Internal memory copying accelerating method and device facing multi-core microprocessor

Abstract

The invention discloses an internal memory copying accelerating method and a device facing a multi-core microprocessor. The method comprises the following steps: an internal memory copying instruction and an MPI (Multi Point Interface) communication accelerating module are added in a microprocessor instruction in a concentration manner to identify internal memory copying request types which are obtained by decoding; general internal memory copying requests are issued to an internal memory copying unit; MPI group communication requests or MPI point-to-point communication requests are issued to the MPI communication accelerating module; the MPI communication accelerating module merges and executes associated internal memory copying requests to improve internal memory copying performance and execution efficiency; and the device comprises a decoding unit, the internal memory copying unit, associated detecting parts, and the MPI communication accelerating module for executing the internal memory copying requests which constitute MPI group communication or MPI point-to-point communication. The method and the device have the advantages of high efficiency of internal memory copying, good performance of multi-core optimization, low hardware design complexity, good compatibility, low power consumption and simplicity in hardware realization.

Description

technical field [0001] The invention relates to the field of multi-core microprocessors, in particular to a memory copy acceleration method and device for multi-core microprocessors. Background technique [0002] With the rapid development of computing technology, application programs have higher and higher requirements on the processing capability of microprocessors. People improve the performance of the processor core by increasing the main frequency of the processor, adopting technologies such as superscalar and multi-threading. However, the above-mentioned technologies have gradually been unable to meet the needs of the rapid development of processors. The continuous improvement of clock frequency means that the power consumption of processors has increased sharply and clock synchronization has become more and more difficult. Mainstream processors no longer blindly pursue high main frequency. Given that the parallelism of the application itself often has certain limita...

AI Technical Summary

Problems solved by technology

However, this DMA-based memory copy technology still has certain shortcomings, such as (1) DMA devices often require a long startup time, (2) the kernel needs to be notified through an interrupt after the copy is completed, (3) the support of the operating system is required

[0006] No matter which of the above memory copy implementation methods, there is a problem of relatively low performance

In addition, these memory copy implementation methods are mainly aimed at memory copy operations in single-core microprocessors, and do not give an optimization method for memory copy operations in multi-core microprocessors

In short, with the continuous development of the architecture and manufacturing process, the performance gap between the processor core and the memory bandwidth is constantly increasing, and the performance of the memory copy operation that requires frequent memory access restricts the improvement of the overall performance of the multi-core processor; On the one hand, memory copy operations widely exist in various operating system programs and user programs

The importance of the above-mentioned memory copy and the inefficiency of its performance impel research on memory copy acceleration methods and devices for multi-core microprocessors to become a necessity.

Images