Memory sharing method, heterogeneous hardware, host and heterogeneous system

Abstract

The invention discloses a memory sharing method applied to heterogeneous hardware. The heterogeneous hardware is connected with a host. The method comprises the steps that: the heterogeneous hardware obtains a memory address of a partial memory of the host, sent by the host; and when the idle capacity of the memory of the heterogeneous hardware is lower than a predetermined capacity, the heterogeneous hardware stores data with an operating frequency lower than a predetermined operating frequency in the memory of the heterogeneous hardware to the partial memory according to the memory address. With the adoption of the memory sharing method provided by the invention, the data with the operating frequency lower than the predetermined operating frequency in the memory of the heterogeneous hardware can be stored to the partial memory of the host, so that the occupied storage space of the data with the operating frequency lower than the predetermined operating frequency in the memory of the heterogeneous hardware is reduced, the idle storage space of the heterogeneous hardware is expanded, and more memory spaces are provided for applications running in the heterogeneous hardware.

Description

technical field [0001] The invention relates to the field of data storage, in particular to a memory sharing method, heterogeneous hardware, a host and a heterogeneous system. Background technique [0002] An existing single-node heterogeneous system includes a host and heterogeneous hardware, and the host and hardware are interconnected through a bus PCI-E. Among them, the heterogeneous hardware may include many-core (ManyIntegratedCores, MIC) expansion card, general-purpose graphics processing unit (Generate-purpose Graphic Processing Units, GPGPU), etc., which as an expansion card provide the host (Host) with more powerful vector processing, floating-point calculation or Capabilities such as multi-thread parallelism. Typically, in a heterogeneous system, the memory on the host is large and the memory on the heterogeneous hardware is small. Since the memory on the current heterogeneous hardware has less free storage space after storing data, it may be difficult to suppor...

AI Technical Summary

Problems solved by technology

Since the current memory on heterogeneous hardware has less free storage space after storing data, it may be difficult to support the running of some applications with high memory requirements, or even to fully load the data of these applications

Images