|cuda| 잡동사니 노트 + 리눅스 활용

- nvvp ./a.out

GUI(NVIDIA Visual Profiler)를 활용해 GPU 커널의 수행시간 분석

- nvcc "~~.cu"

cuda 파일을 컴파일

- nvprof ./a.out

컴파일 된 a.out파일을 nvprof라는 분석 툴을 활용해 수행시간을 세밀하게 분석한다.

이 과정에서 시간을 줄일 수 있는지 다양한 시도를 해보는 것이 중요하다.

- nvprof --print-gpu-trace ./nbody --benchmark -numdevices=2 -i=1

- nvprof --analysis-metrics -o nbody-analysis.nvprof ./nbody --benchmark -numdevices=2 -i=1

https://developer.nvidia.com/blog/cuda-pro-tip-nvprof-your-handy-universal-gpu-profiler/

- cuDriverGetVersion

Returns in *driverVersion the version number of the installed CUDA driver. This function automatically returns CUDA_ERROR_INVALID_VALUE if the driverVersion argument is NULL.

Parameters:

driverVersion

- Returns the CUDA driver version

Returns:

CUDA_SUCCESS, CUDA_ERROR_INVALID_VALUE

Note:

Note that this function may also return error codes from previous, asynchronous launches.

Returns the latest version of CUDA supported by the driver.

- cuInit

Initializes the driver API and must be called before any other function from the driver API. Currently, the Flags parameter must be 0. If cuInit() has not been called, any function from the driver API will return CUDA_ERROR_NOT_INITIALIZED.

Parameters:

Flags

- Initialization flag for CUDA.

Returns:

CUDA_SUCCESS, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_INVALID_DEVICE

Note:

Note that this function may also return error codes from previous, asynchronous launches.

- cuDeviceGet

Returns a handle to a compute device.

Parameters

device

- Returned device handle

ordinal

- Device number to get handle for

- cuDeviceGetName

CUresult cuDeviceGetName ( char* name, int  len, CUdevice dev )

Returns an identifer string for the device.

Parameters

name

- Returned identifier string for the device

len

- Maximum length of string to store in name

dev

- Device to get identifier string for

Returns

CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_CONTEXT, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_INVALID_DEVICE

Description

Returns an ASCII string identifying the device dev in the NULL-terminated string pointed to by name. len specifies the maximum length of the string that may be returned.

Note:

Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuDeviceGetAttribute, cuDeviceGetUuid, cuDeviceGetLuid, cuDeviceGetCount, cuDeviceGet, cuDeviceTotalMem, cudaGetDeviceProperties

- cuDeviceTotalMem_v2

CUresult cuDeviceTotalMem ( size_t* bytes, CUdevice dev )

Returns the total amount of memory on the device.

Parameters

bytes

- Returned memory available on device in bytes

dev

- Device handle

Returns

CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_CONTEXT, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_INVALID_DEVICE

Description

Returns in *bytes the total amount of memory available on the device dev in bytes.

Note:

Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuDeviceGetAttribute, cuDeviceGetCount, cuDeviceGetName, cuDeviceGetUuid, cuDeviceGet, cudaMemGetInfo

- cuDeviceGetAttribute

CUresult cuDeviceGetAttribute ( int* pi, CUdevice_attribute attrib, CUdevice dev )

Returns information about the device.

Parameters

pi

- Returned device attribute value

attrib

- Device attribute to query

dev

- Device handle

Returns

CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_CONTEXT, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_INVALID_DEVICE

Description

Returns in *pi the integer value of the attribute attrib on device dev. The supported attributes are:

• CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK: Maximum number of threads per block;

• CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X: Maximum x-dimension of a block;

• CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y: Maximum y-dimension of a block;

• CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z: Maximum z-dimension of a block;

• CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X: Maximum x-dimension of a grid;

• CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y: Maximum y-dimension of a grid;

• CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z: Maximum z-dimension of a grid;

• CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK: Maximum amount of shared memory available to a thread block in bytes;

• CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY: Memory available on device for __constant__ variables in a CUDA C kernel in bytes;

• CU_DEVICE_ATTRIBUTE_WARP_SIZE: Warp size in threads;

• CU_DEVICE_ATTRIBUTE_MAX_PITCH: Maximum pitch in bytes allowed by the memory copy functions that involve memory regions allocated through cuMemAllocPitch();

