| | |
Summary: From Sequential Programs to Concurrent Threads
Guilherme Ottoni Ram Rangan Adam Stoler Matthew J. Bridges David I. August
Departments of Computer Science and Electrical Engineering
Princeton University
Abstract-- Chip multiprocessors are of increasing importance
due to recent difficulties in achieving higher clock frequencies
in uniprocessors, but their success depends on finding useful
work for the processor cores. This paper addresses this challenge
by presenting a simple compiler approach that extracts non-
speculative thread-level parallelism from sequential codes. We
present initial results from this technique targeting a validated
dual-core processor model, achieving speedups ranging from 9-
48% with an average of 25% for important benchmark loops over
their single-threaded versions. We also identify important next
steps found during our pursuit of higher degrees of automatic
threading.
I. INTRODUCTION
For years, a steadily growing clock speed has been relied
upon to consistently deliver increased performance for a
wide range of applications. Recently, however, this trend has
|
