System and method for extending nonvolatile memory based on consistency buses

Abstract

The invention discloses a system and method for extending a nonvolatile memory based on consistent buses. The system structurally comprises a plurality of nodes mutually connected through cache consistency high-speed mutually-connected buses, wherein each node is configured with a hybrid memory consisting of a processor, a DRAM memory and a NVM memory, a NVM memory controller is configured between the processor and the NVM memory, a DRAM memory controller is configured between the processor and the DRAM memory, the processor is mutually connected with the NVM memory and the DRAM memory through the cache consistency high-speed mutually-connected buses, and the DRAM memory and the NVM memory are addressed in a unified mode to achieve overall cache consistency of a heterogeneous hybrid memory system. The method is achieved based on the system. Compared with the prior art, existing technical bottlenecks of the DRAM memory are solved by adopting the system and method for extending the nonvolatile memory based on the consistent buses, the NVM memory access performance is improved, data processing capability of the whole system is improved, and the system and method is high in practicability, wide in application range and easy to popularize.

Description

technical field [0001] The invention relates to the technical field of computers, in particular to a highly practical system and method for expanding non-volatile memory based on a coherent bus. Background technique [0002] In recent years, the global data volume has grown at an annual rate of 58%, and this rate will be even faster in the future, which makes users pay more and more attention to the timely and efficient processing of massive data and implementation of analysis. Existing computing-centric technologies are difficult to meet the application requirements of big data. Therefore, the reconstruction of IT architecture is imperative. The emergence of new types of non-volatile memory devices and the continuous reduction in cost have created opportunities for data-centric big data processing models, namely in-memory computing. [0003] The I / O performance mismatch between memory and external storage has always been an important reason for slow data processing. In-me...

AI Technical Summary

Problems solved by technology

[0006] Based on this, a system and method for expanding non-volatile memory based on a coherent bus are now provided to solve the problem of possible inconsistency between data stored in DRAM and Cache and data in NVM. Here, DRAM refers to Dynamic Random Access Memory. dynamic random access memory

Images