Automatic transplanting and optimizing method for heterogeneous parallel program

Abstract

The invention discloses an automatic transplanting and optimizing method for a heterogeneous parallel program, and belongs to a heterogeneous parallel program development technology. The invention aims to realize automatic transplantation of CPU parallel programs and improve the program performance while reducing the workload of developers, thereby solving the problems of parallel instruction conversion, data transmission management and optimization. The method is characterized in that a framework of a heterogeneous parallel program automatic transplanting system is constructed, and the heterogeneous parallel program automatic transplanting system is used for automatically translating an OpenMP CPU parallel program into an OpenMP Offloading heterogeneous parallel program; consistency stateconversion is formalized, on the premise that data consistency is guaranteed, transmission operation is optimized, and redundant data transmission is reduced; a runtime library is designed, wherein the runtime library is used for providing an automatic data transmission management and optimization function and maintaining the consistency state of each variable memory area; and a source-to-sourcetranslator is designed, wherein the translator is used for automatically converting a parallel instruction and automatically inserting a runtime API. The method can automatically identify the CPU parallel instruction and convert the CPU parallel instruction into the accelerator parallel instruction, so that the program performance is improved.

Description

technical field

[0001] The invention relates to a heterogeneous parallel program automatic transplantation and optimization method, which belongs to the heterogeneous parallel program development technology. Background technique

[0002] With the huge demand for computing power in different applications such as artificial intelligence, image processing, multi-physics simulation, quantum simulation, and climate simulation, heterogeneous platforms based on various accelerators have replaced the CPU (Central Processing Unit, central processing unit) as the computing power. main source of power. In the field of high-performance computing, GPU (Graphics Processing Unit, graphics processing unit) is mainly used as an accelerator, and GPU, DSP (Digital Signal Processing, digital signal processor) or FPGA (Field Programmable Gate Array, field programmable logic gate) are mainly used on mobile platforms. array) as an accelerator. While accelerators provide huge computing power, the...

Images