查看自己GPU参数

0.引言

了解自己的GPU参数很重要.

1.Detect

在sample里面编译deviceQuery查看。CMakeLists.txt添加(/usr/local/cuda-10.1/samples/common/inc/)不然有些头文件无法找到.

CMakeLists.txt

cmake_minimum_required(VERSION 2.8)
project(deviceQuery)

# packages
find_package(CUDA REQUIRED)
if(${CUDA_FOUND})
	set(CUDA_SOURCE_PROPERTY_FORMAT OBJ)
	set(CUDA_SEPARABLE_COMPILATION ON)
	include_directories(${CUDA_INCLUDE_DIRS})
	set(CUDA_PROPAGATE_HOST_FLAGS OFF)
	set(CUDA_NVCC_FLAGS -arch=sm_61;-O3;-G;-g;-std=c++11)#根据具体GPU性能更改算力参数
	#SET(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS};-gencode arch=compute_61,code=sm_61;-std=c++11;-O3;-G;-g)
	link_directories($ENV{CUDA_PATH}/lib/x64)
else(${CUDA_FOUND})
	MESSAGE(STATUS "cuda not found!")
endif(${CUDA_FOUND})

find_package(OpenCV REQUIRED)
include_directories(${OpenCV_INCLUDE_DIRS}
/usr/local/cuda-10.1/samples/common/inc/)#主要就是添加这一句

file(GLOB_RECURSE CURRENT_HEADERS  *.h *.hpp *.cuh)
file(GLOB CURRENT_SOURCES  *.cpp *.cu)
set_source_files_properties(deviceQuery.cpp PROPERTIES CUDA_SOURCE_PROPERTY_FORMAT OBJ)
source_group("Include" FILES ${CURRENT_HEADERS})
source_group("Source" FILES ${CURRENT_SOURCES})

cuda_add_executable(deviceQuery  ${CURRENT_HEADERS} ${CURRENT_SOURCES} )
target_link_libraries(deviceQuery ${OpenCV_LIBS})

2.result

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 / 10.1
  CUDA Capability Major/Minor version number:    6.1
  Total amount of global memory:                 1992 MBytes (2089025536 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:                     Yes
  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
  Device supports Compute Preemption:            Yes
  Supports Cooperative Kernel Launch:            Yes
  Supports MultiDevice Co-op Kernel Launch:      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 7 / 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 = 10.1, NumDevs = 1
Result = PASS