Efficient fine-grained shared buffer management for multiple OpenCL devices

OpenCL programming provides full code portability between different hardware platforms, and can serve as a good programming candidate for heterogeneous systems, which typically consist of a host processor and several accelerators. However, to make full use of the computing capacity of such a system,...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers of information technology & electronic engineering 2013-11, Vol.14 (11), p.859-872
Main Authors: Xun, Chang-qing, Chen, Dong, Lan, Qiang, Zhang, Chun-yuan
Format: Article
Language:English
Subjects:
Buffers
Communications Engineering
Computer Hardware
Computer Science
Computer Systems Organization and Communication Networks
Data transfer (computers)
Distributed memory
Electrical Engineering
Electronics and Microelectronics
Instrumentation
Microprocessors
Networks
Programmers
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:OpenCL programming provides full code portability between different hardware platforms, and can serve as a good programming candidate for heterogeneous systems, which typically consist of a host processor and several accelerators. However, to make full use of the computing capacity of such a system, programmers are requested to manage diverse OpenCL-enabled devices explicitly, including distributing the workload between different devices and managing data transfer between multiple devices. All these tedious jobs pose a huge challenge for programmers. In this paper, a distributed shared OpenCL memory （DSOM） is presented, which relieves users of having to manage data transfer explicitly, by supporting shared buffers across devices. DSOM allocates shared buffers in the system memory and treats the on-device memory as a software managed virtual cache buffer. To support fine-grained shared buffer management, we designed a kernel parser in DSOM for buffer access range analysis. A basic modified, shared, invalid cache coherency is implemented for DSOM to maintain coherency for cache buffers. In addition, we propose a novel strategy to minimize communication cost between devices by launching each necessary data transfer as early as possible. This strategy enables overlap of data transfer with kernel execution. Our experimental results show that the applicability of our method for buffer access range analysis is good, and the efficiency of DSOM is high.
ISSN:1869-1951
2095-9184
1869-196X
2095-9230
DOI:10.1631/jzus.C1300078