Question

我正在CUDA中进行这个简单的求和程序，当anwer应该为14时，它会一直给我回答“答案是5”。我认为这意味着它不是将数据从设备复制回主机，而是我不确定。这是我正在使用的程序，名为“newsum.cu”：

#include <iostream>
#include <cuda.h>

using namespace std;

__global__ void AddIntsCUDA(int* a, int* b)
{
a[0] += b[0];
}

int main()
{
int a = 5, b = 9;
int *d_a, *d_b;

//maybe put (void **) before &d_a in cudaMalloc?
cudaMalloc(&d_a, sizeof(int));
cudaMalloc(&d_b, sizeof(int));

cudaMemcpy(d_a, &a, sizeof(int), cudaMemcpyHostToDevice);
cudaMemcpy(d_b, &b, sizeof(int), cudaMemcpyHostToDevice);

AddIntsCUDA<<<1, 1>>>(d_a, d_b);

cudaMemcpy(&a, d_a, sizeof(int), cudaMemcpyDeviceToHost);

cout<<"The answer is "<<a<<endl;

cudaFree(d_a);
cudaFree(d_b);

return 0;
}

这是我用来编译它的makefile：

# A simple CUDA makefile
#
# Author: Naga Kandasamy
# Date: 9/16/2015
#
# CUDA depends on two things:
#  1) The CUDA nvcc compiler, which needs to be on your path,
#       or called directly, which we do here
#  2) The CUDA shared library being available at runtime,
#       which we make available by setting the LD_LIBRARY_PATH
#       variable for the duration of the makefile.
#
#   Note that you can set your PATH and LD_LIBRARY_PATH variables as part of your
# .bash_profile so that you can compile and run without using this makefile.

NVCCFLAGS       := -O3 -gencode arch=compute_30,code=sm_30
NVCC            := /usr/local/cuda/bin/nvcc
LD_LIBRARY_PATH := /usr/local/cuda/lib64

all: newsum

newsum: newsum.cu
        $(NVCC) -o newsum newsum.cu $(NVCCFLAGS)

clean:
        rm newsum

为什么它给我错误的答案？

为什么我的cuda sum程序无法在设备上运行？

0 个答案: