Renesas GR-PEACH OpenCV Development / gr-peach-opencv-project-sd-card_update

Important changes to repositories hosted on mbed.com

Mbed hosted mercurial repositories are deprecated and are due to be permanently deleted in July 2026.

To keep a copy of this software download the repository Zip archive or clone locally using Mercurial.

It is also possible to export all your personal repositories from the account settings page.

Fork of gr-peach-opencv-project-sd-card by the do

Embed: (wiki syntax)

« Back to documentation index

DeviceInfo Class Reference
Public Types | Public Member Functions

DeviceInfo Class Reference
[Initalization and Information]

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

#include <cuda.hpp>

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

Detailed Description

Class providing functionality for querying the specified GPU properties.

Definition at line 629 of file cuda.hpp.

Member Enumeration Documentation

enum 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)

Definition at line 705 of file cuda.hpp.

Constructor & Destructor Documentation

DeviceInfo (  )

creates DeviceInfo object for the current GPU

DeviceInfo ( int  device_id )

The constructors.

Parameters:
device_idSystem 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

int asyncEngineCount (  ) const

number of asynchronous engines

Definition at line 826 of file cuda_info.cpp.

bool canMapHostMemory (  ) const

device can map host memory with cudaHostAlloc/cudaHostGetDevicePointer

Definition at line 528 of file cuda_info.cpp.

int clockRate (  ) const

clock frequency in kilohertz

Definition at line 438 of file cuda_info.cpp.

DeviceInfo::ComputeMode computeMode (  ) const

compute mode

Definition at line 538 of file cuda_info.cpp.

bool concurrentKernels (  ) const

device can possibly execute multiple kernels concurrently

Definition at line 766 of file cuda_info.cpp.

int deviceID (  ) const

Returns system index of the CUDA device starting with 0.

bool ECCEnabled (  ) const

device has ECC support enabled

Definition at line 776 of file cuda_info.cpp.

bool integrated (  ) const

device is integrated as opposed to discrete

Definition at line 518 of file cuda_info.cpp.

bool isCompatible (  ) const

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 .

Definition at line 904 of file cuda_info.cpp.

bool kernelExecTimeoutEnabled (  ) const

specified whether there is a run time limit on kernels

Definition at line 508 of file cuda_info.cpp.

int l2CacheSize (  ) const

size of L2 cache in bytes

Definition at line 866 of file cuda_info.cpp.

int majorVersion (  ) const

major compute capability

Definition at line 458 of file cuda_info.cpp.

Vec3i maxGridSize (  ) const

maximum size of each dimension of a grid

Definition at line 428 of file cuda_info.cpp.

int maxSurface1D (  ) const

maximum 1D surface size

Definition at line 686 of file cuda_info.cpp.

Vec2i maxSurface1DLayered (  ) const

maximum 1D layered surface dimensions

Definition at line 716 of file cuda_info.cpp.

Vec2i maxSurface2D (  ) const

maximum 2D surface dimensions

Definition at line 696 of file cuda_info.cpp.

Vec3i maxSurface2DLayered (  ) const

maximum 2D layered surface dimensions

Definition at line 726 of file cuda_info.cpp.

Vec3i maxSurface3D (  ) const

maximum 3D surface dimensions

Definition at line 706 of file cuda_info.cpp.

int maxSurfaceCubemap (  ) const

maximum Cubemap surface dimensions

Definition at line 736 of file cuda_info.cpp.

Vec2i maxSurfaceCubemapLayered (  ) const

maximum Cubemap layered surface dimensions

Definition at line 746 of file cuda_info.cpp.

int maxTexture1D (  ) const

maximum 1D texture size

Definition at line 556 of file cuda_info.cpp.

Vec2i maxTexture1DLayered (  ) const

maximum 1D layered texture dimensions

Definition at line 656 of file cuda_info.cpp.

int maxTexture1DLinear (  ) const

maximum size for 1D textures bound to linear memory

Definition at line 581 of file cuda_info.cpp.

int maxTexture1DMipmap (  ) const

maximum 1D mipmapped texture size

Definition at line 566 of file cuda_info.cpp.

