Title: Fast parallel lexical analysis on multi-core machines

Authors: Amit Barve; Brijendra Kumar Joshi

Addresses: Computer Engineering, V.I.I.T., Pune, India ' F.C.E., M.C.T.E Mhow, India

Abstract: Lexical analysis begins the process of compilation of any source program. Various attempts have been made to improve the lexical analysis phase by exploiting the inherent parallel processing capability of multi-core machines. In this paper we present a fast lexical analysis algorithm that performs better than our previous algorithm which uses round robin approach for scheduling jobs to processors. We demonstrate the improvement in lexical analysis phase by automatically generating C programs having up to 300 potentially parallel constructs like if..else, for, while loops, switch..case, etc. The maximum speedup achieved for seven CPUs is 4.14.

Keywords: parallel lexical analysis; processor affinity; flex; multi-core machines; parallel processing; job scheduling; C programming.

DOI: 10.1504/IJHPCN.2016.076270

International Journal of High Performance Computing and Networking, 2016 Vol.9 No.3, pp.250 - 257

Received: 13 May 2015
Accepted: 01 Aug 2015
Published online: 30 Apr 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article