mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 13:11:25 +00:00
16dc18e0f9
* Add conv perlayer quantization
* Add gemm_dlops quantization
* Support int8 for innerproduct
* Refine gemm dlops int8 kernel parameter
* Support gfx908(MI100) and gfx90a(MI200)
* clang-format
* Rename example number
* Support different layout for d tensor
* Add conv dlops perchannel quantization example
* Move to example 40
* Extract the common code for different platform (dlops and xdlops)
* Move ot subfolder. Prepare to add other op of quantization
* Refine the quantization instance library
* Add conv dl instances and client example
* Remove unnecessary type
* Add gemm quantization instance
* Add external api and client example
* Refine num_bytes
* Separete different layout to different cpp
* Add more xdl instances
* Revert "Remove unnecessary type"
This reverts commit 820869182f.
* Remove CShuffleDataType in dlops
Let acc and CShuffleDataType be the same in xdlops
---------
Co-authored-by: zjing14 <zhangjing14@gmail.com>
19 lines
766 B
C++
19 lines
766 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck/ck.hpp"
|
|
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
|
|
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
|
|
|
|
#include "ck/library/utility/algorithm.hpp"
|
|
#include "ck/library/utility/check_err.hpp"
|
|
#include "ck/library/utility/device_memory.hpp"
|
|
#include "ck/library/utility/host_tensor.hpp"
|
|
#include "ck/library/utility/host_tensor_generator.hpp"
|
|
#include "ck/library/utility/literals.hpp"
|
|
#include "ck/library/utility/convolution_parameter.hpp"
|
|
#include "ck/library/utility/convolution_host_tensor_descriptor_helper.hpp"
|
|
#include "ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp"
|