CUDA编程：查询设备

版权声明：本文为博主原创文章，未经作者允许请勿转载。 https://blog.csdn.net/heiheiya https://blog.csdn.net/heiheiya/article/details/82014822

如果要知道设备拥有多少内存以及具备哪些功能，就需要查询设备。通过调用cudaDeviceCount()函数，可以对每个设备进行迭代，查询每个设备的相关信息。CUDA运行时将返回一个cudaDeviceProp类型的结构，其中就包含了设备的相关属性。

struct cudaDeviceProp {
        char name[256];
        size_t totalGlobalMem;
        size_t sharedMemPerBlock;
        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 integrated;
        int canMapHostMemory;
        int computeMode;
        int maxTexture1D;
        int maxTexture2D[2];
        int maxTexture3D[3];
        int maxTexture2DArray[3];
        int concurrentKernels;
    }

部分属性的含义如下：

	cudaDeviceProp prop;
	int count;
	cudaError_t err = cudaGetDeviceCount(&count);
	for (int i=0; i < count; i++)
	{
		err = cudaGetDeviceProperties(&prop, i);
		printf("------------Device %d--------------\n", i);
		printf("Name:  %s\n", prop.name);
		printf("Computer capability:  %d.%d\n", prop.major, prop.minor);
		printf("Clock rate:  %d\n", prop.clockRate);
		printf("Total global memory:  %lld\n", prop.totalGlobalMem);
		printf("Total constant memory:  %ld\n", prop.totalConstMem);
		printf("Shared memory per mp:  %ld\n", prop.sharedMemPerBlock);
		printf("Registers memory per mp:  %ld\n", prop.regsPerBlock);
		printf("Threads in warp:  %d\n", prop.warpSize);
		printf("Max threads per block:  %d\n", prop.maxThreadsPerBlock);
	}