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
795bea35
Commit
795bea35
authored
Sep 26, 2023
by
Umang Yadav
Browse files
remove unnecessary changes
parent
8216854a
Changes
214
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
9 additions
and
104 deletions
+9
-104
include/ck/host_utility/kernel_launch.hpp
include/ck/host_utility/kernel_launch.hpp
+1
-1
include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
.../ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
+0
-5
include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
.../tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
+0
-5
include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
...ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
+0
-5
include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
...ude/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
+0
-5
include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
...e/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
+0
-5
include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
..._operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
+0
-5
include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
+0
-5
include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
...ration/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
+0
-5
include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
+0
-5
include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
...sor_operation/gpu/block/reduction_functions_blockwise.hpp
+0
-5
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
...ion/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
+0
-5
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
...ion/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
+0
-5
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
...ion/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
+0
-5
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
...ion/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
+0
-5
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
...ation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
+0
-5
include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
...n/gpu/device/convolution_backward_data_specialization.hpp
+0
-5
include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
...gpu/device/convolution_backward_weight_specialization.hpp
+0
-5
include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
...eration/gpu/device/convolution_forward_specialization.hpp
+0
-5
include/ck/tensor_operation/gpu/device/device_base.hpp
include/ck/tensor_operation/gpu/device/device_base.hpp
+8
-13
No files found.
include/ck/host_utility/kernel_launch.hpp
View file @
795bea35
...
...
@@ -142,4 +142,4 @@ float launch_and_time_kernel_with_preprocess(const StreamConfig& stream_config,
return
0
;
#endif
}
#endif
\ No newline at end of file
#endif
include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -413,5 +410,3 @@ struct BlockwiseGemmDl_A_BK0_BM_BK1_B_BK0_BN_BK1_C_BM0_BM1_BN0_BN1_pipeline_BM0_
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -398,5 +395,3 @@ struct BlockwiseGemmDlops_km_kn_m0m1n0n1_v2r2_pipeline_2x2
}
// namespace ck
#endif
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -179,5 +176,3 @@ struct BlockwiseGemmDlops_km_kn_m0m1n0n1_v3
}
// namespace ck
#endif
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -802,5 +799,3 @@ struct BlockwiseGemmWMMA_k0mk1_k0nk1_m0m1m2n0n1n2m3_CShuffle_FIFO
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -1004,5 +1001,3 @@ struct BlockwiseGemmXdlops_v2
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -322,5 +319,3 @@ struct BlockwiseGemmXdlops_k0mk1_k0nk1_m0n0m1n1m2m3m4n2_v1r1
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -126,5 +123,3 @@ struct BlockwiseSoftmax
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -157,5 +154,3 @@ struct BlockwiseTensorSliceTransfer_v5r1
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -111,5 +108,3 @@ struct BlockwiseWelford
};
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -245,5 +242,3 @@ struct PartitionedBlockwiseReductionWithIndex
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -194,5 +191,3 @@ struct ThreadGroupTensorSliceTransfer_v4r1
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -135,5 +132,3 @@ struct ThreadGroupTensorSliceTransfer_v6r1
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -159,5 +156,3 @@ struct ThreadGroupTensorSliceTransfer_v6r2
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -184,5 +181,3 @@ struct ThreadGroupTensorSliceTransfer_v6r3
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -173,5 +170,3 @@ struct ThreadGroupTensorSliceTransfer_v7
};
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -30,5 +27,3 @@ getConvBackwardDataSpecializationString(const ConvolutionBackwardDataSpecializat
}
// namespace device
}
// namespace tensor_operation
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -34,5 +31,3 @@ getConvBackwardWeightSpecializationString(const ConvolutionBackwardWeightSpecial
}
// namespace device
}
// namespace tensor_operation
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -35,5 +32,3 @@ inline std::string getConvForwardSpecializationString(const ConvolutionForwardSp
}
// namespace device
}
// namespace tensor_operation
}
// namespace ck
#pragma clang diagnostic pop
include/ck/tensor_operation/gpu/device/device_base.hpp
View file @
795bea35
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Weverything"
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
...
...
@@ -11,15 +8,14 @@
#include "ck/stream_config.hpp"
#endif
namespace
ck
{
namespace
tensor_operation
{
namespace
device
{
struct
BaseArgument
{
BaseArgument
()
=
default
;
BaseArgument
(
const
BaseArgument
&
)
=
default
;
BaseArgument
()
=
default
;
BaseArgument
(
const
BaseArgument
&
)
=
default
;
BaseArgument
&
operator
=
(
const
BaseArgument
&
)
=
default
;
virtual
~
BaseArgument
()
{}
...
...
@@ -30,8 +26,8 @@ struct BaseArgument
#ifndef __HIPCC_RTC__
struct
BaseInvoker
{
BaseInvoker
()
=
default
;
BaseInvoker
(
const
BaseInvoker
&
)
=
default
;
BaseInvoker
()
=
default
;
BaseInvoker
(
const
BaseInvoker
&
)
=
default
;
BaseInvoker
&
operator
=
(
const
BaseInvoker
&
)
=
default
;
virtual
float
Run
(
const
BaseArgument
*
,
const
StreamConfig
&
=
StreamConfig
{})
...
...
@@ -45,17 +41,18 @@ struct BaseInvoker
struct
BaseOperator
{
BaseOperator
()
=
default
;
BaseOperator
(
const
BaseOperator
&
)
=
default
;
BaseOperator
()
=
default
;
BaseOperator
(
const
BaseOperator
&
)
=
default
;
BaseOperator
&
operator
=
(
const
BaseOperator
&
)
=
default
;
virtual
bool
IsSupportedArgument
(
const
BaseArgument
*
)
{
return
false
;
}
#ifndef __HIPCC_RTC__
virtual
std
::
string
GetTypeIdName
()
const
{
return
typeid
(
*
this
).
name
();
}
virtual
std
::
string
GetTypeString
()
const
{
return
""
;
}
virtual
std
::
string
GetTypeIdName
()
const
{
return
typeid
(
*
this
).
name
();
}
virtual
std
::
string
GetTypeIdHashCode
()
const
{
std
::
ostringstream
oss
;
...
...
@@ -79,5 +76,3 @@ struct BaseOperator
}
// namespace device
}
// namespace tensor_operation
}
// namespace ck
#pragma clang diagnostic pop
Prev
1
2
3
4
5
…
11
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