cv::cuda::DeviceInfo Class Reference

Class providing functionality for querying the specified GPU properties. More...

#include <opencv2/core/cuda.hpp>

Collaboration diagram for cv::cuda::DeviceInfo:

Public Types
enum	ComputeMode {   ComputeModeDefault ,   ComputeModeExclusive ,   ComputeModeProhibited ,   ComputeModeExclusiveProcess }

Public Member Functions
	DeviceInfo ()
	creates DeviceInfo object for the current GPU
	DeviceInfo (int device_id)
	The constructors.
int	asyncEngineCount () const
	number of asynchronous engines
bool	canMapHostMemory () const
	device can map host memory with cudaHostAlloc/cudaHostGetDevicePointer
int	clockRate () const
	clock frequency in kilohertz
DeviceInfo::ComputeMode	computeMode () const
	compute mode
bool	concurrentKernels () const
	device can possibly execute multiple kernels concurrently
int	deviceID () const
	Returns system index of the CUDA device starting with 0.
bool	ECCEnabled () const
	device has ECC support enabled
size_t	freeMemory () const
bool	integrated () const
	device is integrated as opposed to discrete
bool	isCompatible () const
	Checks the CUDA module and device compatibility.
bool	kernelExecTimeoutEnabled () const
	specified whether there is a run time limit on kernels
int	l2CacheSize () const
	size of L2 cache in bytes
int	majorVersion () const
	major compute capability
Vec3i	maxGridSize () const
	maximum size of each dimension of a grid
int	maxSurface1D () const
	maximum 1D surface size
Vec2i	maxSurface1DLayered () const
	maximum 1D layered surface dimensions
Vec2i	maxSurface2D () const
	maximum 2D surface dimensions
Vec3i	maxSurface2DLayered () const
	maximum 2D layered surface dimensions
Vec3i	maxSurface3D () const
	maximum 3D surface dimensions
int	maxSurfaceCubemap () const
	maximum Cubemap surface dimensions
Vec2i	maxSurfaceCubemapLayered () const
	maximum Cubemap layered surface dimensions
int	maxTexture1D () const
	maximum 1D texture size
Vec2i	maxTexture1DLayered () const
	maximum 1D layered texture dimensions
int	maxTexture1DLinear () const
	maximum size for 1D textures bound to linear memory
int	maxTexture1DMipmap () const
	maximum 1D mipmapped texture size
Vec2i	maxTexture2D () const
	maximum 2D texture dimensions
Vec2i	maxTexture2DGather () const
	maximum 2D texture dimensions if texture gather operations have to be performed
Vec3i	maxTexture2DLayered () const
	maximum 2D layered texture dimensions
Vec3i	maxTexture2DLinear () const
	maximum dimensions (width, height, pitch) for 2D textures bound to pitched memory
Vec2i	maxTexture2DMipmap () const
	maximum 2D mipmapped texture dimensions
Vec3i	maxTexture3D () const
	maximum 3D texture dimensions
int	maxTextureCubemap () const
	maximum Cubemap texture dimensions
Vec2i	maxTextureCubemapLayered () const
	maximum Cubemap layered texture dimensions
Vec3i	maxThreadsDim () const
	maximum size of each dimension of a block
int	maxThreadsPerBlock () const
	maximum number of threads per block
int	maxThreadsPerMultiProcessor () const
	maximum resident threads per multiprocessor
int	memoryBusWidth () const
	global memory bus width in bits
int	memoryClockRate () const
	peak memory clock frequency in kilohertz
size_t	memPitch () const
	maximum pitch in bytes allowed by memory copies
int	minorVersion () const
	minor compute capability
int	multiProcessorCount () const
	number of multiprocessors on device
const char *	name () const
	ASCII string identifying device.
int	pciBusID () const
	PCI bus ID of the device.
int	pciDeviceID () const
	PCI device ID of the device.
int	pciDomainID () const
	PCI domain ID of the device.
void	queryMemory (size_t &totalMemory, size_t &freeMemory) const
	gets free and total device memory
int	regsPerBlock () const
	32-bit registers available per block
size_t	sharedMemPerBlock () const
	shared memory available per block in bytes
bool	supports (FeatureSet feature_set) const
	Provides information on CUDA feature support.
size_t	surfaceAlignment () const
	alignment requirements for surfaces
bool	tccDriver () const
	true if device is a Tesla device using TCC driver, false otherwise
size_t	textureAlignment () const
	alignment requirement for textures
size_t	texturePitchAlignment () const
	pitch alignment requirement for texture references bound to pitched memory
size_t	totalConstMem () const
	constant memory available on device in bytes
size_t	totalGlobalMem () const
	global memory available on device in bytes
size_t	totalMemory () const
bool	unifiedAddressing () const
	device shares a unified address space with the host
int	warpSize () const
	warp size in threads

Detailed Description

Class providing functionality for querying the specified GPU properties.

