pyarrow.cuda.Context

class pyarrow.cuda.Context

Bases: pyarrow.lib._Weakrefable

CUDA driver context.

__init__()

Create a CUDA driver context for a particular device.

If a CUDA context handle is passed, it is wrapped, otherwise a default CUDA context for the given device is requested.

Parameters
  • device_number (int (default 0)) – Specify the GPU device for which the CUDA driver context is requested.

  • handle (int, optional) – Specify CUDA handle for a shared context that has been created by another library.

Methods

__init__

Create a CUDA driver context for a particular device.

buffer_from_data

Create device buffer and initialize with data.

buffer_from_object

Create device buffer view of arbitrary object that references device accessible memory.

foreign_buffer

Create device buffer from address and size as a view.

from_numba

Create a Context instance from a Numba CUDA context.

get_device_address

Return the device address that is reachable from kernels running in the context

get_num_devices

Return the number of GPU devices.

new_buffer

Return new device buffer.

open_ipc_buffer

Open existing CUDA IPC memory handle

synchronize

Blocks until the device has completed all preceding requested tasks.

to_numba

Convert Context to a Numba CUDA context.

Attributes

bytes_allocated

Return the number of allocated bytes.

device_number

Return context device number.

handle

Return pointer to context handle.

buffer_from_data()

Create device buffer and initialize with data.

Parameters
  • data ({CudaBuffer, HostBuffer, Buffer, array-like}) – Specify data to be copied to device buffer.

  • offset (int) – Specify the offset of input buffer for device data buffering. Default: 0.

  • size (int) – Specify the size of device buffer in bytes. Default: all (starting from input offset)

Returns

cbuf (CudaBuffer) – Device buffer with copied data.

buffer_from_object()

Create device buffer view of arbitrary object that references device accessible memory.

When the object contains a non-contiguous view of device accessible memory then the returned device buffer will contain contiguous view of the memory, that is, including the intermediate data that is otherwise invisible to the input object.

Parameters

obj ({object, Buffer, HostBuffer, CudaBuffer, ..}) – Specify an object that holds (device or host) address that can be accessed from device. This includes objects with types defined in pyarrow.cuda as well as arbitrary objects that implement the CUDA array interface as defined by numba.

Returns

cbuf (CudaBuffer) – Device buffer as a view of device accessible memory.

bytes_allocated

Return the number of allocated bytes.

device_number

Return context device number.

foreign_buffer()

Create device buffer from address and size as a view.

The caller is responsible for allocating and freeing the memory. When address==size==0 then a new zero-sized buffer is returned.

Parameters
  • address (int) – Specify the starting address of the buffer. The address can refer to both device or host memory but it must be accessible from device after mapping it with get_device_address method.

  • size (int) – Specify the size of device buffer in bytes.

  • base ({None, object}) – Specify object that owns the referenced memory.

Returns

cbuf (CudaBuffer) – Device buffer as a view of device reachable memory.

static from_numba()

Create a Context instance from a Numba CUDA context.

Parameters

context ({numba.cuda.cudadrv.driver.Context, None}) – A Numba CUDA context instance. If None, the current Numba context is used.

Returns

shared_context (pyarrow.cuda.Context) – Context instance.

get_device_address()

Return the device address that is reachable from kernels running in the context

Parameters

address (int) – Specify memory address value

Returns

device_address (int) – Device address accessible from device context

Notes

The device address is defined as a memory address accessible by device. While it is often a device memory address but it can be also a host memory address, for instance, when the memory is allocated as host memory (using cudaMallocHost or cudaHostAlloc) or as managed memory (using cudaMallocManaged) or the host memory is page-locked (using cudaHostRegister).

static get_num_devices()

Return the number of GPU devices.

handle

Return pointer to context handle.

new_buffer()

Return new device buffer.

Parameters

nbytes (int) – Specify the number of bytes to be allocated.

Returns

buf (CudaBuffer) – Allocated buffer.

open_ipc_buffer()

Open existing CUDA IPC memory handle

Parameters

ipc_handle (IpcMemHandle) – Specify opaque pointer to CUipcMemHandle (driver API).

Returns

buf (CudaBuffer) – referencing device buffer

synchronize()

Blocks until the device has completed all preceding requested tasks.

to_numba()

Convert Context to a Numba CUDA context.

Returns

context (numba.cuda.cudadrv.driver.Context) – Numba CUDA context instance.