CUDA

CUDA（Compute Unified Device Architecture），是显卡厂商NVIDIA推出的运算平台。 CUDA™是一种由NVIDIA推出的通用并行计算架构，该架构使GPU能够解决复杂的计算问题。 它包含了CUDA指令集架构（ISA）以及GPU内部的并行计算引擎。 开发人员可以使用C语言来为CUDA™架构编写程序，所编写出的程序可以在支持CUDA™的处理器上以超高性能运行。

 如果这是你第一次使用CUDA，在Linux系统中，你可能想使用以下命令来检查CUDA
编译器是否正确安装：

nvcc

使用nvidia-smi查询GPU信息

nvidia-smi

在运行时设置设备

CUDA_VISIBLE_DEVICES=2，nvidia驱动程序会屏蔽其他GPU，这时设备2作为设备0出现在应用程序中。

CUDA_VISIBLE_DEVICES=2，3 nvidia驱动程序将只使用ID为2和3的设备，并且会将设备ID分别映射为0和1。

使用运行时API查询GPU信息

checkDeviceInfor.cu

#include "../common/common.h"
#include <cuda_runtime.h>
#include <stdio.h>
​
/** Display a variety of information on the first CUDA device in this system,* including driver version, runtime version, compute capability, bytes of* global memory, etc.*/
​
int main(int argc, char **argv)
{printf("%s Starting...\n", argv[0]);
​int deviceCount = 0;cudaGetDeviceCount(&deviceCount);
​if (deviceCount == 0){printf("There are no available device(s) that support CUDA\n");}else{printf("Detected %d CUDA Capable device(s)\n", deviceCount);}
​int dev = 0, driverVersion = 0, runtimeVersion = 0;cudaDeviceProp deviceProp;
​for(;  dev < deviceCount; dev++){CHECK(cudaSetDevice(dev));CHECK(cudaGetDeviceProperties(&deviceProp, dev));printf("Device %d: \"%s\"\n", dev, deviceProp.name);}
​cudaDriverGetVersion(&driverVersion);cudaRuntimeGetVersion(&runtimeVersion);printf("  CUDA Driver Version / Runtime Version          %d.%d / %d.%d\n",driverVersion / 1000, (driverVersion % 100) / 10,runtimeVersion / 1000, (runtimeVersion % 100) / 10);printf("  CUDA Capability Major/Minor version number:    %d.%d\n",deviceProp.major, deviceProp.minor);printf("  Total amount of global memory:                 %.2f GBytes (%llu ""bytes)\n", (float)deviceProp.totalGlobalMem / pow(1024.0, 3),(unsigned long long)deviceProp.totalGlobalMem);printf("  GPU Clock rate:                                %.0f MHz (%0.2f ""GHz)\n", deviceProp.clockRate * 1e-3f,deviceProp.clockRate * 1e-6f);printf("  Memory Clock rate:                             %.0f Mhz\n",deviceProp.memoryClockRate * 1e-3f);printf("  Memory Bus Width:                              %d-bit\n",deviceProp.memoryBusWidth);
​if (deviceProp.l2CacheSize){printf("  L2 Cache Size:                                 %d bytes\n",deviceProp.l2CacheSize);}
​printf("  Max Texture Dimension Size (x,y,z)             1D=(%d), ""2D=(%d,%d), 3D=(%d,%d,%d)\n", deviceProp.maxTexture1D,deviceProp.maxTexture2D[0], deviceProp.maxTexture2D[1],deviceProp.maxTexture3D[0], deviceProp.maxTexture3D[1],deviceProp.maxTexture3D[2]);printf("  Max Layered Texture Size (dim) x layers        1D=(%d) x %d, ""2D=(%d,%d) x %d\n", deviceProp.maxTexture1DLayered[0],deviceProp.maxTexture1DLayered[1], deviceProp.maxTexture2DLayered[0],deviceProp.maxTexture2DLayered[1],deviceProp.maxTexture2DLayered[2]);printf("  Total amount of constant memory:               %lu bytes\n",deviceProp.totalConstMem);printf("  Total amount of shared memory per block:       %lu bytes\n",deviceProp.sharedMemPerBlock);printf("  Total number of registers available per block: %d\n",deviceProp.regsPerBlock);printf("  Warp size:                                     %d\n",deviceProp.warpSize);printf("  Maximum number of threads per multiprocessor:  %d\n",deviceProp.maxThreadsPerMultiProcessor);printf("  Maximum number of threads per block:           %d\n",deviceProp.maxThreadsPerBlock);printf("  Maximum sizes of each dimension of a block:    %d x %d x %d\n",deviceProp.maxThreadsDim[0],deviceProp.maxThreadsDim[1],deviceProp.maxThreadsDim[2]);printf("  Maximum sizes of each dimension of a grid:     %d x %d x %d\n",deviceProp.maxGridSize[0],deviceProp.maxGridSize[1],deviceProp.maxGridSize[2]);printf("  Maximum memory pitch:                          %lu bytes\n",deviceProp.memPitch);
​exit(EXIT_SUCCESS);
}
​