我在Ubuntu12.04上正确安装了CUDA 6.0，并且在Nsight Eclipse中传递了样本vectorAdd.cu：
/**
* Copyright 1993-2014 NVIDIA Corporation. All rights reserved.
*
* Please refer to the NVIDIA end user license agreement (EULA) associated
* with this source code for terms and conditions that govern your use of
* this software. Any use, reproduction, disclosure, or distribution of
* this software and related documentation outside the terms of the EULA
* is strictly prohibited.
*
*/
/**
* Vector addition: C = A + B.
*
* This sample is a very basic sample that implements element by element
* vector addition. It is the same as the sample illustrating Chapter 2
* of the programming guide with some additions like error checking.
*/
#include <stdio.h>
// For the CUDA runtime routines (prefixed with "cuda_")
#include <cuda_runtime.h>
/**
* CUDA Kernel Device code
*
* Computes the vector addition of A and B into C. The 3 vectors have the same
* number of elements numElements.
*/
__global__ void
vectorAdd(const float *A, const float *B, float *C, int numElements)
{
int i = blockDim.x * blockIdx.x + threadIdx.x;
if (i < numElements)
{
C[i] = A[i] + B[i];
C[i] = C[i] + 1;
}
}
/**
* Host main routine
*/
int
main(void)
{
// Error code to check return values for CUDA calls
cudaError_t err = cudaSuccess;
// Print the vector length to be used, and compute its size
int numElements = 50000;
size_t size = numElements * sizeof(float);
printf("[Vector addition of %d elements]\n", numElements);
// Allocate the host input vector A
float *h_A = (float *)malloc(size);
// Allocate the host input vector B
float *h_B = (float *)malloc(size);
// Allocate the host output vector C
float *h_C = (float *)malloc(size);
// Verify that allocations succeeded
if (h_A == NULL || h_B == NULL || h_C == NULL)
{
fprintf(stderr, "Failed to allocate host vectors!\n");
exit(EXIT_FAILURE);
}
// Initialize the host input vectors
for (int i = 0; i < numElements; ++i)
{
h_A[i] = rand()/(float)RAND_MAX;
h_B[i] = rand()/(float)RAND_MAX;
}
// Allocate the device input vector A
float *d_A = NULL;
err = cudaMalloc((void **)&d_A, size);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to allocate device vector A (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Allocate the device input vector B
float *d_B = NULL;
err = cudaMalloc((void **)&d_B, size);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to allocate device vector B (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Allocate the device output vector C
float *d_C = NULL;
err = cudaMalloc((void **)&d_C, size);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to allocate device vector C (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Copy the host input vectors A and B in host memory to the device input vectors in
// device memory
printf("Copy input data from the host memory to the CUDA device\n");
err = cudaMemcpy(d_A, h_A, size, cudaMemcpyHostToDevice);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to copy vector A from host to device (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
err = cudaMemcpy(d_B, h_B, size, cudaMemcpyHostToDevice);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to copy vector B from host to device (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Launch the Vector Add CUDA Kernel
int threadsPerBlock = 256;
int blocksPerGrid =(numElements + threadsPerBlock - 1) / threadsPerBlock;
printf("CUDA kernel launch with %d blocks of %d threads\n", blocksPerGrid, threadsPerBlock);
vectorAdd<<<blocksPerGrid, threadsPerBlock>>>(d_A, d_B, d_C, numElements);
err = cudaGetLastError();
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to launch vectorAdd kernel (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Copy the device result vector in device memory to the host result vector
// in host memory.
printf("Copy output data from the CUDA device to the host memory\n");
err = cudaMemcpy(h_C, d_C, size, cudaMemcpyDeviceToHost);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to copy vector C from device to host (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Verify that the result vector is correct
for (int i = 0; i < numElements; ++i)
{
if (fabs(h_A[i] + h_B[i] - h_C[i]) > 1e-5)
{
fprintf(stderr, "Result verification failed at element %d!\n", i);
exit(EXIT_FAILURE);
}
}
printf("Test PASSED\n");
// Free device global memory
err = cudaFree(d_A);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to free device vector A (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
err = cudaFree(d_B);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to free device vector B (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
err = cudaFree(d_C);
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to free device vector C (error code %s)!\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
// Free host memory
free(h_A);
free(h_B);
free(h_C);
// Reset the device and exit
// cudaDeviceReset causes the driver to clean up all state. While
// not mandatory in normal operation, it is good practice. It is also
// needed to ensure correct operation when the application is being
// profiled. Calling cudaDeviceReset causes all profile data to be
// flushed before the application exits
err = cudaDeviceReset();
if (err != cudaSuccess)
{
fprintf(stderr, "Failed to deinitialize the device! error=%s\n", cudaGetErrorString(err));
exit(EXIT_FAILURE);
}
printf("Done\n");
return 0;
}
当我尝试使用cuda-gdb来调试该程序（CUDA设备是GT240）时，按Ctrl + Alt + F1并使用sudo service lightdm stop关闭X11。
使用以下命令编译源文件：
nvcc -g -G vectorAdd.cu -o vectorAdd -gencode arch=compute_12,code=sm_12
然后使用以下命令输入debug：
$ cuda-gdb vectorAdd
NVIDIA (R) CUDA Debugger
6.0 release
Portions Copyright (C) 2007-2014 NVIDIA Corporation
GUN gdb (GDB) 7.6
Copyright (C) 2013 Free SoftWare Foundation, Inc.
Licnese GPLv3+: GNU GPL version 3 or later <http://gnu.org/license/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law. Type "show copying" and "show warranty" for details.
This GDB was configured as "x86_64-unknown-linux-gnu".
For bug reporting instructions, please see:
<http://www.gnu.org/software/gdb/bugs/>...
Reading symbols from /home/<username>/cuda-workspace/SampleForGDB/src/vectorAdd...done
(cuda-gdb) break 131
Breakpoint 1 at 0x402814: file vectorAdd.cu line, 131.
(cuda-gdb) run
Staring program: /home/<username>/cuda-workspace/SampleForGDB/src/vectorAdd
[Thread debugging using libthread_db enable]
Using host libthread_db library: "/lib/x86_64-linux-gnu/libthread_db.so.1".
[Vector addition of 50000 elements]
Error: Failed to read the vaild warps mask (dev=0, sm=0, error=16)
即使我没有设置断点，也会发生同样的错误。我输入(cuda-gdb)info cuda devices，它显示＆＃34; No Devices＆＃34;虽然我在cuda_samples / bin下运行./deviceQueryDrv得到了正确的结果。