~/samples/NVIDIA_CUDA-9.1_Samples/1_Utilities/deviceQuery$ make
/usr/local/cuda-9.1/bin/nvcc -ccbin g++ -I../../common/inc -m64 -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_70,code=compute_70 -o deviceQuery.o -c deviceQuery.cpp
/usr/local/cuda-9.1/bin/nvcc -ccbin g++ -m64 -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_37,code=sm_37 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_70,code=compute_70 -o deviceQuery deviceQuery.o
mkdir -p ../../bin/x86_64/linux/release
cp deviceQuery ../../bin/x86_64/linux/release
~/samples/NVIDIA_CUDA-9.1_Samples/1_Utilities/deviceQuery$ ls
deviceQuery deviceQuery.cpp deviceQuery.o Makefile NsightEclipse.xml readme.txt
~/samples/NVIDIA_CUDA-9.1_Samples/1_Utilities/deviceQuery$ ./deviceQuery
./deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 1 CUDA Capable device(s)
Device 0: "GeForce GTX 1050"
CUDA Driver Version / Runtime Version 10.1 / 9.1
CUDA Capability Major/Minor version number: 6.1
Total amount of global memory: 1998 MBytes (2095382528 bytes)
( 5) Multiprocessors, (128) CUDA Cores/MP: 640 CUDA Cores
GPU Max Clock rate: 1455 MHz (1.46 GHz)
Memory Clock rate: 3504 Mhz
Memory Bus Width: 128-bit
L2 Cache Size: 1048576 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 2 copy engine(s)
Run time limit on kernels: No
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
Device supports Unified Addressing (UVA): Yes
Supports Cooperative Kernel Launch: Yes
Supports MultiDevice Co-op Kernel Launch: Yes
Device PCI Domain ID / Bus ID / location ID: 0 / 2 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 10.1, CUDA Runtime Version = 9.1, NumDevs = 1
Result = PASS
~/samples/NVIDIA_CUDA-9.1_Samples/1_Utilities/deviceQuery$ cat deviceQuery.cpp
/*
* Copyright 1993-2015 NVIDIA Corporation. All rights reserved.
*
* Please refer to the NVIDIA end user license agreement (EULA) associated
* with this source code for terms and conditions that govern your use of
* this software. Any use, reproduction, disclosure, or distribution of
* this software and related documentation outside the terms of the EULA
* is strictly prohibited.
*
*/
/* This sample queries the properties of the CUDA devices present in the system via CUDA Runtime API. */
// Shared Utilities (QA Testing)
// std::system includes
#include <memory>
#include <iostream>
#include <cuda_runtime.h>
#include <helper_cuda.h>
int *pArgc = NULL;
char **pArgv = NULL;
#if CUDART_VERSION < 5000
// CUDA-C includes
#include <cuda.h>
// This function wraps the CUDA Driver API into a template function
template <class T>
inline void getCudaAttribute(T *attribute, CUdevice_attribute device_attribute, int device)
{
CUresult error = cuDeviceGetAttribute(attribute, device_attribute, device);
if (CUDA_SUCCESS != error)
{
fprintf(stderr, "cuSafeCallNoSync() Driver API error = %04d from file <%s>, line %i.\n",
error, __FILE__, __LINE__);
exit(EXIT_FAILURE);
}
}
#endif /* CUDART_VERSION < 5000 */
////////////////////////////////////////////////////////////////////////////////
// Program main
////////////////////////////////////////////////////////////////////////////////
int
main(int argc, char **argv)
{
pArgc = &argc;
pArgv = argv;
printf("%s Starting...\n\n", argv[0]);
printf(" CUDA Device Query (Runtime API) version (CUDART static linking)\n\n");
int deviceCount = 0;
cudaError_t error_id = cudaGetDeviceCount(&deviceCount);
if (error_id != cudaSuccess)
{
printf("cudaGetDeviceCount returned %d\n-> %s\n", (int)error_id, cudaGetErrorString(error_id));
printf("Result = FAIL\n");
exit(EXIT_FAILURE);
}
// This function call returns 0 if there are no CUDA capable devices.
