mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 10:09:41 +00:00
b887c7b709
* port layernorm * change warp_welford.hpp * Update warpshuffle * 1. Add save mean and save std back 2. Move construction of tensor_view and tile_window to operator() * refine welford max count calculation * unify layernorm api * Rename file * Remove save mean and inv std * Revert "refine welford max count calculation" This reverts commit022365802b. * Fix order of parameter * refine welford max count calculation again * Remove fp32 instances * Fix bug of padding * refactor api * Support bf16 * Extract common function * Refine arg of operator() * Add kMThreadPerBlock to template parameter * clang format * Refine variable name * Refine file name * remove redundant line * refactor layernorm2d pipeline and add block-per-block utility * fix name * rename more * add more block-per-tile instance * remove duplicated define * update instance for 2048, 1024 case * support up to 2048 now * opt loading * add n1536 * Add two pass pipeline * format * Fix incorrect type * parallel compilation * Use smaller N * fix 2p pass * Support Repeat_M in distribution * Refine nameing * Add reduce example --------- Co-authored-by: letaoqin <letaoqin@amd.com> Co-authored-by: aska-0096 <haocwang@amd.com> Co-authored-by: rocking <ChunYu.Lai@amd.com> Co-authored-by: carlushuang <carlus.huang@amd.com> [ROCm/composable_kernel commit:0394f8a713]
29 lines
1.3 KiB
C++
29 lines
1.3 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck_tile/host/arg_parser.hpp"
|
|
#include "ck_tile/host/check_err.hpp"
|
|
#include "ck_tile/host/convolution_host_tensor_descriptor_helper.hpp"
|
|
#include "ck_tile/host/convolution_parameter.hpp"
|
|
#include "ck_tile/host/device_memory.hpp"
|
|
#include "ck_tile/host/fill.hpp"
|
|
#include "ck_tile/host/hip_check_error.hpp"
|
|
#include "ck_tile/host/host_tensor.hpp"
|
|
#include "ck_tile/host/kernel_launch.hpp"
|
|
#include "ck_tile/host/ranges.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_dropout.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_elementwise.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_gemm.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_masking.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_rotary_position_embedding.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_softmax.hpp"
|
|
#include "ck_tile/host/reference/reference_gemm.hpp"
|
|
#include "ck_tile/host/reference/reference_im2col.hpp"
|
|
#include "ck_tile/host/reference/reference_layernorm2d_fwd.hpp"
|
|
#include "ck_tile/host/reference/reference_reduce.hpp"
|
|
#include "ck_tile/host/reference/reference_softmax.hpp"
|
|
#include "ck_tile/host/stream_config.hpp"
|
|
#include "ck_tile/host/timer.hpp"
|