Skip to content

GitLab

"wrappers/vscode:/vscode.git/clone" did not exist on "fabb38d1aa6eb3bb4dee0d86d253831e4a0c4181"
Unverified Commit 9efb5cc4 authored by Rostyslav Geyyer's avatar Rostyslav Geyyer Committed by GitHub
Browse files

Merge branch 'develop' into lwpck-759

parents af52fe33 40365904
Hide whitespace changes
Inline Side-by-side
Showing with 26 additions and 24 deletions
include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
...@@ -406,10 +406,12 @@ struct DeviceGroupedGemmXdlSplitKCShuffle : public DeviceGroupedGemmSplitK<ALayo ...@@ -406,10 +406,12 @@ struct DeviceGroupedGemmXdlSplitKCShuffle : public DeviceGroupedGemmSplitK<ALayo
} }
} }
hip_check_error(hipMemcpy(arg.p_workspace_, hip_check_error(
arg.gemm_kernel_args_.data(), hipMemcpyWithStream(arg.p_workspace_,
arg.gemm_kernel_args_.size() * sizeof(GemmTransKernelArg), arg.gemm_kernel_args_.data(),
hipMemcpyHostToDevice)); arg.gemm_kernel_args_.size() * sizeof(GemmTransKernelArg),
hipMemcpyHostToDevice,
stream_config.stream_id_));
float ave_time = 0; float ave_time = 0;
......
include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_permute_impl.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/masking_specialization.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/matrix_padder.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/tensor_layout.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/tensor_specialization.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/device/welford_helper.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
View file @ 9efb5cc4
// SPDX-License-Identifier: MIT // SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved. // Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
#pragma once #pragma once
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment