Quantifying the Semantic Gap Between Serial and Parallel Programming
View / Open Files
Authors
Zhang, Xiaochun
Jones, Timothy M
Campanoni, Simone
Conference Name
IEEE International Symposium on Workload Characterization
Publisher
IEEE
Type
Conference Object
This Version
AM
Metadata
Show full item recordCitation
Zhang, X., Jones, T. M., & Campanoni, S. Quantifying the Semantic Gap Between Serial and Parallel Programming. IEEE International Symposium on Workload Characterization. https://doi.org/10.17863/CAM.76893
Abstract
Automatic parallelizing compilers are often constrained in their transformations because they must conservatively respect data dependences within the program. Developers, on the other hand, often take advantage of domain-specific knowledge to apply transformations that modify data dependences but respect the application’s semantics. This creates a semantic gap between the parallelism extracted automatically by compilers and manually by developers. Although prior work has proposed programming language extensions to close this semantic gap, their relative contribution is unclear and it is uncertain whether compilers can actually achieve the same performance as manually parallelized code when using them. We quantify this semantic gap in a set of sequential and parallel programs and leverage these existing programming-language extensions to empirically measure the impact of closing it for an automatic parallelizing compiler. This lets us achieve an average speedup of 12.6× on an Intel-based 28-core machine, matching the speedup obtained by the manually parallelized code. Further, we apply these extensions to widely used sequential system tools, obtaining 7.1× speedup on the same system.
Relationships
Is supplemented by: https://doi.org/10.17863/CAM.76224
Sponsorship
Engineering and Physical Sciences Research Council (EP/K026399/1)
Engineering and Physical Sciences Research Council (EP/P020011/1)
Embargo Lift Date
2024-10-15
Identifiers
External DOI: https://doi.org/10.17863/CAM.76893
This record's URL: https://www.repository.cam.ac.uk/handle/1810/329445
Rights
All rights reserved
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.