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, driverVersion = 0, runtimeVersion = 0;
for (dev = 0; dev < deviceCount; ++dev)
{
cudaSetDevice(dev);
cudaDeviceProp deviceProp;
cudaGetDeviceProperties(&deviceProp, dev);
printf("\nDevice %d: \"%s\"\n", dev, deviceProp.name);
// Console log
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);
char msg[256];
SPRINTF(msg, " Total amount of global memory: %.0f MBytes (%llu bytes)\n",
(float)deviceProp.totalGlobalMem/1048576.0f, (unsigned long long) deviceProp.totalGlobalMem);
printf("%s", msg);
printf(" (%2d) Multiprocessors, (%3d) CUDA Cores/MP: %d CUDA Cores\n",
deviceProp.multiProcessorCount,
_ConvertSMVer2Cores(deviceProp.major, deviceProp.minor),
_ConvertSMVer2Cores(deviceProp.major, deviceProp.minor) * deviceProp.multiProcessorCount);
printf(" GPU Max Clock rate: %.0f MHz (%0.2f GHz)\n", deviceProp.clockRate * 1e-3f, deviceProp.clockRate * 1e-6f);
#if CUDART_VERSION >= 5000
// This is supported in CUDA 5.0 (runtime API device properties)
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);
}
#else
// This only available in CUDA 4.0-4.2 (but these were only exposed in the CUDA Driver API)
int memoryClock;
getCudaAttribute<int>(&memoryClock, CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE, dev);
printf(" Memory Clock rate: %.0f Mhz\n", memoryClock * 1e-3f);
int memBusWidth;
getCudaAttribute<int>(&memBusWidth, CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH, dev);
printf(" Memory Bus Width: %d-bit\n", memBusWidth);
int L2CacheSize;
getCudaAttribute<int>(&L2CacheSize, CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE, dev);
if (L2CacheSize)
{
printf(" L2 Cache Size: %d bytes\n", L2CacheSize);
}
#endif
printf(" Maximum 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(" Maximum Layered 1D Texture Size, (num) layers 1D=(%d), %d layers\n",
deviceProp.maxTexture1DLayered[0], deviceProp.maxTexture1DLayered[1]);
printf(" Maximum Layered 2D Texture Size, (num) layers 2D=(%d, %d), %d layers\n",
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(" Max dimension size of a thread block (x,y,z): (%d, %d, %d)\n",
deviceProp.maxThreadsDim[0],
deviceProp.maxThreadsDim[1],
deviceProp.maxThreadsDim[2]);
printf(" Max dimension size of a grid size (x,y,z): (%d, %d, %d)\n",
deviceProp.maxGridSize[0],
deviceProp.maxGridSize[1],
deviceProp.maxGridSize[2]);
printf(" Maximum memory pitch: %lu bytes\n", deviceProp.memPitch);
printf(" Texture alignment: %lu bytes\n", deviceProp.textureAlignment);
printf(" Concurrent copy and kernel execution: %s with %d copy engine(s)\n", (deviceProp.deviceOverlap ? "Yes" : "No"), deviceProp.asyncEngineCount);
printf(" Run time limit on kernels: %s\n", deviceProp.kernelExecTimeoutEnabled ? "Yes" : "No");
printf(" Integrated GPU sharing Host Memory: %s\n", deviceProp.integrated ? "Yes" : "No");
printf(" Support host page-locked memory mapping: %s\n", deviceProp.canMapHostMemory ? "Yes" : "No");
printf(" Alignment requirement for Surfaces: %s\n", deviceProp.surfaceAlignment ? "Yes" : "No");
printf(" Device has ECC support: %s\n", deviceProp.ECCEnabled ? "Enabled" : "Disabled");
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
printf(" CUDA Device Driver Mode (TCC or WDDM): %s\n", deviceProp.tccDriver ? "TCC (Tesla Compute Cluster Driver)" : "WDDM (Windows Display Driver Model)");
