Data processing method and related device

Abstract

The embodiment of the invention provides a data processing method and a related device, and the method comprises the steps: receiving each data processing request with a request category, and writing each data processing request into a corresponding request category queue; according to a writing sequence of the data processing requests located at the head of each request category queue, determining a previous data processing request and a later data processing request, and according to the previous data processing request, determining a storage space of a current-level module corresponding to previous request data; when the previous request data is not obtained, determining a storage space of a current-level module corresponding to the post-requested data according to the post-data processing request, obtaining the post-requested data, and when previous obtained data in the previous request data and the post-requested data is obtained, processing the request category of the data processing request corresponding to the previously obtained data. According to the embodiment of the invention, the cache data processing efficiency can be improved.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, and in particular, to a data processing method and a related device. Background technique [0002] In computer technology, processors and multi-level memory are typical computer structures. During the data operation process, the main memory in the multi-level memory stores instructions and data, and the processor obtains instructions and corresponding data from the main memory, executes the instructions, and writes the resulting data back to the main memory. There is usually one or more levels of cache memory (Cache) between the processor and the main memory. Cache memory is used to reduce the time it takes for the processor to fetch instructions and data. [0003] In the core operations of high-performance computing such as data operations and matrix operations, there is usually a clear processing order for data. When operation requests are received in the cache, ...

AI Technical Summary

Problems solved by technology

[0004] However, the above-mentioned operations are likely to cause the problem of mutual blocking of reading and writing. For example, when the cache processes a queue of read and write requests received, according to the order in which the requests arrive, the first-arriving read requests should be processed first, but the later ones should be processed first. The write data required by the write request is already in place, which causes the read request to block the write request, resulting in low cache data processing efficiency

Images