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
26 additions
and
21 deletions
+26
-21
example/39_permute/permute_1xHxW_fp16.cpp
example/39_permute/permute_1xHxW_fp16.cpp
+1
-1
example/39_permute/permute_HxWx4_fp16.cpp
example/39_permute/permute_HxWx4_fp16.cpp
+1
-1
example/39_permute/permute_NxHxW_fp16.cpp
example/39_permute/permute_NxHxW_fp16.cpp
+1
-1
example/39_permute/run_permute_bundle_example.inc
example/39_permute/run_permute_bundle_example.inc
+1
-1
example/39_permute/run_permute_element_example.inc
example/39_permute/run_permute_element_example.inc
+1
-1
example/40_conv2d_fwd_quantization/CMakeLists.txt
example/40_conv2d_fwd_quantization/CMakeLists.txt
+7
-2
example/40_conv2d_fwd_quantization/common.hpp
example/40_conv2d_fwd_quantization/common.hpp
+1
-1
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perchannel_quantization_int8.cpp
.../conv2d_fwd_dl_bias_relu_perchannel_quantization_int8.cpp
+1
-1
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perlayer_quantization_int8.cpp
...on/conv2d_fwd_dl_bias_relu_perlayer_quantization_int8.cpp
+1
-1
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perchannel_quantization_int8.cpp
.../conv2d_fwd_dl_bias_tanh_perchannel_quantization_int8.cpp
+1
-1
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perlayer_quantization_int8.cpp
...on/conv2d_fwd_dl_bias_tanh_perlayer_quantization_int8.cpp
+1
-1
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perchannel_quantization_int8.cpp
...antization/conv2d_fwd_dl_perchannel_quantization_int8.cpp
+1
-1
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perlayer_quantization_int8.cpp
...quantization/conv2d_fwd_dl_perlayer_quantization_int8.cpp
+1
-1
example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp
...conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp
+1
-1
example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
...n/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
+1
-1
example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perchannel_quantization_int8.cpp
...ntization/conv2d_fwd_xdl_perchannel_quantization_int8.cpp
+1
-1
example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perlayer_quantization_int8.cpp
...uantization/conv2d_fwd_xdl_perlayer_quantization_int8.cpp
+1
-1
example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perchannel_quantization_example.inc
...n/run_conv2d_fwd_bias_perchannel_quantization_example.inc
+1
-1
example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perlayer_quantization_example.inc
...ion/run_conv2d_fwd_bias_perlayer_quantization_example.inc
+1
-1
example/40_conv2d_fwd_quantization/run_conv2d_fwd_perchannel_quantization_example.inc
...zation/run_conv2d_fwd_perchannel_quantization_example.inc
+1
-1
No files found.
Too many changes to show.
To preserve performance only
1000 of 1000+
files are displayed.
Plain diff
Email patch
example/39_permute/permute_1xHxW_fp16.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
...
...
example/39_permute/permute_HxWx4_fp16.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
...
...
example/39_permute/permute_NxHxW_fp16.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
...
...
example/39_permute/run_permute_bundle_example.inc
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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
#pragma once
...
...
example/39_permute/run_permute_element_example.inc
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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
#pragma once
...
...
example/40_conv2d_fwd_quantization/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_conv2d_fwd_xdl_perlayer_quantization_int8 conv2d_fwd_xdl_perlayer_quantization_int8.cpp
)
add_example_executable
(
example_conv2d_fwd_xdl_perlayer_quantization_int8 conv2d_fwd_xdl_perlayer_quantization_int8.cpp
)
add_example_executable
(
example_conv2d_fwd_xdl_perchannel_quantization_int8 conv2d_fwd_xdl_perchannel_quantization_int8.cpp
)
add_example_executable
(
example_conv2d_fwd_xdl_perchannel_quantization_int8 conv2d_fwd_xdl_perchannel_quantization_int8.cpp
)
add_example_executable
(
example_conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8 conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
)
add_example_executable
(
example_conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8 conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
)
add_example_executable
(
example_conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8 conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp
)
add_example_executable
(
example_conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8 conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp
)
endif
()
set
(
target 1
)
endif
()
endforeach
()
# Conv perlayer quantization
# Conv perlayer quantization
add_example_executable
(
example_conv2d_fwd_dl_perlayer_quantization_int8 conv2d_fwd_dl_perlayer_quantization_int8.cpp
)
add_example_executable
(
example_conv2d_fwd_dl_perlayer_quantization_int8 conv2d_fwd_dl_perlayer_quantization_int8.cpp
)
...
...
example/40_conv2d_fwd_quantization/common.hpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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
#pragma once
...
...
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perchannel_quantization_int8.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
...
...
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_relu_perlayer_quantization_int8.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
...
...
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perchannel_quantization_int8.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
...
...
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_bias_tanh_perlayer_quantization_int8.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
...
...
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perchannel_quantization_int8.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
...
...
example/40_conv2d_fwd_quantization/conv2d_fwd_dl_perlayer_quantization_int8.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp"
...
...
example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp"
...
...
example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp"
...
...
example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perchannel_quantization_int8.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp"
...
...
example/40_conv2d_fwd_quantization/conv2d_fwd_xdl_perlayer_quantization_int8.cpp
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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 "common.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_xdl_cshuffle.hpp"
...
...
example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perchannel_quantization_example.inc
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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
#pragma once
template
<
ck
::
index_t
NDimSpatial
,
template
<
ck
::
index_t
NDimSpatial
,
...
...
example/40_conv2d_fwd_quantization/run_conv2d_fwd_bias_perlayer_quantization_example.inc
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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
#pragma once
...
...
example/40_conv2d_fwd_quantization/run_conv2d_fwd_perchannel_quantization_example.inc
View file @
a7342032
// SPDX-License-Identifier: MIT
// 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
#pragma once
...
...
Prev
1
…
8
9
10
11
12
13
14
15
16
…
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