XeTLA v0.3.6
IntelĀ® Xe Templates for Linear Algebra - API Definition Document
 
Loading...
Searching...
No Matches
api.hpp
Go to the documentation of this file.
1/*******************************************************************************
2* Copyright (c) 2022-2023 Intel Corporation
3*
4* Licensed under the Apache License, Version 2.0 (the "License");
5* you may not use this file except in compliance with the License.
6* You may obtain a copy of the License at
7*
8* http://www.apache.org/licenses/LICENSE-2.0
9*
10* Unless required by applicable law or agreed to in writing, software
11* distributed under the License is distributed on an "AS IS" BASIS,
12* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13* See the License for the specific language governing permissions and
14* limitations under the License.
15*******************************************************************************/
16
19
20#pragma once
21
24
25namespace gpu::xetla::kernel {
26
37template <typename dtype_x_, typename dtype_y_, typename dtype_weight_,
38 typename dtype_acc_, typename layer_norm_attr_,
39 bool store_for_bwd_ = true, gpu_arch arch_ = gpu_arch::Xe,
40 typename ln_fwd_fused_op_
41 = group::ln_fwd_fused_op_t<ln_fwd_fused_kind::none, dtype_x_, dtype_y_,
42 dtype_acc_, layer_norm_attr_, arch_>>
44
54template <typename dtype_x_, typename dtype_y_, typename dtype_weight_,
55 typename dtype_acc_, typename layer_norm_attr_,
56 gpu_arch arch_ = gpu_arch::Xe,
57 typename ln_bwd_fused_op_
59 /*in bwd, y is input, x is output*/ dtype_acc_,
60 layer_norm_attr_, arch_>>
62
63} // namespace gpu::xetla::kernel
C++ API.
C++ API.
Definition limitation.hpp:734
gpu_arch
Definition common.hpp:73
Definition layer_norm_fused_op_api.hpp:73