A Benchmark Suite for Evaluating Parallel Programming Models

Abstract

The transition to multi-core processors enforces software developers to explicitly exploit thread-level parallelism to increase performance. The associated programmability problem has led to the introduction of a plethora of parallel programming models that aim at simplifying software development by raising the abstraction level. Since industry has not settled for a single model, however, multiple significantly different approaches exist. This work presents a benchmark suite which can be used to classify and compare such parallel programming models and, therefore, aids in selecting the appropriate programming model for a given task. After a detailed explanation of the suite's design, preliminary results for two programming models, Pthreads and OmpSs/SMPSs, are presented and analyzed, leading to an outline of further extensions of the suite.