ai.rapids.cudf

Class RmmCudaAsyncMemoryResource

java.lang.Object

ai.rapids.cudf.RmmCudaAsyncMemoryResource

All Implemented Interfaces:

RmmDeviceMemoryResource, AutoCloseable

public class RmmCudaAsyncMemoryResource
extends Object
implements RmmDeviceMemoryResource

A device memory resource that uses `cudaMallocAsync` and `cudaFreeAsync` for allocation and deallocation.

Constructor Summary

Constructors

Constructor and Description
RmmCudaAsyncMemoryResource(long size, long releaseThreshold) Create a new async memory resource

Method Summary

Modifier and Type	Method and Description
void	close()
long	getHandle() Returns a pointer to the underlying C++ class that implements rmm::mr::device_memory_resource
long	getSize()
String	toString()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

RmmCudaAsyncMemoryResource

public RmmCudaAsyncMemoryResource(long size,
                                  long releaseThreshold)

Create a new async memory resource

Parameters:

size - the initial size of the pool

releaseThreshold - size in bytes for when memory is released back to cuda

Method Detail

getHandle

public long getHandle()

Description copied from interface: RmmDeviceMemoryResource

Returns a pointer to the underlying C++ class that implements rmm::mr::device_memory_resource

Specified by:

getHandle in interface RmmDeviceMemoryResource

getSize

public long getSize()

close

public void close()

Specified by:

close in interface RmmDeviceMemoryResource

Specified by:

close in interface AutoCloseable

toString

public String toString()

Overrides:

toString in class Object