Files
composable_kernel/include/ck_tile/host/reference/reference_batched_dropout.hpp
Dan Yao 2cab8d39e3 CK Tile FA Training kernels (#1286)
* FA fwd dropout

* FA bwd

* epilogue reuse

* CMakeLists update

* [CK_TILE] support alibi (#1269)

* add alibi support

* fix code

* update code based on comment

* Support more hdim

* fix fp8 bias

* support seqlen_k=0 case

* remove unused printf

* fix format

---------

Co-authored-by: rocking <ChunYu.Lai@amd.com>

* now fwd/bwd can build

* bwd alibi

* add bwd validation stream_config

* update generated filenames

* update bwd kernel launch

* CK_TILE_HOST_DEVICE in philox

* Transpose -> transpose

* format

* format

* format

* Generate the instance for FA required

* format

* fix error in WarpGemm

---------

Co-authored-by: danyao12 <danyao12>
Co-authored-by: carlushuang <carlus.huang@amd.com>
Co-authored-by: rocking <ChunYu.Lai@amd.com>
Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
Co-authored-by: Jing Zhang <jizhan@amd.com>
2024-06-04 13:12:45 -05:00

34 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/core.hpp"
#include "ck_tile/host/host_tensor.hpp"
#include <thread>
namespace ck_tile {
template <typename DataType, typename RandValOutputDataType>
CK_TILE_HOST void reference_batched_dropout(HostTensor<DataType>& in_out_b_m_n,
const HostTensor<RandValOutputDataType>& randval_b_m_n,
const uint8_t& p_undrop_in_uint8_t,
const float scale)
{
const int N = in_out_b_m_n.mDesc.get_lengths()[2];
auto f = [&](auto batch, auto m) {
for(int n = 0; n < N; ++n)
{
float tmp = ck_tile::type_convert<float>(in_out_b_m_n(batch, m, n)) * scale;
in_out_b_m_n(batch, m, n) = randval_b_m_n(batch, m, n) <= p_undrop_in_uint8_t
? ck_tile::type_convert<DataType>(tmp)
: DataType(0);
}
};
make_ParallelTensorFunctor(
f, randval_b_m_n.mDesc.get_lengths()[0], randval_b_m_n.mDesc.get_lengths()[1])(
std::thread::hardware_concurrency());
}
} // namespace ck_tile