Quantitative analysis of parallelism and data movement properties across the Berkeley computational motifs
Victoria Caparrós Cabezas IBM Research --- Zürich, Säumerstrasse, Rüschlikon, Switzerland
Abstract
This work presents the first thorough quantitative study of the available instruction-level parallelism, basic-block-granularity thread parallelism, and data movement, across the Berkeley dwarfs/computational motifs. Although this classification was intended to group applications with common computation and (albeit coarse-grained) communication patterns, the applications analyzed exhibit a wide range of available machine-extractable parallelism and data motion within and across dwarfs.
Cite as:
Victoria Caparrós Cabezas and Phillip Stanley-Marbell. 2011. Quantitative analysis of parallelism and data movement properties across the Berkeley computational motifs. In Proceedings of the 8th ACM International Conference on Computing Frontiers (CF '11). Association for Computing Machinery, New York, NY, USA, Article 17, 1–2. DOI:https://doi.org/10.1145/2016604.2016625
BibTeX:
@inproceedings{10.1145/2016604.2016625,
author = {Cabezas, Victoria Caparr\'{o}s and Stanley-Marbell, Phillip},
title = {Quantitative Analysis of Parallelism and Data Movement Properties across the Berkeley Computational Motifs},
year = {2011},
isbn = {9781450306980},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/2016604.2016625},
doi = {10.1145/2016604.2016625},
articleno = {17},
numpages = {2},
keywords = {Berkeley computational motifs, basic-block-level parallelism, instruction-level parallelism, data movement},
location = {Ischia, Italy},
series = {CF '11}
}
