Harmony: Collection and analysis of parallel block vectors

11 years 7 months ago

Download arcade.cs.columbia.edu

Efﬁcient execution of well-parallelized applications is central to performance in the multicore era. Program analysis tools support the hardware and software sides of this effort by exposing relevant features of multithreaded applications. This paper describes parallel block vectors, which uncover previously unseen characteristics of parallel programs. Parallel block vectors provide block execution proﬁles per concurrency phase (e.g., the block execution proﬁle of all serial regions of a program). This information provides a direct and ﬁne-grained mapping between an application’s runtime parallel phases and the static code that makes up those phases. This paper also demonstrates how to collect parallel block vectors with minimal application perturbation using Harmony. Harmony is an instrumentation pass for the LLVM compiler that introduces just 1621% overhead on average across eight Parsec benchmarks. We apply parallel block vectors to uncover several novel insights about pa...

Melanie Kambadur, Kui Tang, Martha A. Kim

Real-time Traffic