Shared memory based method for realizing multiprocess GPU (Graphics Processing Unit) sharing

Abstract

The invention discloses a shared memory based method for realizing multiprocess GPU (Graphics Processing Unit) sharing, aiming to solve the problem that multiple processes of an SPMD (Single Program Multiple Data) program on a single heterogeneous computing node cannot share the GPU. In a technical scheme, the method comprises the steps: a GPU server side is started and waits for the arrival of request signals of a GPU client side; the GPU client side is started and sends request signals to the GPU server side when GPU acceleration is needed; and GPU server side responds to the request signalwhich is received at first, performing accelerated computing by using a GPU, and simultaneously executes a computing process of a CPU (Central Processing Unit). In a GPU computing process, the request signals from the GPU client side enters a signal queue in an operating system for queuing; and after GPU computing is completed, the GPU sever side responds to other request signals in the signal queue. On the single heterogeneous computing node containing one GPU, the method in the invention can be used to ensure that operation faults cannot be generated when a plurality of processes, in need of GPU acceleration, of the SPMD program run, and the GPU can be shared by the plurality of processes.

Description

technical field [0001] The invention relates to a method for sharing a Graphics Processing Unit (GPU), in particular to a method for sharing the GPU between multiple processes based on shared memory for data communication. Background technique [0002] In recent years, with the continuous development of GPU hardware technology and programming models, more and more attention has been paid to the powerful computing capabilities of GPUs. A large number of scientific computing programs use GPUs to accelerate their key code segments and obtain good speedup ratios. The tasks of the scientific computing program using the GPU are: initialize the GPU, prepare data for the GPU, calculate on the GPU, write back the calculation results to the GPU, and release the GPU. [0003] However, existing GPUs do not support simultaneous access by multiple processes. After a process initializes the GPU, other processes cannot use the GPU until the GPU is released. The parallel program of SPMD (S...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is: Aiming at the situation that the multiple processes of the SPMD program on a single heterogeneous computing node cannot share the use of the GPU, a method for data communication based on shared memory is proposed to realize the shared use of multiple processes GPU

Images