CUDA: identifier "cudaMemGetInfo" is undefined

To estimate how much data the program may process in one kernel launch i try to get some memory info with cudaMemGetInfo(). However, the compiler tells me this:

error: identifier "cudaMemGetInfo" is undefined

Other functions like cudaGetDeviceProperties(); work fine. Do I have to install a certain CUDA-version? The library description does not contain infos about the version and so on.

EDIT: the smallest possible code. cudaSetDevice() generates no compiler error while cudaMemGetInfo() does

#include <cuda.h>
#include <cuda_runtime_api.h>

int main(){
   unsigned int f, t;
   cudaSetDevice(0);
   cudaMemGetInfo(&f, &t);
   return 0;
}

EDIT 2:

I'm on Linux using "Cuda compilation tools, release 2.0, V0.2.1221" (nvcc).

As I tried to get the cuda driver version installed with cudaDriverGetVersion() the same error occured (same thing when I use the driver function cuDriverGetVersion()).

开发者_Go百科 It seems that the system wont let me know any detail about itself...

---

For the very old version of CUDA you are using, cudaMemGetInfo is not part of the runtime API. It has a counterpart in the driver cuMemGetInfo, which can be used instead. Note that using the driver API version of this call will require establishing a context first. This should work on CUDA 2.x:

// CUDA 2.x version
#include <cstdio>
#include <cuda.h>
#include <cuda_runtime_api.h>

int main(){
    unsigned int f, t;
    cudaSetDevice(0);
    cudaFree(0); // This will establish a context on the device
    cuMemGetInfo(&f, &t);
    fprintf(stdout,"%d %d\n",f/1024,t/1024);
    return 0;
}

EDIT: this answer applied to CUDA 3.0 and later:

Your problem isn't cudaMemGetInfo, it is the arguments you are supplying it. I would predict that this:

// CUDA 3.0 or later version
#include <cuda.h>
#include <cuda_runtime_api.h>

int main(){
    size_t f, t;
    cudaSetDevice(0);
    cudaMemGetInfo(&f, &t);
    return 0;
}

will work where your example fails. Note that nvcc uses a host C++ compiler to compile host code, and it will not find instances of API functions with incorrect arguments. Note that the prototype of cudaMemGetInfo is

cudaError_t cudaMemGetInfo(size_t * free, size_t * total)       

and that the arguments should be size_t, which is not the same as unsigned int on many platforms.

---

to fix this error:

error: argument of type "unsigned int *" is incompatible with parameter of type "size_t *".

I found from nvidia technical report for cuda 3.2 that: Driver API functions that accept or return memory sizes, such as cuMemAlloc() and cuMemGetInfo(), now use size_t for this purpose rather than unsigned int.

so you must change *.cu code, as the following lines:

Incorrect code: unsigned int free, total; cuMemGetInfo(&free, &total);

Correct code: size_t free, total; cuMemGetInfo(&free, &total);