Linux
$ nsight
ncvv编译器
单卡模式(一个GPU)
双卡模式(两个GPU,1个显示,1个调试)
远程调试(连接远程服务器)
查看硬件配置:$ lspci | grep -i nvidia
显示设置放在GPU,专业调试放在另一个GPU
$ nvidia-smi系统管理接口
1、启动Nsight
2、新建project
3、选择平台CUDA的计算能力是不一样的
4、release和debug的选项
5、添加sorce file,自动生成模板
#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <stdio.h>
cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size);
__global__ void addKernel(int *c, const int *a, const int *b)
{
int i = threadIdx.x;
int m, n;
m = 0;
n = 1;
c[i] = m+n+a[i] + b[i];
}
int main()
{
const int arraySize = 5;
const int a[arraySize] = { 1, 2, 3, 4, 5 };
const int b[arraySize] = { 10, 20, 30, 40, 50 };
int c[arraySize] = { 0 };
// Add vectors in parallel.
cudaError_t cudaStatus = addWithCuda(c, a, b, arraySize);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "addWithCuda failed!");
return 1;
}
printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n",
c[0], c[1], c[2], c[3], c[4]);
// cudaDeviceReset must be called before exiting in order for profiling and
// tracing tools such as Nsight and Visual Profiler to show complete traces.
cudaStatus = cudaDeviceReset();
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaDeviceReset failed!");
return 1;
}
return 0;
}
// Helper function for using CUDA to add vectors in parallel.
cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size)
{
int *dev_a = 0;
int *dev_b = 0;
int *dev_c = 0;
cudaError_t cudaStatus;
// Choose which GPU to run on, change this on a multi-GPU system.
cudaStatus = cudaSetDevice(0);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaSetDevice failed! Do you have a CUDA-capable GPU installed?");
goto Error;
}
// Allocate GPU buffers for three vectors (two input, one output) .
cudaStatus = cudaMalloc((void**)&dev_c, size * sizeof(int));
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMalloc failed!");
goto Error;
}
cudaStatus = cudaMalloc((void**)&dev_a, size * sizeof(int));
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMalloc failed!");
goto Error;
}
cudaStatus = cudaMalloc((void**)&dev_b, size * sizeof(int));
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMalloc failed!");
goto Error;
}
// Copy input vectors from host memory to GPU buffers.
cudaStatus = cudaMemcpy(dev_a, a, size * sizeof(int), cudaMemcpyHostToDevice);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMemcpy failed!");
goto Error;
}
cudaStatus = cudaMemcpy(dev_b, b, size * sizeof(int), cudaMemcpyHostToDevice);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMemcpy failed!");
goto Error;
}
// Launch a kernel on the GPU with one thread for each element.
addKernel<<<1, size>>>(dev_c, dev_a, dev_b);
// Check for any errors launching the kernel
cudaStatus = cudaGetLastError();
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "addKernel launch failed: %s\n", cudaGetErrorString(cudaStatus));
goto Error;
}
// cudaDeviceSynchronize waits for the kernel to finish, and returns
// any errors encountered during the launch.
cudaStatus = cudaDeviceSynchronize();
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaDeviceSynchronize returned error code %d after launching addKernel!\n", cudaStatus);
goto Error;
}
// Copy output vector from GPU buffer to host memory.
cudaStatus = cudaMemcpy(c, dev_c, size * sizeof(int), cudaMemcpyDeviceToHost);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMemcpy failed!");
goto Error;
}
Error:
cudaFree(dev_c);
cudaFree(dev_a);
cudaFree(dev_b);
return cudaStatus;
}
6、编译
7、配置
8、执行
利用Nsight跟踪程序
1、配置debug
2、启动debug
3、双击打断点
直接进行系统性能分析。
profiler,会得到性能指标,占用率;
使用命令行CUDA GDB调试
1、编译生成a.out:$ nvcc -g -G xx.cu
2、执行: ./a.out
3、代码调试:cuda-gdb a.out
4、查看代码(cuda-gdb) l
5、cuda-gdb的差异:(cuda-gdb) help cuda
6、14行打断点: (cuda-gdb) b 14
7、 直接执行:(cuda-gdb) r
8、观察其他变量:(cuda-gdb) p x
9、执行下一步:(cuda-gdb) n
10、查看另一个线程:(cuda-gdb) cuda thread (2,0,0)
11、执行完剩余代码:(cuda-gdb) c
12、退出:(cuda-gdb) q
13、清屏 : $ clear
如果只有一块GPU的卡,使用nsight有点困难,同时做显示和调试有些冲突,一个GPU推荐使用CUDA-GDB使用命令行,有一些要求就是要停掉占用GPU做图形显示的
$ /etc/init.d/lightdm stop
如果使用远程服务器的GPU,使用SSH登陆上去做服务器调试
$ ssh a@123.123.12.1
即使用nsight又使用远程调试
不是很方便
硬件需求:远程服务器+远程cuda-gdbserver+账户密码+网络环境
1、建立cuda工程
2、设置PTX和GPU code版本
3、配置release和debug
4、新建源代码
5、编译
6、执行 (本机上没有CUDA环境)
7、配置服务器环境:Run-->Debug Remote Application-->Debug CUDA Application-->Debug an application on a remote system-->Upload local executable--》remote connection ->new-->ssh only--> host name;connection name; description-->connect-->user ID ;Password
a)把本地编译的可执行文件上传到服务器:Upload local executable
b) 如果在服务器已经有了编译好的可执行文件:Debug remote executable
c) 不上传,只是在本地执行
7、设置远程服务器
8、选择cuda-gdbserver的路径(默认),远程目录环境,