CUDA 运行时GPU信息查询

cuda 官网文档名：CUDA_Runtime_API

运行时API查询GPU信息

调用

cudaDeviceProp prop;

cudaGetDeviceProperties(&prop, device_id)

定义

由此可见，只能在主机上调用。

#include <cuda_runtime.h>

#include <iostream>
#include <stdio.h>

static void CheckCudaErrorAux(const char*, unsigned, const char*, cudaError_t);
#define CUDA_CHECK_RETURN(value) CheckCudaErrorAux(__FILE__,__LINE__, #value, value)


int main()
{
	int iDeviceId = 0;
	CUDA_CHECK_RETURN(cudaGetDevice(&iDeviceId));

	cudaDeviceProp prop;
	cudaGetDeviceProperties(&prop, iDeviceId);
	std::cout << "device_id :                                      " << iDeviceId << std::endl;
	std::cout << "device_name :                                    " << prop.name << std::endl;
	std::cout << "compute capability :                             " << prop.major << "." << prop.minor << std::endl;
	std::cout << "amount of global memory :                        " << prop.totalGlobalMem / (1024.0*1024*1024)<<"GB" << std::endl;
	std::cout << "amount of constant memory  :                     " << prop.totalConstMem / 1024.0 << "KB" << std::endl;
	std::cout << "maximum grid size :                              " << prop.maxGridSize[0] <<"," << prop.maxGridSize[1] << "," << prop.maxGridSize[2] << std::endl;
	std::cout << "maximum block size :                             " << prop.maxThreadsDim[0] << "," << prop.maxThreadsDim[1] << "," << prop.maxThreadsDim[2] << std::endl;
	std::cout << "number of SMs :                                  " << prop.multiProcessorCount << std::endl;
	std::cout << "maximum amount of shared memory per block :      " << prop.sharedMemPerBlock / 1024.0 << "KB" << std::endl;
	std::cout << "maximum amount of shared memory per SM :         " << prop.sharedMemPerMultiprocessor / 1024.0 << "KB" << std::endl;
	std::cout << "maximum number of registers per block :          " << prop.regsPerBlock / 1024.0 << "K" << std::endl;
	std::cout << "maximum number of registers per SM :             " << prop.regsPerMultiprocessor / 1024.0 << "K" << std::endl;
	std::cout << "maximum number of thread per block :             " << prop.maxThreadsPerBlock << std::endl;
	std::cout << "maximum number of thread per SM :                " << prop.maxThreadsPerMultiProcessor << std::endl;

	return 0;
}

static void CheckCudaErrorAux(const char* file, unsigned line, const char* statement, cudaError_t err)
{
	if (err == cudaSuccess)
		return;
	std::cerr << statement << " returned: " << cudaGetErrorName(err) << "  \t : " << cudaGetErrorString(err) << "(" << err << ") at " << file << ":" << line << std::endl;
	exit(1);
}

结果

查询GPU计算核心数量

#include "cuda_runtime_api.h"
#include <stdio.h>
#include <iostream>

static void CheckCudaErrorAux(const char*, unsigned, const char*, cudaError_t);
#define CUDA_CHECK_RETURN(value) CheckCudaErrorAux(__FILE__,__LINE__, #value, value)

int getSPcores(cudaDeviceProp devProp)
{
	int cores = 0;
	int mp = devProp.multiProcessorCount;
	switch (devProp.major) {
	case 2: // Fermi
		if (devProp.minor == 1) cores = mp * 48;
		else cores = mp * 32;
		break;
	case 3: // Kepler
		cores = mp * 192;
		break;
	case 5: // Maxwell
		cores = mp * 128;
		break;
	case 6: // Pascal
		if ((devProp.minor == 1) || (devProp.minor == 2)) cores = mp * 128;
		else if (devProp.minor == 0) cores = mp * 64;
		else printf("Unknown device type\n");
		break;
	case 7: // Volta and Turing
		if ((devProp.minor == 0) || (devProp.minor == 5)) cores = mp * 64;
		else printf("Unknown device type\n");
		break;
	case 8: // Ampere
		if (devProp.minor == 0) cores = mp * 64;
		else if (devProp.minor == 6) cores = mp * 128;
		else if (devProp.minor == 9) cores = mp * 128; // ada lovelace
		else printf("Unknown device type\n");
		break;
	case 9: // Hopper
		if (devProp.minor == 0) cores = mp * 128;
		else printf("Unknown device type\n");
		break;
	default:
		printf("Unknown device type\n");
		break;
	}
	return cores;
}

int main()
{
	int iDeviceId = 0;
	CUDA_CHECK_RETURN(cudaGetDevice(&iDeviceId));
	cudaDeviceProp prop;
	CUDA_CHECK_RETURN(cudaGetDeviceProperties(&prop, iDeviceId));

	std::cout << "Compute cores is " << getSPcores(prop) << std::endl;
	return 0;
}

static void CheckCudaErrorAux(const char* file, unsigned line, const char* statement, cudaError_t err)
{
	if (err == cudaSuccess)
		return;
	std::cerr << statement << " returned: " << cudaGetErrorName(err) << "  \t : " << cudaGetErrorString(err) << "(" << err << ") at " << file << ":" << line << std::endl;
	exit(1);
}