Hi there,
I am trying to generate a dll cuda file in VS 2010, but I get an error at the linking stage.
The steps to create the dll are:
- Make a new CUDA project (CUDA version 6.5) and add the main file (see below)
- Add a new CUDA project, add the header and function files and set the Configuration Type as dynamic library (.dll)
- Add the path of the header file in Additional Include Directory properties of the CUDA project main application. Same for the compiled library path: I add it in the Additional Library directories plus in the Input section I add the cudaDllModule.lib file.
Here my simple test files:
Header file: CUDASommaDiNumeri.h
//-----------------------------------------------------------------------------
#ifndef CUDA_SOMMA_DI_NUMERI
#define CUDA_SOMMA_DI_NUMERI
__declspec ( dllexport) device float CUDAsum(float n1, float n2);
#endif
//-----------------------------------------------------------------------------
Function file: CUDASommaDiNumeri.cu
//-----------------------------------------------------------------------------
#include “cuda_runtime.h”
#include “device_launch_parameters.h”
#include “CUDASommaDiNumeri.h”
device float CUDAsum(float n1, float n2)
{
return n1+n2;
}
//-----------------------------------------------------------------------------
Main file: kernel.cu
//-----------------------------------------------------------------------------
#include “cuda_runtime.h”
#include “device_launch_parameters.h”
#include <stdio.h>
#include “CUDASommaDiNumeri.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];
float ccc=CUDAsum(6.,8.);
c[i]=int(ccc);
}
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;
}
The error I get is:
ptxas fatal : Unresolved extern function ‘_Z7CUDAsumff’
Here the full output:
1>------ Build started: Project: CUDADll, Configuration: Release x64 ------
1> Compiling CUDA source file kernel.cu…
1>
1> F:\jony\Work\Development\Test_CUDA\CUDADll\CUDADll>“C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\bin\nvcc.exe” -gencode=arch=compute_20,code="sm_20,compute_20" --use-local-env --cl-version 2010 -ccbin “C:\Program Files (x86)\Microsoft Visual Studio 10.0\VC\bin\x86_amd64” -IF:\jony\Work\Development\Test_CUDA\CUDADll\dllModule -IF:\jony\Work\Development\Test_CUDA\CUDADll\cudaDllModule -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include" --keep-dir x64\Release -maxrregcount=0 --machine 64 --compile -cudart static -DWIN32 -DWIN64 -DNDEBUG -D_CONSOLE -D_MBCS -Xcompiler “/EHsc /W3 /nologo /O2 /Zi /MD " -o x64\Release\kernel.cu.obj “F:\jony\Work\Development\Test_CUDA\CUDADll\CUDADll\kernel.cu”
1> ptxas fatal : Unresolved extern function ‘_Z7CUDAsumff’
1> kernel.cu
1>C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\BuildCustomizations\CUDA 6.5.targets(593,9): error MSB3721: The command ““C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\bin\nvcc.exe” -gencode=arch=compute_20,code="sm_20,compute_20" --use-local-env --cl-version 2010 -ccbin “C:\Program Files (x86)\Microsoft Visual Studio 10.0\VC\bin\x86_amd64” -IF:\jony\Work\Development\Test_CUDA\CUDADll\dllModule -IF:\jony\Work\Development\Test_CUDA\CUDADll\cudaDllModule -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include” -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v6.5\include” --keep-dir x64\Release -maxrregcount=0 --machine 64 --compile -cudart static -DWIN32 -DWIN64 -DNDEBUG -D_CONSOLE -D_MBCS -Xcompiler “/EHsc /W3 /nologo /O2 /Zi /MD " -o x64\Release\kernel.cu.obj “F:\jony\Work\Development\Test_CUDA\CUDADll\CUDADll\kernel.cu”” exited with code 255.
========== Build: 0 succeeded, 1 failed, 2 up-to-date, 0 skipped ==========
Do you have any idea of where the problem is?
Many thanks in advance
Jony