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH: Maximum 1D texture width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH: Maximum width for a 1D texture bound to linear memory;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH: Maximum mipmapped 1D texture width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH: Maximum 2D texture width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT: Maximum 2D texture height;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH: Maximum width for a 2D texture bound to linear memory;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT: Maximum height for a 2D texture bound to linear memory;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH: Maximum pitch in bytes for a 2D texture bound to linear memory;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH: Maximum mipmapped 2D texture width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT: Maximum mipmapped 2D texture height;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH: Maximum 3D texture width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT: Maximum 3D texture height;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH: Maximum 3D texture depth;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE: Alternate maximum 3D texture width, 0 if no alternate maximum 3D texture size is supported;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE: Alternate maximum 3D texture height, 0 if no alternate maximum 3D texture size is supported;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE: Alternate maximum 3D texture depth, 0 if no alternate maximum 3D texture size is supported;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH: Maximum cubemap texture width or height;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH: Maximum 1D layered texture width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS: Maximum layers in a 1D layered texture;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH: Maximum 2D layered texture width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT: Maximum 2D layered texture height;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS: Maximum layers in a 2D layered texture;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH: Maximum cubemap layered texture width or height;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS: Maximum layers in a cubemap layered texture;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH: Maximum 1D surface width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH: Maximum 2D surface width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT: Maximum 2D surface height;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH: Maximum 3D surface width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT: Maximum 3D surface height;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH: Maximum 3D surface depth;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH: Maximum 1D layered surface width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS: Maximum layers in a 1D layered surface;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH: Maximum 2D layered surface width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT: Maximum 2D layered surface height;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS: Maximum layers in a 2D layered surface;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH: Maximum cubemap surface width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH: Maximum cubemap layered surface width;

• CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS: Maximum layers in a cubemap layered surface;

• CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK: Maximum number of 32-bit registers available to a thread block;

• CU_DEVICE_ATTRIBUTE_CLOCK_RATE: The typical clock frequency in kilohertz;

• CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT: Alignment requirement; texture base addresses aligned to textureAlign bytes do not need an offset applied to texture fetches;

• CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT: Pitch alignment requirement for 2D texture references bound to pitched memory;

• CU_DEVICE_ATTRIBUTE_GPU_OVERLAP: 1 if the device can concurrently copy memory between host and device while executing a kernel, or 0 if not;

• CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT: Number of multiprocessors on the device;

• CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT: 1 if there is a run time limit for kernels executed on the device, or 0 if not;

• CU_DEVICE_ATTRIBUTE_INTEGRATED: 1 if the device is integrated with the memory subsystem, or 0 if not;

• CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY: 1 if the device can map host memory into the CUDA address space, or 0 if not;

• CU_DEVICE_ATTRIBUTE_COMPUTE_MODE: Compute mode that device is currently in. Available modes are as follows:

  • CU_COMPUTEMODE_DEFAULT: Default mode - Device is not restricted and can have multiple CUDA contexts present at a single time.

  • CU_COMPUTEMODE_PROHIBITED: Compute-prohibited mode - Device is prohibited from creating new CUDA contexts.

  • CU_COMPUTEMODE_EXCLUSIVE_PROCESS: Compute-exclusive-process mode - Device can have only one context used by a single process at a time.

• CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS: 1 if the device supports executing multiple kernels within the same context simultaneously, or 0 if not. It is not guaranteed that multiple kernels will be resident on the device concurrently so this feature should not be relied upon for correctness;

• CU_DEVICE_ATTRIBUTE_ECC_ENABLED: 1 if error correction is enabled on the device, 0 if error correction is disabled or not supported by the device;

• CU_DEVICE_ATTRIBUTE_PCI_BUS_ID: PCI bus identifier of the device;

• CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID: PCI device (also known as slot) identifier of the device;

• CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID: PCI domain identifier of the device

• CU_DEVICE_ATTRIBUTE_TCC_DRIVER: 1 if the device is using a TCC driver. TCC is only available on Tesla hardware running Windows Vista or later;

• CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE: Peak memory clock frequency in kilohertz;

• CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH: Global memory bus width in bits;

• CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE: Size of L2 cache in bytes. 0 if the device doesn't have L2 cache;

• CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR: Maximum resident threads per multiprocessor;

• CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING: 1 if the device shares a unified address space with the host, or 0 if not;

• CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR: Major compute capability version number;

• CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR: Minor compute capability version number;

• CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED: 1 if device supports caching globals in L1 cache, 0 if caching globals in L1 cache is not supported by the device;

• CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED: 1 if device supports caching locals in L1 cache, 0 if caching locals in L1 cache is not supported by the device;

• CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR: Maximum amount of shared memory available to a multiprocessor in bytes; this amount is shared by all thread blocks simultaneously resident on a multiprocessor;

• CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR: Maximum number of 32-bit registers available to a multiprocessor; this number is shared by all thread blocks simultaneously resident on a multiprocessor;

• CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY: 1 if device supports allocating managed memory on this system, 0 if allocating managed memory is not supported by the device on this system.

• CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD: 1 if device is on a multi-GPU board, 0 if not.

• CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID: Unique identifier for a group of devices associated with the same board. Devices on the same multi-GPU board will share the same identifier.

• CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED: 1 if Link between the device and the host supports native atomic operations.

• CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO: Ratio of single precision performance (in floating-point operations per second) to double precision performance.

• CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS: Device suppports coherently accessing pageable memory without calling cudaHostRegister on it.

• CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS: Device can coherently access managed memory concurrently with the CPU.

• CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED: Device supports Compute Preemption.

• CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM: Device can access host registered memory at the same virtual address as the CPU.

• CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN: The maximum per block shared memory size suported on this device. This is the maximum value that can be opted into when using the cuFuncSetAttribute() call. For more details see CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES

• CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES: Device accesses pageable memory via the host's page tables.

