我对这一切都很陌生（从本周开始），所以请善待 :) 我需要找出我的内存是如何在我的 GPU 卡上分布的。我正在运行具有 6 个内核的 Intel Xeon CPU 和 Tesla C2050 GPU 卡。如何找出全局、共享、本地、常量和纹理内存的大小？ 我尝试使用一些上传的 deviceQuery 代码，但此时我无法编译任何 cuda 代码。
提前致谢
【问题讨论】：
#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <stdio.h>
int main( void ) {
cudaDeviceProp prop;
int count;
cudaGetDeviceCount( &count );
printf("This machine has %d CUDA devices availiable for harvesting \n\n", count);
for (int i=0; i< count; i++) {
cudaGetDeviceProperties( &prop, i );
printf( " --- General Information 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( "Disabled\n");
printf( "Kernel execution timeout : " );
if (prop.kernelExecTimeoutEnabled)
printf( "Enabled\n" );
else
printf( "Disabled\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" );
}
}
代码取自Cuda by Example（并稍作修改）。这个对我有用。当您尝试编译时会收到哪些错误消息？
【讨论】：