From 787d5345609459f21fd65d2d8b4fcd55201e21a1 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Mon, 13 Oct 2014 07:31:10 +0000
Subject: [PATCH] Convolutional working on GPU
---
src/mini_blas.h | 52 +++++++++++++++++++++++++++++++++++++++++-----------
1 files changed, 41 insertions(+), 11 deletions(-)
diff --git a/src/mini_blas.h b/src/mini_blas.h
index 34f15de..a155c35 100644
--- a/src/mini_blas.h
+++ b/src/mini_blas.h
@@ -1,3 +1,5 @@
+#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,
@@ -6,15 +8,41 @@
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);
-void im2col_gpu(float* data_im, const int channels,
- const int height, const int width, const int ksize, const int stride,
- float* data_col);
-void im2col_cpu(float* data_im, const int channels,
- const int height, const int width, const int ksize, const int stride,
- float* data_col);
-void col2im_cpu(float* data_col, const int channels,
- const int height, const int width, const int ksize, const int stride,
- float* data_im);
+
+#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,
@@ -27,6 +55,8 @@
float *B, int ldb,
float BETA,
float *C, int ldc);
-void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY);
-void scal_cpu(int N, float ALPHA, float *X, int INCX);
+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();
--
Gitblit v1.10.0