Member Enumeration Documentation

ComputeMode

enum cv::cuda::DeviceInfo::ComputeMode

Enumerator
ComputeModeDefault	default compute mode (Multiple threads can use cudaSetDevice with this device)
ComputeModeExclusive	compute-exclusive-thread mode (Only one thread in one process will be able to use cudaSetDevice with this device)
ComputeModeProhibited	compute-prohibited mode (No threads can use cudaSetDevice with this device)
ComputeModeExclusiveProcess	compute-exclusive-process mode (Many threads in one process will be able to use cudaSetDevice with this device)

Constructor & Destructor Documentation

DeviceInfo() [1/2]

cv::cuda::DeviceInfo::DeviceInfo

(

)

Python:
	cv.cuda.DeviceInfo(		) ->	<cuda_DeviceInfo object>
	cv.cuda.DeviceInfo(	device_id	) ->	<cuda_DeviceInfo object>

creates DeviceInfo object for the current GPU

DeviceInfo() [2/2]

cv::cuda::DeviceInfo::DeviceInfo

(

int

device_id

)

Python:
	cv.cuda.DeviceInfo(		) ->	<cuda_DeviceInfo object>
	cv.cuda.DeviceInfo(	device_id	) ->	<cuda_DeviceInfo object>

The constructors.

Parameters

device_id

System index of the CUDA device starting with 0.

Constructs the DeviceInfo object for the specified device. If device_id parameter is missed, it constructs an object for the current device.

Member Function Documentation

asyncEngineCount()

int cv::cuda::DeviceInfo::asyncEngineCount

(

)

const

Python:
	cv.cuda.DeviceInfo.asyncEngineCount(		) ->	retval

number of asynchronous engines

canMapHostMemory()

bool cv::cuda::DeviceInfo::canMapHostMemory

(

)

const

Python:
	cv.cuda.DeviceInfo.canMapHostMemory(		) ->	retval

device can map host memory with cudaHostAlloc/cudaHostGetDevicePointer

clockRate()

int cv::cuda::DeviceInfo::clockRate

(

)

const

Python:
	cv.cuda.DeviceInfo.clockRate(		) ->	retval

clock frequency in kilohertz

computeMode()

DeviceInfo::ComputeMode cv::cuda::DeviceInfo::computeMode

(

)

const

Python:
	cv.cuda.DeviceInfo.computeMode(		) ->	retval

compute mode

concurrentKernels()

bool cv::cuda::DeviceInfo::concurrentKernels

(

)

const

Python:
	cv.cuda.DeviceInfo.concurrentKernels(		) ->	retval

device can possibly execute multiple kernels concurrently

deviceID()

int cv::cuda::DeviceInfo::deviceID

(

)

const

Python:
	cv.cuda.DeviceInfo.deviceID(		) ->	retval

Returns system index of the CUDA device starting with 0.

ECCEnabled()

bool cv::cuda::DeviceInfo::ECCEnabled

(

)

const

Python:
	cv.cuda.DeviceInfo.ECCEnabled(		) ->	retval

device has ECC support enabled

freeMemory()

size_t cv::cuda::DeviceInfo::freeMemory

(

)

const

Python:
	cv.cuda.DeviceInfo.freeMemory(		) ->	retval

integrated()

bool cv::cuda::DeviceInfo::integrated

(

)

const

Python:
	cv.cuda.DeviceInfo.integrated(		) ->	retval

device is integrated as opposed to discrete

isCompatible()

bool cv::cuda::DeviceInfo::isCompatible

(

)

const

Python:
	cv.cuda.DeviceInfo.isCompatible(		) ->	retval

Checks the CUDA module and device compatibility.

This function returns true if the CUDA module can be run on the specified device. Otherwise, it returns false .

kernelExecTimeoutEnabled()

bool cv::cuda::DeviceInfo::kernelExecTimeoutEnabled

(

)

const

Python:
	cv.cuda.DeviceInfo.kernelExecTimeoutEnabled(		) ->	retval

specified whether there is a run time limit on kernels

l2CacheSize()

int cv::cuda::DeviceInfo::l2CacheSize

(

)

const

Python:
	cv.cuda.DeviceInfo.l2CacheSize(		) ->	retval

size of L2 cache in bytes

majorVersion()

int cv::cuda::DeviceInfo::majorVersion

(

)

const

Python:
	cv.cuda.DeviceInfo.majorVersion(		) ->	retval

major compute capability

maxGridSize()

Vec3i cv::cuda::DeviceInfo::maxGridSize

(

)

const

Python:
	cv.cuda.DeviceInfo.maxGridSize(		) ->	retval

maximum size of each dimension of a grid

maxSurface1D()

int cv::cuda::DeviceInfo::maxSurface1D

(

)

const

Python:
	cv.cuda.DeviceInfo.maxSurface1D(		) ->	retval

maximum 1D surface size

maxSurface1DLayered()

