mirror/darknet
1
0
Fork 0
mirror of https://github.com/pjreddie/darknet.git synced 2023-08-10 21:13:14 +03:00
Code Issues Projects Releases Wiki Activity

CUDA so fast

Browse Source
This commit is contained in:
Joseph Redmon
2015-01-22 16:38:24 -08:00
parent 4ac78c8926
commit 809f924db2
57 changed files with 1116 additions and 2181 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
src/blas.h Normal file
View File

@ -0,0 +1,23 @@
#ifndef BLAS_H
#define BLAS_H
void pm(int M, int N, float *A);
float *random_matrix(int rows, int cols);
void time_random_matrix(int TA, int TB, int m, int k, int n);
void test_blas();
void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY);
void copy_cpu(int N, float *X, int INCX, float *Y, int INCY);
void scal_cpu(int N, float ALPHA, float *X, int INCX);
float dot_cpu(int N, float *X, int INCX, float *Y, int INCY);
void test_gpu_blas();
#ifdef GPU
void axpy_ongpu(int N, float ALPHA, float * X, int INCX, float * Y, int INCY);
void axpy_ongpu_offset(int N, float ALPHA, float * X, int OFFX, int INCX, float * Y, int OFFY, int INCY);
void copy_ongpu(int N, float * X, int INCX, float * Y, int INCY);
void copy_ongpu_offset(int N, float * X, int OFFX, int INCX, float * Y, int OFFY, int INCY);
void scal_ongpu(int N, float ALPHA, float * X, int INCX);
void mask_ongpu(int N, float * X, float * mask, float mod);
#endif
#endif