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.
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 core/cuda.hpp.
Member Enumeration Documentation
| enum ComputeMode |
- Enumerator:
Definition at line 705 of file core/cuda.hpp.
Constructor & Destructor Documentation
| DeviceInfo | ( | ) |
creates DeviceInfo object for the current GPU
| DeviceInfo | ( | int | device_id ) |
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
| 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
| 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
| bool integrated | ( | ) | const |
device is integrated as opposed to discrete
| 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 .
| 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.
- 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
| 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
| bool unifiedAddressing | ( | ) | const |
device shares a unified address space with the host
| int warpSize | ( | ) | const |
warp size in threads
Generated on Tue Jul 12 2022 16:42:44 by
1.7.2