Vec2i maxTexture2D (  ) const

maximum 2D texture dimensions

Definition at line 591 of file cuda_info.cpp.

Vec2i maxTexture2DGather (  ) const

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

Definition at line 626 of file cuda_info.cpp.

Vec3i maxTexture2DLayered (  ) const

maximum 2D layered texture dimensions

Definition at line 666 of file cuda_info.cpp.

Vec3i maxTexture2DLinear (  ) const

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

Definition at line 616 of file cuda_info.cpp.

Vec2i maxTexture2DMipmap (  ) const

maximum 2D mipmapped texture dimensions

Definition at line 601 of file cuda_info.cpp.

Vec3i maxTexture3D (  ) const

maximum 3D texture dimensions

Definition at line 636 of file cuda_info.cpp.

int maxTextureCubemap (  ) const

maximum Cubemap texture dimensions

Definition at line 646 of file cuda_info.cpp.

Vec2i maxTextureCubemapLayered (  ) const

maximum Cubemap layered texture dimensions

Definition at line 676 of file cuda_info.cpp.

Vec3i maxThreadsDim (  ) const

maximum size of each dimension of a block

Definition at line 418 of file cuda_info.cpp.

int maxThreadsPerBlock (  ) const

maximum number of threads per block

Definition at line 408 of file cuda_info.cpp.

int maxThreadsPerMultiProcessor (  ) const

maximum resident threads per multiprocessor

Definition at line 876 of file cuda_info.cpp.

int memoryBusWidth (  ) const

global memory bus width in bits

Definition at line 856 of file cuda_info.cpp.

int memoryClockRate (  ) const

peak memory clock frequency in kilohertz

Definition at line 846 of file cuda_info.cpp.

size_t memPitch (  ) const

maximum pitch in bytes allowed by memory copies

Definition at line 398 of file cuda_info.cpp.

int minorVersion (  ) const

minor compute capability

Definition at line 468 of file cuda_info.cpp.

int multiProcessorCount (  ) const

number of multiprocessors on device

Definition at line 498 of file cuda_info.cpp.

const char * name (  ) const

ASCII string identifying device.

Definition at line 348 of file cuda_info.cpp.

int pciBusID (  ) const

PCI bus ID of the device.

Definition at line 786 of file cuda_info.cpp.

int pciDeviceID (  ) const

PCI device ID of the device.

Definition at line 796 of file cuda_info.cpp.

int pciDomainID (  ) const

PCI domain ID of the device.

Definition at line 806 of file cuda_info.cpp.

void queryMemory ( size_t &  totalMemory,
size_t &  freeMemory 
) const

gets free and total device memory

Definition at line 886 of file cuda_info.cpp.

int regsPerBlock (  ) const

32-bit registers available per block

Definition at line 378 of file cuda_info.cpp.

size_t sharedMemPerBlock (  ) const

shared memory available per block in bytes

Definition at line 368 of file cuda_info.cpp.

bool supports ( FeatureSet  feature_set ) const

Provides information on CUDA feature support.

Parameters:
feature_setFeatures to be checked. See cuda::FeatureSet.

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

size_t surfaceAlignment (  ) const

alignment requirements for surfaces

Definition at line 756 of file cuda_info.cpp.

bool tccDriver (  ) const

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

Definition at line 816 of file cuda_info.cpp.

size_t textureAlignment (  ) const

alignment requirement for textures

Definition at line 478 of file cuda_info.cpp.

size_t texturePitchAlignment (  ) const

pitch alignment requirement for texture references bound to pitched memory

Definition at line 488 of file cuda_info.cpp.

size_t totalConstMem (  ) const

constant memory available on device in bytes

Definition at line 448 of file cuda_info.cpp.

size_t totalGlobalMem (  ) const

global memory available on device in bytes

Definition at line 358 of file cuda_info.cpp.

bool unifiedAddressing (  ) const

device shares a unified address space with the host

Definition at line 836 of file cuda_info.cpp.

int warpSize (  ) const

warp size in threads

Definition at line 388 of file cuda_info.cpp.

Generated on Tue Jul 12 2022 14:48:02 by  doxygen 1.7.2