Vec2i cv::cuda::DeviceInfo::maxSurface1DLayered

(

)

const

Python:
	cv.cuda.DeviceInfo.maxSurface1DLayered(		) ->	retval

maximum 1D layered surface dimensions

maxSurface2D()

Vec2i cv::cuda::DeviceInfo::maxSurface2D

(

)

const

Python:
	cv.cuda.DeviceInfo.maxSurface2D(		) ->	retval

maximum 2D surface dimensions

maxSurface2DLayered()

Vec3i cv::cuda::DeviceInfo::maxSurface2DLayered

(

)

const

Python:
	cv.cuda.DeviceInfo.maxSurface2DLayered(		) ->	retval

maximum 2D layered surface dimensions

maxSurface3D()

Vec3i cv::cuda::DeviceInfo::maxSurface3D

(

)

const

Python:
	cv.cuda.DeviceInfo.maxSurface3D(		) ->	retval

maximum 3D surface dimensions

maxSurfaceCubemap()

int cv::cuda::DeviceInfo::maxSurfaceCubemap

(

)

const

Python:
	cv.cuda.DeviceInfo.maxSurfaceCubemap(		) ->	retval

maximum Cubemap surface dimensions

maxSurfaceCubemapLayered()

Vec2i cv::cuda::DeviceInfo::maxSurfaceCubemapLayered

(

)

const

Python:
	cv.cuda.DeviceInfo.maxSurfaceCubemapLayered(		) ->	retval

maximum Cubemap layered surface dimensions

maxTexture1D()

int cv::cuda::DeviceInfo::maxTexture1D

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTexture1D(		) ->	retval

maximum 1D texture size

maxTexture1DLayered()

Vec2i cv::cuda::DeviceInfo::maxTexture1DLayered

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTexture1DLayered(		) ->	retval

maximum 1D layered texture dimensions

maxTexture1DLinear()

int cv::cuda::DeviceInfo::maxTexture1DLinear

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTexture1DLinear(		) ->	retval

maximum size for 1D textures bound to linear memory

maxTexture1DMipmap()

int cv::cuda::DeviceInfo::maxTexture1DMipmap

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTexture1DMipmap(		) ->	retval

maximum 1D mipmapped texture size

maxTexture2D()

Vec2i cv::cuda::DeviceInfo::maxTexture2D

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTexture2D(		) ->	retval

maximum 2D texture dimensions

maxTexture2DGather()

Vec2i cv::cuda::DeviceInfo::maxTexture2DGather

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTexture2DGather(		) ->	retval

maximum 2D texture dimensions if texture gather operations have to be performed

maxTexture2DLayered()

Vec3i cv::cuda::DeviceInfo::maxTexture2DLayered

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTexture2DLayered(		) ->	retval

maximum 2D layered texture dimensions

maxTexture2DLinear()

Vec3i cv::cuda::DeviceInfo::maxTexture2DLinear

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTexture2DLinear(		) ->	retval

maximum dimensions (width, height, pitch) for 2D textures bound to pitched memory

maxTexture2DMipmap()

Vec2i cv::cuda::DeviceInfo::maxTexture2DMipmap

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTexture2DMipmap(		) ->	retval

maximum 2D mipmapped texture dimensions

maxTexture3D()

Vec3i cv::cuda::DeviceInfo::maxTexture3D

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTexture3D(		) ->	retval

maximum 3D texture dimensions

maxTextureCubemap()

int cv::cuda::DeviceInfo::maxTextureCubemap

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTextureCubemap(		) ->	retval

maximum Cubemap texture dimensions

maxTextureCubemapLayered()

Vec2i cv::cuda::DeviceInfo::maxTextureCubemapLayered

(

)

const

Python:
	cv.cuda.DeviceInfo.maxTextureCubemapLayered(		) ->	retval

maximum Cubemap layered texture dimensions

maxThreadsDim()

Vec3i cv::cuda::DeviceInfo::maxThreadsDim

(

)

const

Python:
	cv.cuda.DeviceInfo.maxThreadsDim(		) ->	retval

maximum size of each dimension of a block

maxThreadsPerBlock()

int cv::cuda::DeviceInfo::maxThreadsPerBlock

(

)

const

Python:
	cv.cuda.DeviceInfo.maxThreadsPerBlock(		) ->	retval

maximum number of threads per block

maxThreadsPerMultiProcessor()

int cv::cuda::DeviceInfo::maxThreadsPerMultiProcessor

(

)

const

Python:
	cv.cuda.DeviceInfo.maxThreadsPerMultiProcessor(		) ->	retval

maximum resident threads per multiprocessor

memoryBusWidth()

int cv::cuda::DeviceInfo::memoryBusWidth

(

)

