I installed CUDA toolkit and NSight plugin for VS 2017. Did all those fixes to enable creating CUDA project in VS2017. However when I am running this pre-generated code:
#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;
c[i] = 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;
}
It fails at the line cudaStatus = cudaSetDevice(0); in the function addWithCuda() and prints the error: “cudaSetDevice failed! Do you have a CUDA-capable GPU installed?”
I have NVidia GTX 1050 2GB GPU and just recently updated its driver and restarted my computer.
I also run nvidia-smi and got this output:
Mon Apr 08 21:43:57 2019
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 399.24 Driver Version: 399.24 |
|-------------------------------+----------------------+----------------------+
| GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 1050 WDDM | 00000000:01:00.0 On | N/A |
| 29% 28C P8 N/A / 65W | 653MiB / 2048MiB | 1% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 1108 C+G ...dows.Cortana_cw5n1h2txyewy\SearchUI.exe N/A |
| 0 1176 C+G Insufficient Permissions N/A |
| 0 1904 C+G C:\Windows\explorer.exe N/A |
| 0 3128 C+G ...ost.CLR.x86\ServiceHub.Host.CLR.x86.exe N/A |
| 0 4368 C+G ...42.60.0_x64__kzf8qxf38zg5c\SkypeApp.exe N/A |
| 0 6944 C+G ...t_cw5n1h2txyewy\ShellExperienceHost.exe N/A |
| 0 8368 C+G ...11411.0_x64__8wekyb3d8bbwe\Video.UI.exe N/A |
| 0 9044 C+G ...al\Binaries\Win64\EpicGamesLauncher.exe N/A |
| 0 9472 C+G ...\bin\cef\cef.win7x64\steamwebhelper.exe N/A |
| 0 9724 C+G ...ogram Files\Mozilla Firefox\firefox.exe N/A |
| 0 9788 C+G ...\Binaries\Win64\UnrealCEFSubProcess.exe N/A |
| 0 9984 C+G ...o017\Community\Common7\IDE\devenv.exe N/A |
| 0 11572 C+G ...ogram Files\Mozilla Firefox\firefox.exe N/A |
| 0 11580 C+G ...ogram Files\Mozilla Firefox\firefox.exe N/A |
| 0 11840 C+G ...ogram Files\Mozilla Firefox\firefox.exe N/A |
| 0 12416 C+G ...ogram Files\Mozilla Firefox\firefox.exe N/A |
| 0 13136 C+G ...ogram Files\Mozilla Firefox\firefox.exe N/A |
+-----------------------------------------------------------------------------+
which seems ok, though i don’t understand what it says.
What should I do additionaly to make VS 2017 or NSight plugin or, CUDA find my card?