#endif
printf(" Device supports Unified Addressing (UVA): %s\n", deviceProp.unifiedAddressing ? "Yes" : "No");
printf(" Supports Cooperative Kernel Launch: %s\n", deviceProp.cooperativeLaunch ? "Yes" : "No");
printf(" Supports MultiDevice Co-op Kernel Launch: %s\n", deviceProp.cooperativeMultiDeviceLaunch ? "Yes" : "No");
printf(" Device PCI Domain ID / Bus ID / location ID: %d / %d / %d\n", deviceProp.pciDomainID, deviceProp.pciBusID, deviceProp.pciDeviceID);
const char *sComputeMode[] =
{
"Default (multiple host threads can use ::cudaSetDevice() with device simultaneously)",
"Exclusive (only one host thread in one process is able to use ::cudaSetDevice() with this device)",
"Prohibited (no host thread can use ::cudaSetDevice() with this device)",
"Exclusive Process (many threads in one process is able to use ::cudaSetDevice() with this device)",
"Unknown",
NULL
};
printf(" Compute Mode:\n");
printf(" < %s >\n", sComputeMode[deviceProp.computeMode]);
}
// If there are 2 or more GPUs, query to determine whether RDMA is supported
if (deviceCount >= 2)
{
cudaDeviceProp prop[64];
int gpuid[64]; // we want to find the first two GPUs that can support P2P
int gpu_p2p_count = 0;
for (int i=0; i < deviceCount; i++)
{
checkCudaErrors(cudaGetDeviceProperties(&prop[i], i));
// Only boards based on Fermi or later can support P2P
if ((prop[i].major >= 2)
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
// on Windows (64-bit), the Tesla Compute Cluster driver for windows must be enabled to support this
&& prop[i].tccDriver
#endif
)
{
// This is an array of P2P capable GPUs
gpuid[gpu_p2p_count++] = i;
}
}
// Show all the combinations of support P2P GPUs
int can_access_peer;
if (gpu_p2p_count >= 2)
{
for (int i = 0; i < gpu_p2p_count; i++)
{
for (int j = 0; j < gpu_p2p_count; j++)
{
if (gpuid[i] == gpuid[j])
{
continue;
}
checkCudaErrors(cudaDeviceCanAccessPeer(&can_access_peer, gpuid[i], gpuid[j]));
printf("> Peer access from %s (GPU%d) -> %s (GPU%d) : %s\n", prop[gpuid[i]].name, gpuid[i],
prop[gpuid[j]].name, gpuid[j] ,
can_access_peer ? "Yes" : "No");
}
}
}
}
// csv masterlog info
// *****************************
// exe and CUDA driver name
printf("\n");
std::string sProfileString = "deviceQuery, CUDA Driver = CUDART";
char cTemp[16];
// driver version
sProfileString += ", CUDA Driver Version = ";
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
sprintf_s(cTemp, 10, "%d.%d", driverVersion/1000, (driverVersion%100)/10);
#else
sprintf(cTemp, "%d.%d", driverVersion/1000, (driverVersion%100)/10);
#endif
sProfileString += cTemp;
// Runtime version
sProfileString += ", CUDA Runtime Version = ";
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
sprintf_s(cTemp, 10, "%d.%d", runtimeVersion/1000, (runtimeVersion%100)/10);
#else
sprintf(cTemp, "%d.%d", runtimeVersion/1000, (runtimeVersion%100)/10);
#endif
sProfileString += cTemp;
// Device count
sProfileString += ", NumDevs = ";
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
sprintf_s(cTemp, 10, "%d", deviceCount);
#else
sprintf(cTemp, "%d", deviceCount);
#endif
sProfileString += cTemp;
sProfileString += "\n";
printf("%s", sProfileString.c_str());
printf("Result = PASS\n");
// finish
exit(EXIT_SUCCESS);
}
