From 0e610b056dbcd85affa23f64f9f8da4d197f110a Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 08 Sep 2016 05:46:10 +0000
Subject: [PATCH] and again
---
src/cuda.c | 36 ++++++++++++++++++++++++++++++------
1 files changed, 30 insertions(+), 6 deletions(-)
diff --git a/src/cuda.c b/src/cuda.c
index 1b914a5..327813d 100644
--- a/src/cuda.c
+++ b/src/cuda.c
@@ -12,6 +12,7 @@
void check_error(cudaError_t status)
{
+ cudaError_t status2 = cudaGetLastError();
if (status != cudaSuccess)
{
const char *s = cudaGetErrorString(status);
@@ -21,6 +22,15 @@
snprintf(buffer, 256, "CUDA Error: %s", s);
error(buffer);
}
+ if (status2 != cudaSuccess)
+ {
+ const char *s = cudaGetErrorString(status);
+ char buffer[256];
+ printf("CUDA Error Prev: %s\n", s);
+ assert(0);
+ snprintf(buffer, 256, "CUDA Error Prev: %s", s);
+ error(buffer);
+ }
}
dim3 cuda_gridsize(size_t n){
@@ -36,6 +46,19 @@
return d;
}
+#ifdef CUDNN
+cudnnHandle_t cudnn_handle()
+{
+ static int init = 0;
+ static cudnnHandle_t handle;
+ if(!init) {
+ cudnnCreate(&handle);
+ init = 1;
+ }
+ return handle;
+}
+#endif
+
cublasHandle_t blas_handle()
{
static int init = 0;
@@ -47,7 +70,7 @@
return handle;
}
-float *cuda_make_array(float *x, int n)
+float *cuda_make_array(float *x, size_t n)
{
float *x_gpu;
size_t size = sizeof(float)*n;
@@ -57,10 +80,11 @@
status = cudaMemcpy(x_gpu, x, size, cudaMemcpyHostToDevice);
check_error(status);
}
+ if(!x_gpu) error("Cuda malloc failed\n");
return x_gpu;
}
-void cuda_random(float *x_gpu, int n)
+void cuda_random(float *x_gpu, size_t n)
{
static curandGenerator_t gen;
static int init = 0;
@@ -73,7 +97,7 @@
check_error(cudaPeekAtLastError());
}
-float cuda_compare(float *x_gpu, float *x, int n, char *s)
+float cuda_compare(float *x_gpu, float *x, size_t n, char *s)
{
float *tmp = calloc(n, sizeof(float));
cuda_pull_array(x_gpu, tmp, n);
@@ -86,7 +110,7 @@
return err;
}
-int *cuda_make_int_array(int n)
+int *cuda_make_int_array(size_t n)
{
int *x_gpu;
size_t size = sizeof(int)*n;
@@ -101,14 +125,14 @@
check_error(status);
}
-void cuda_push_array(float *x_gpu, float *x, int n)
+void cuda_push_array(float *x_gpu, float *x, size_t n)
{
size_t size = sizeof(float)*n;
cudaError_t status = cudaMemcpy(x_gpu, x, size, cudaMemcpyHostToDevice);
check_error(status);
}
-void cuda_pull_array(float *x_gpu, float *x, int n)
+void cuda_pull_array(float *x_gpu, float *x, size_t n)
{
size_t size = sizeof(float)*n;
cudaError_t status = cudaMemcpy(x, x_gpu, size, cudaMemcpyDeviceToHost);
--
Gitblit v1.10.0