Understanding object-level memory access patterns across the spectrum
Name
2017.objprof.sc.pdf
Description
Accepted version
Size
783.64 KB
Format
Adobe PDF
Checksum (MD5)
70111357b11d310cd74a3fa27897b307
Author(s)
El-Sayed, Nosayba
Sanchez, Daniel
Date Issued
November 2017
Journal
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017
Publisher
Association for Computing Machinery (ACM)
Citation
Ji, Xu et al. “Understanding object-level memory access patterns across the spectrum.” Paper presented in Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017, Denver, CO, November 12 -17, 2017, Association for Computing Machinery (ACM): article 25, 1-12 © 2017 The Author(s)
Version
Author's final manuscript
Abstract
Memory accesses limit the performance and scalability of countless applications. Many design and optimization efforts will benefit from an in-depth understanding of memory access behavior, which is not offered by extant access tracing and profiling methods. In this paper, we adopt a holistic memory access profiling approach to enable a better understanding of program-system memory interactions. We have developed a two-pass tool adopting fast online and slow offline profiling, with which we have profiled, at the variable/object level, a collection of 38 representative applications spanning major domains (HPC, personal computing, data analytics, AI, graph processing, and datacenter workloads), at varying problem sizes. We have performed detailed result analysis and code examination. Our findings provide new insights into application memory behavior, including insights on per-object access patterns, adoption of data structures, and memory-access changes at different problem sizes. We find that scientific computation applications exhibit distinct behaviors compared to datacenter workloads, motivating separate memory system design/optimizations.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3126908.3126917