const

Python:
	cv.cuda.DeviceInfo.memoryBusWidth(		) ->	retval

global memory bus width in bits

memoryClockRate()

int cv::cuda::DeviceInfo::memoryClockRate

(

)

const

Python:
	cv.cuda.DeviceInfo.memoryClockRate(		) ->	retval

peak memory clock frequency in kilohertz

memPitch()

size_t cv::cuda::DeviceInfo::memPitch

(

)

const

Python:
	cv.cuda.DeviceInfo.memPitch(		) ->	retval

maximum pitch in bytes allowed by memory copies

minorVersion()

int cv::cuda::DeviceInfo::minorVersion

(

)

const

Python:
	cv.cuda.DeviceInfo.minorVersion(		) ->	retval

minor compute capability

multiProcessorCount()

int cv::cuda::DeviceInfo::multiProcessorCount

(

)

const

Python:
	cv.cuda.DeviceInfo.multiProcessorCount(		) ->	retval

number of multiprocessors on device

name()

const char * cv::cuda::DeviceInfo::name

(

)

const

ASCII string identifying device.

pciBusID()

int cv::cuda::DeviceInfo::pciBusID

(

)

const

Python:
	cv.cuda.DeviceInfo.pciBusID(		) ->	retval

PCI bus ID of the device.

pciDeviceID()

int cv::cuda::DeviceInfo::pciDeviceID

(

)

const

Python:
	cv.cuda.DeviceInfo.pciDeviceID(		) ->	retval

PCI device ID of the device.

pciDomainID()

int cv::cuda::DeviceInfo::pciDomainID

(

)

const

Python:
	cv.cuda.DeviceInfo.pciDomainID(		) ->	retval

PCI domain ID of the device.

queryMemory()

void cv::cuda::DeviceInfo::queryMemory	(	size_t &	totalMemory,
		size_t &	freeMemory ) const

Python:
	cv.cuda.DeviceInfo.queryMemory(	totalMemory, freeMemory	) ->	None

gets free and total device memory

regsPerBlock()

int cv::cuda::DeviceInfo::regsPerBlock

(

)

const

Python:
	cv.cuda.DeviceInfo.regsPerBlock(		) ->	retval

32-bit registers available per block

sharedMemPerBlock()

size_t cv::cuda::DeviceInfo::sharedMemPerBlock

(

)

const

Python:
	cv.cuda.DeviceInfo.sharedMemPerBlock(		) ->	retval

shared memory available per block in bytes

supports()

bool cv::cuda::DeviceInfo::supports

(

FeatureSet

feature_set

)

const

Provides information on CUDA feature support.

Parameters

feature_set

Features to be checked. See cuda::FeatureSet.

This function returns true if the device has the specified CUDA feature. Otherwise, it returns false

surfaceAlignment()

size_t cv::cuda::DeviceInfo::surfaceAlignment

(

)

const

Python:
	cv.cuda.DeviceInfo.surfaceAlignment(		) ->	retval

alignment requirements for surfaces

tccDriver()

bool cv::cuda::DeviceInfo::tccDriver

(

)

const

Python:
	cv.cuda.DeviceInfo.tccDriver(		) ->	retval

true if device is a Tesla device using TCC driver, false otherwise

textureAlignment()

size_t cv::cuda::DeviceInfo::textureAlignment

(

)

const

Python:
	cv.cuda.DeviceInfo.textureAlignment(		) ->	retval

alignment requirement for textures

texturePitchAlignment()

size_t cv::cuda::DeviceInfo::texturePitchAlignment

(

)

const

Python:
	cv.cuda.DeviceInfo.texturePitchAlignment(		) ->	retval

pitch alignment requirement for texture references bound to pitched memory

totalConstMem()

size_t cv::cuda::DeviceInfo::totalConstMem

(

)

const

Python:
	cv.cuda.DeviceInfo.totalConstMem(		) ->	retval

constant memory available on device in bytes

totalGlobalMem()

size_t cv::cuda::DeviceInfo::totalGlobalMem

(

)

const

Python:
	cv.cuda.DeviceInfo.totalGlobalMem(		) ->	retval

global memory available on device in bytes

totalMemory()

size_t cv::cuda::DeviceInfo::totalMemory

(

)

const

Python:
	cv.cuda.DeviceInfo.totalMemory(		) ->	retval

unifiedAddressing()

bool cv::cuda::DeviceInfo::unifiedAddressing

(

)

const

Python:
	cv.cuda.DeviceInfo.unifiedAddressing(		) ->	retval

device shares a unified address space with the host

warpSize()

int cv::cuda::DeviceInfo::warpSize

(

)

const

Python:
	cv.cuda.DeviceInfo.warpSize(		) ->	retval

warp size in threads

---

The documentation for this class was generated from the following file:

• opencv2/core/cuda.hpp