1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
| #include "opencl.h"
|
| void pm(int M, int N, float *A);
| void gemm(int TA, int TB, int M, int N, int K, float ALPHA,
| float *A, int lda,
| float *B, int ldb,
| float BETA,
| float *C, int ldc);
| float *random_matrix(int rows, int cols);
| void time_random_matrix(int TA, int TB, int m, int k, int n);
|
| #ifdef GPU
| void axpy_ongpu(int N, float ALPHA, cl_mem X, int INCX, cl_mem Y, int INCY);
| void copy_ongpu(int N, cl_mem X, int INCX, cl_mem Y, int INCY);
| void scal_ongpu(int N, float ALPHA, cl_mem X, int INCX);
| void im2col_ongpu(cl_mem data_im, int batch,
| int channels, int height, int width,
| int ksize, int stride, int pad, cl_mem data_col);
|
| void col2im_gpu(float *data_col, int batch,
| int channels, int height, int width,
| int ksize, int stride, int pad, float *data_im);
| void col2im_ongpu(cl_mem data_col, int batch,
| int channels, int height, int width,
| int ksize, int stride, int pad, cl_mem data_im);
|
| void im2col_gpu(float *data_im, int batch,
| int channels, int height, int width,
| int ksize, int stride, int pad, float *data_col);
|
| void gemm_ongpu(int TA, int TB, int M, int N, int K, float ALPHA,
| cl_mem A_gpu, int lda,
| cl_mem B_gpu, int ldb,
| float BETA,
| cl_mem C_gpu, int ldc);
| #endif
|
| void im2col_cpu(float* data_im, int batch,
| int channels, int height, int width,
| int ksize, int stride, int pad, float* data_col);
|
| void col2im_cpu(float* data_col, int batch,
| int channels, int height, int width,
| int ksize, int stride, int pad, float* data_im);
|
| void test_blas();
|
| void gemm_gpu(int TA, int TB, int M, int N, int K, float ALPHA,
| float *A, int lda,
| float *B, int ldb,
| float BETA,
| float *C, int ldc);
| void gemm_cpu(int TA, int TB, int M, int N, int K, float ALPHA,
| float *A, int lda,
| float *B, int ldb,
| float BETA,
| float *C, int ldc);
| inline void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY);
| inline void copy_cpu(int N, float *X, int INCX, float *Y, int INCY);
| inline void scal_cpu(int N, float ALPHA, float *X, int INCX);
| inline float dot_cpu(int N, float *X, int INCX, float *Y, int INCY);
| void test_gpu_blas();
|
|