• CU_DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST: The host can directly access managed memory on the device without migration.

• CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED: Device supports virtual address management APIs like cuMemAddressReserve, cuMemCreate, cuMemMap and related APIs

• CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED: Device supports exporting memory to a posix file descriptor with cuMemExportToShareableHandle, if requested via cuMemCreate

• CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED: Device supports exporting memory to a Win32 NT handle with cuMemExportToShareableHandle, if requested via cuMemCreate

• CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED: Device supports exporting memory to a Win32 KMT handle with cuMemExportToShareableHandle, if requested cuMemCreate

• CU_DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE: maximum L2 cache size in byte for persisting lines

• CU_DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR: Maximum number of thread blocks that can reside on a multiprocessor.

• CU_DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED: Device supports compressible memory allocation via cuMemCreate

• CU_DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK: Amount of shared memory per block reserved by CUDA driver in bytes.

Note:

Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuDeviceGetCount, cuDeviceGetName, cuDeviceGetUuid, cuDeviceGet, cuDeviceTotalMem, cudaDeviceGetAttribute, cudaGetDeviceProperties

- cuDeviceGetUuid

CUresult cuDeviceGetUuid ( CUuuid* uuid, CUdevice dev )

Return an UUID for the device.

Parameters

uuid

- Returned UUID

dev

- Device to get identifier string for

Returns

CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_INVALID_DEVICE

Description

Returns 16-octets identifing the device dev in the structure pointed by the uuid.

Note:

Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuDeviceGetAttribute, cuDeviceGetCount, cuDeviceGetName, cuDeviceGetLuid, cuDeviceGet, cuDeviceTotalMem, cudaGetDeviceProperties

- cuDeviceGetLuid

CUresult cuDeviceGetLuid ( char* luid, unsigned int* deviceNodeMask, CUdevice dev )

Return an LUID and device node mask for the device.

Parameters

luid

- Returned LUID

deviceNodeMask

- Returned device node mask

dev

- Device to get identifier string for

Returns

CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_INVALID_DEVICE

Description

Return identifying information (luid and deviceNodeMask) to allow matching device with graphics APIs.

Note:

Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuDeviceGetAttribute, cuDeviceGetCount, cuDeviceGetName, cuDeviceGet, cuDeviceTotalMem, cudaGetDeviceProperties

- cuModuleUnload

CUresult cuModuleUnload ( CUmodule hmod )

Unloads a module.

Parameters

hmod

- Module to unload

Returns

CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_CONTEXT, CUDA_ERROR_INVALID_VALUE

Description

Unloads a module hmod from the current context.

Note:

Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuModuleGetFunction, cuModuleGetGlobal, cuModuleGetTexRef, cuModuleLoad, cuModuleLoadData, cuModuleLoadDataEx, cuModuleLoadFatBinary

- cuDevicePrimaryCtxRelease

CUresult cuDevicePrimaryCtxRelease ( CUdevice dev )

Release the primary context on the GPU.

Parameters

dev

- Device which primary context is released

Returns

CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_DEVICE

Description

Releases the primary context interop on the device by decreasing the usage count by 1. If the usage drops to 0 the primary context of device dev will be destroyed regardless of how many threads it is current to.

Please note that unlike cuCtxDestroy() this method does not pop the context from stack in any circumstances.

Note:

Note that this function may also return error codes from previous, asynchronous launches.

See also:

cuDevicePrimaryCtxRetain, cuCtxDestroy, cuCtxGetApiVersion, cuCtxGetCacheConfig, cuCtxGetDevice, cuCtxGetFlags, cuCtxGetLimit, cuCtxPopCurrent, cuCtxPushCurrent, cuCtxSetCacheConfig, cuCtxSetLimit, cuCtxSynchronize

------------------------------------------------

리눅스 활용!

- cd "폴더명"

폴더로 커서 위치가 진입하게 된다.

- tap

현재 입력하는 단어를 통해 만들어 낼 수 있는 파일명을 검색하여 바로 입력으로 결과를 출력!

설명이 어려운데 해보면 바로 느낌이 올 것이다.

visual studio의 tap과 매우매우매우!!! 유사하다.

- cd ..

상위 디렉토리로 이동.

- dir

현재 디렉토리에 포함되어 있는 파일을 확인

- 참조

- cuDriverGetVersion

https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART____VERSION.html

http://developer.download.nvidia.com/compute/cuda/2_3/toolkit/docs/online/group__CUVERSION_gf83e088e9433ce2e9ce87203791dd122.html

- cuInit

http://developer.download.nvidia.com/compute/cuda/2_3/toolkit/docs/online/group__CUINIT_g4703189f4c7f490c73f77942a3fa8443.html

- cuDeviceGet

https://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__DEVICE.html\

- cuDeviceGetName

- cuDeviceTotalMem_v2

- cuDeviceGetAttribute

- cuDeviceGetUuid

- cuDeviceGetLuid

- cuModuleUnload

- cuDevicePrimaryCtxRelease