/45_elementwise_normalization/elementwise_layernorm_blockwise.cpp
...entwise_normalization/elementwise_layernorm_blockwise.cpp
+1
-1
example/46_gemm_add_multiply/common.hpp
example/46_gemm_add_multiply/common.hpp
+1
-1
example/46_gemm_add_multiply/gemm_add_multiply_dl_fp16.cpp
example/46_gemm_add_multiply/gemm_add_multiply_dl_fp16.cpp
+1
-1
example/46_gemm_add_multiply/gemm_add_multiply_xdl_fp16.cpp
example/46_gemm_add_multiply/gemm_add_multiply_xdl_fp16.cpp
+1
-1
example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
+7
-2
No files found.
Too many changes to show.
To preserve performance only
1000 of 1000+
files are displayed.
Plain diff
Email patch
example/40_conv2d_fwd_quantization/run_conv2d_fwd_perlayer_quantization_example.inc
View file @
a7342032
// 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.
#pragma once
...
...
example/41_grouped_conv_conv_fwd/CMakeLists.txt
View file @
a7342032
if
(
GPU_TARGETS MATCHES
"gfx908"
OR GPU_TARGETS MATCHES
"gfx90a"
OR GPU_TARGETS MATCHES
"gfx940"
)
list
(
APPEND gpu_list1 gfx908 gfx90a gfx940 gfx941 gfx942
)
list
(
APPEND gpu_list2 gfx908 gfx90a
)
set
(
target 0
)
foreach
(
gpu IN LISTS GPU_TARGETS
)
if
(
gpu IN_LIST gpu_list1 AND target EQUAL 0
)
add_example_executable
(
example_grouped_conv_conv_fwd_xdl_fp32 grouped_conv_conv_fwd_xdl_fp32.cpp
)
add_example_executable
(
example_grouped_conv_conv_fwd_xdl_fp16 grouped_conv_conv_fwd_xdl_fp16.cpp
)
add_example_executable
(
example_grouped_conv_conv_fwd_xdl_bf16 grouped_conv_conv_fwd_xdl_bf16.cpp
)
if
(
NOT GPU_TARGETS MATCHES
"gfx940"
)
add_example_executable
(
example_grouped_conv_conv_fwd_xdl_int8 grouped_conv_conv_fwd_xdl_int8.cpp
)
endif
()
if
(
USE_BITINT_EXTENSION_INT4
)
add_example_executable
(
example_grouped_conv_conv_fwd_xdl_int4 grouped_conv_conv_fwd_xdl_int4.cpp
)
endif
(
USE_BITINT_EXTENSION_INT4
)
endif
()
set
(
target 1
)
endif
()
endforeach
()
set
(
target 0
)
foreach
(
gpu IN LISTS GPU_TARGETS
)
if
(
gpu IN_LIST gpu_list2 AND target EQUAL 0
)
add_example_executable
(
example_grouped_conv_conv_fwd_xdl_int8 grouped_conv_conv_fwd_xdl_int8.cpp
)
set
(
target 1
)
endif
()
endforeach
()
example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_bf16.cpp
View file @
a7342032
// 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>
#include <iostream>
...
...
example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp16.cpp
View file @
a7342032
// 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>
#include <iostream>
...
...
example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_fp32.cpp
View file @
a7342032
// 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>
#include <iostream>
...
...
example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int4.cpp
View file @
a7342032
// 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.
#ifndef CK_EXPERIMENTAL_BIT_INT_EXTENSION_INT4
#error Should compile this file with ck::int4_t support
...
...
example/41_grouped_conv_conv_fwd/grouped_conv_conv_fwd_xdl_int8.cpp
View file @
a7342032
// 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>
#include <iostream>
...
...
example/41_grouped_conv_conv_fwd/run_grouped_conv_conv_fwd_example.inc
View file @
a7342032
// 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.
#pragma once
...
...
example/42_groupnorm/common.hpp
View file @
a7342032
// 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.
#pragma once
...
...
example/42_groupnorm/groupnorm_sigmoid_mul_fp16.cpp
View file @
a7342032
// 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 "common.hpp"
...
...
example/42_groupnorm/groupnorm_splitk_fp16.cpp
View file @
a7342032
// 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 "common.hpp"
...
...
example/42_groupnorm/groupnorm_swish_fp16.cpp
View file @
a7342032
// 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 "common.hpp"
...
...
example/42_groupnorm/run_groupnorm_example.inc
View file @
a7342032
// 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.
#pragma once
...
...
example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp16.cpp
View file @
a7342032
// 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 <iostream>
#include <numeric>
...
...
example/43_splitk_gemm_bias_e_permute/splitk_gemm_bias_e_permute_xdl_fp32.cpp
View file @
a7342032
// 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 <iostream>
#include <numeric>
...
...
example/45_elementwise_normalization/elementwise_layernorm_blockwise.cpp
View file @
a7342032
// 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 <iostream>
#include <numeric>
...
...
example/46_gemm_add_multiply/common.hpp
View file @
a7342032
// 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.
#pragma once
...
...
example/46_gemm_add_multiply/gemm_add_multiply_dl_fp16.cpp
View file @
a7342032
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_dl.hpp"
...
...
example/46_gemm_add_multiply/gemm_add_multiply_xdl_fp16.cpp
View file @
a7342032
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp"
...
...
example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
View file @
a7342032
if
(
GPU_TARGETS MATCHES
"gfx908"
OR GPU_TARGETS MATCHES
"gfx90a"
OR GPU_TARGETS MATCHES
"gfx940"
)
list
(
APPEND gpu_list gfx908 gfx90a gfx940 gfx941 gfx942
)
set
(
target 0
)
foreach
(
gpu IN LISTS GPU_TARGETS
)
if
(
gpu IN_LIST gpu_list AND target EQUAL 0
)
add_example_executable
(
example_gemm_bias_softmax_gemm_permute gemm_bias_softmax_gemm_permute.cpp
)
endif
()
set
(
target 1
)
endif
()
endforeach
()
Prev
1
…
9
10
11
12
13
14
15
16
17
…
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