Heuristics for Thread-Level Speculation in Web Applications

Author

Martinsen, Jan Kasper ; Grahn, Hakan ; Isberg, Anders

Author_Institution

Sch. of Comput., Blekinge Inst. of Technol., Karlskrona, Sweden

Volume

13

Issue

2

fYear

2014

fDate

July-Dec. 19 2014

Firstpage

77

Lastpage

80

Abstract

JavaScript is a sequential programming language, and Thread-Level Speculation has been proposed to dynamically extract parallelism in order to take advantage of parallel hardware. In previous work, we have showed significant speed-ups with a simple on/off speculation heuristic. In this paper, we propose and evaluate three heuristics for dynamically adapt the speculation: a 2-bit heuristic, an exponential heuristic, and a combination of these two. Our results show that the combined heuristic is able to both increase the number of successful speculations and decrease the execution time for 15 popular web applications.

Keywords

Internet; Java; parallel programming; 2-bit heuristic; JavaScript; Web applications; exponential heuristic; parallel hardware; sequential programming language; thread-level speculation; Benchmark testing; Instruction sets; Java; Multithreading; Parallel processing; Social network services; Automatic Parallelization; C.1.4 Parallel Architectures; C.1.4.f Speculative multi-threading; JavaScript; Multicore processors; Parallel Computing;

fLanguage

English

Journal_Title

Computer Architecture Letters

Publisher

ieee

ISSN

1556-6056

Type

jour

DOI

10.1109/L-CA.2013.26

Filename

6671600