Apollo 11.0
自动驾驶开放平台
gemm.h
浏览该文件的文档.
1/******************************************************************************
2 * Copyright 2018 The Apollo Authors. All Rights Reserved.
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
17#pragma once
18
19#include <cblas.h>
20
23
24namespace apollo {
25namespace perception {
26namespace inference {
27class GPUL2Norm {
28 public:
29 void L2Norm(base::Blob<float> *input_data);
30
31 private:
32 base::Blob<float> scale_;
34 base::Blob<float> square_;
35};
36
37void GPUGemmFloat(const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB,
38 const int M, const int N, const int K, const float alpha,
39 const float *A, const float *B, const float beta, float *C);
40void GPUMultiFloat(const int n, const float *a, const float *b, float *result);
41void GPUMSetFloat(const int n, const float alpha, float *result);
42
43} // namespace inference
44} // namespace perception
45} // namespace apollo
A wrapper around SyncedMemory holders serving as the basic computational unit for images,...
Definition blob.h:88
void L2Norm(base::Blob< float > *input_data)
void GPUMSetFloat(const int n, const float alpha, float *result)
void GPUMultiFloat(const int n, const float *a, const float *b, float *result)
void GPUGemmFloat(const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const int M, const int N, const int K, const float alpha, const float *A, const float *B, const float beta, float *C)
class register implement
Definition arena_queue.h:37