下面的cublas代码给出了我们的错误:在“cublasSnrm2(handle,row,dy,incy,de)”中倾倒核心,你能给出一些建议吗?
main.cu
#include <iostream>
#include "cublas.h"
#include "cublas_v2.h"
#include "helper_cuda.h"
using namespace std;
int main(int argc,char *args[])
{
float y[10] = {1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0};
int dev=0;
checkCudaErrors(cudaSetDevice(dev));
//cublas init
cublasStatus stat;
cublasInit();
cublasHandle_t handle;
stat = cublasCreate(&handle);
if (stat !=CUBLAS_STATUS_SUCCESS)
{
printf("cublas handle create failed!\n");
cublasShutdown();
}
float * dy,*de,*e;
int incy = 1,ONE = 1,row = 10;
e = (float *)malloc(sizeof(float)*ONE);
e[0]=0.0f;
checkCudaErrors(cudaMalloc(&dy,sizeof(float)*row));
checkCudaErrors(cudaMalloc(&de,sizeof(float)*ONE));
checkCudaErrors(cudaMemcpy(dy,y,row*sizeof(float),cudaMemcpyHostToDevice));
checkCudaErrors(cudaMemcpy(de,e,ONE*sizeof(float),cudaMemcpyHostToDevice));
stat = cublasSnrm2(handle,row,dy,incy,de);
if (stat !=CUBLAS_STATUS_SUCCESS)
{
printf("norm2 compute failed!\n");
cublasShutdown();
}
checkCudaErrors(cudaMemcpy(e,de,ONE*sizeof(float),cudaMemcpyDeviceToHost));
std::cout<<e[0]<<endl;
return 0;
}
makefile如下:
NVIDIA = $(HOME)/NVIDIA_CUDA-5.0_Samples
CUDA = /usr/local/cuda-5.0
NVIDINCADD = -I$(NVIDIA)/common/inc
CUDAINCADD = -I$(CUDA)/include
CC = -L/usr/lib64/ -lstdc++
GCCOPT = -O2 -fno-rtti -fno-exceptions
INTELOPT = -O3 -fno-rtti -xW -restrict -fno-alias
DEB = -g
NVCC = -G
ARCH = -arch=sm_35
bcg:main.cu
nvcc $(DEB) $(NVCC) $(ARCH) $(CC) -lm $(NVIDINCADD) $(CUDAINCADD) -lcublas -I./ -o $(@) $(<)
clean:
rm -f bcg
rm -f hyb
我的操作系统是linux redhat 6.2,CUDA的版本是5.0,GPU是K20M。
答案 0 :(得分:4)
问题在于:
cublasSnrm2(handle,row,dy,incy,de);
默认情况下,最后一个参数是主机指针。因此要么将e
传递给snrm2调用而不是de
,要么执行此操作:
cublasSetPointerMode(handle,CUBLAS_POINTER_MODE_DEVICE);
stat = cublasSnrm2(handle,row,dy,incy,de);
如果要传递设备指针以存储结果,则需要将指针模式设置为设备。