linux cuda查询设备信息,CUDA编程——设备属性信息的查询

CUDA的目的就是将大量的计算分配给GPU进行快速运算来节省时间。我们希望在设备上(显卡)上分配内存和执行代码，当今的显卡可能包含多个GPU。如，某些NVIDIA产品-GeForce GTX TITAN X，就是在单块卡上包含两个GPU，所以装配该显卡的计算机拥有两个支持CUDA的处理器。

从CUDA3.0开始，在cudaDeviceProp结构中包含了以下信息:

struct cudaDeviceProp{

char name[256];

size_t totalGlobalMem;

size_t shaerdMemPerBlock;

int regsPerBlock;

int warpSize;

size_t memPitch;

int maxThreadsPerBlock;

int maxThreadsDim[3];

int maxGridSize[3];

size_t totalConstMem;

int major;

int minor;

int clockRate;

size_t textureAlignment;

int deviceOverlap;

int multiProcessorCount;

int kernelExecTimeoutEnabled;

int integrradted;

int canMapHostMemory;

int computeMode；

int maxTexture1D;

int maxTexture2D[2];

int maxTexture3D[3];

int maxTexture2DArray[3];

int concurrentKernels;

}

某些属性可能见文知意很容易理解，但是为了更好的学习还是说明一下吧。见下表。

具体操作代码如下:

int main() {

cudaDeviceProp prop;

int count;

cudaGetDeviceCount(&count);

for (int i = 0; i < count; i++)

{

cudaGetDeviceProperties(&prop, i);

printf("   --- General Inromation for device %d ---\n", i);

printf("Name: %s\n", prop.name);

printf("Compute capability: %d.%d\n", prop.major, prop.minor);

printf("Clock rate: %d\n", prop.clockRate);

printf("Device copy overlap: ");

if (prop.deviceOverlap)

printf("Enabled\n");

else

printf("Dissabled\n");

printf("Kernel execition timeout : ");

if (prop.kernelExecTimeoutEnabled)

printf("Enabled\n");

else

printf("Dissabled\n");

printf("Kernel execition timeout : ");

if (prop.kernelExecTimeoutEnabled)

printf("Enabled\n");

else

printf("Dissabled\n");

printf("    --- Memory Information for device %d ---\n", i);

printf("Total global mem: %ld\n", prop.totalGlobalMem);

printf("Total constant Mem: %ld \n", prop.totalConstMem);

printf("Max mem pitch: %ld\n", prop.memPitch);

printf("Texture Alignment: %ld\n", prop.textureAlignment);

printf("   ---MP Information for device %d ---\n", i);

printf("Multiprocessor count: %d\n", prop.multiProcessorCount);

printf("Shared mem per mp: %ld\n", prop.sharedMemPerBlock);

printf("Registers per mp: %d\n", prop.regsPerBlock);

printf("Threads in warp: %d\n", prop.warpSize);

printf("Max threads per block: %d\n", prop.maxThreadsPerBlock);

printf("Max thread dimensions: (%d, %d, %d)\n", prop.maxThreadsDim[0], prop.maxThreadsDim[1], prop.maxThreadsDim[2]);

printf("Max grid dimensions: (%d, %d,%d)\n", prop.maxGridSize[0], prop.maxGridSize[1], prop.maxGridSize[2]);

printf("\n");

}

return 0;

}

对GPU进行简单的了解后，在后续的GPU运算中能够轻松的进行GPU的调用以及内存相关问题的操作。