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
9efb5cc4
Unverified
Commit
9efb5cc4
authored
Jun 05, 2023
by
Rostyslav Geyyer
Committed by
GitHub
Jun 05, 2023
Browse files
Merge branch 'develop' into lwpck-759
parents
af52fe33
40365904
Changes
1000
Show whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
26 additions
and
24 deletions
+26
-24
include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
...u/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
+7
-5
include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.hpp
...ion/gpu/device/impl/device_multiple_reduce_multiblock.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.hpp
...ion/gpu/device/impl/device_multiple_reduce_threadwise.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp
...r_operation/gpu/device/impl/device_normalization_impl.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp
...tion/gpu/device/impl/device_normalization_splitk_impl.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_permute_impl.hpp
.../tensor_operation/gpu/device/impl/device_permute_impl.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp
...operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
...eration/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp
...tensor_operation/gpu/device/impl/device_reduce_common.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp
...or_operation/gpu/device/impl/device_reduce_multiblock.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp
...or_operation/gpu/device/impl/device_reduce_threadwise.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
.../tensor_operation/gpu/device/impl/device_softmax_impl.hpp
+1
-1
include/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.hpp
...evice/impl/device_sparse_embeddings_forward_layernorm.hpp
+1
-1
include/ck/tensor_operation/gpu/device/masking_specialization.hpp
...ck/tensor_operation/gpu/device/masking_specialization.hpp
+1
-1
include/ck/tensor_operation/gpu/device/matrix_padder.hpp
include/ck/tensor_operation/gpu/device/matrix_padder.hpp
+1
-1
include/ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp
...ensor_operation/gpu/device/reduction_operator_mapping.hpp
+1
-1
include/ck/tensor_operation/gpu/device/tensor_layout.hpp
include/ck/tensor_operation/gpu/device/tensor_layout.hpp
+1
-1
include/ck/tensor_operation/gpu/device/tensor_specialization.hpp
.../ck/tensor_operation/gpu/device/tensor_specialization.hpp
+1
-1
include/ck/tensor_operation/gpu/device/welford_helper.hpp
include/ck/tensor_operation/gpu/device/welford_helper.hpp
+1
-1
include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
...r_operation/gpu/element/binary_element_wise_operation.hpp
+1
-1
No files found.
Too many changes to show.
To preserve performance only
1000 of 1000+
files are displayed.
Plain diff
Email patch
include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
View file @
9efb5cc4
// 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
...
...
@@ -406,10 +406,12 @@ struct DeviceGroupedGemmXdlSplitKCShuffle : public DeviceGroupedGemmSplitK<ALayo
}
}
hip_check_error
(
hipMemcpy
(
arg
.
p_workspace_
,
hip_check_error
(
hipMemcpyWithStream
(
arg
.
p_workspace_
,
arg
.
gemm_kernel_args_
.
data
(),
arg
.
gemm_kernel_args_
.
size
()
*
sizeof
(
GemmTransKernelArg
),
hipMemcpyHostToDevice
));
hipMemcpyHostToDevice
,
stream_config
.
stream_id_
));
float
ave_time
=
0
;
...
...
include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_permute_impl.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/masking_specialization.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/matrix_padder.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/tensor_layout.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/tensor_specialization.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/device/welford_helper.hpp
View file @
9efb5cc4
// 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
...
...
include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
View file @
9efb5cc4
// 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
...
...
Prev
1
…
15
16
17
18
19
20
21
22
23
…
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