MemGaze: Rapid and Effective Load-Level Memory Trace Analysis

  • Ozgur O. Kilic
  • , Nathan R. Tallent
  • , Yasodha Suriyakumar
  • , Chenhao Xie
  • , Andres Marquez
  • , Stephane Eranian

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A challenge of memory trace analysis is combining detailed analysis and low overhead measurement. Currently, hardware/software-based analysis of load-level sequences easily incurs time slowdowns of 100x. We present MemGaze, a tool for low-overhead, high-resolution memory trace analysis. MemGaze uses Intel's Processor Tracing (PT) instruction ptwrite to collect sampled and compressed memory address traces for load-level, sequence-aware analysis of data reuse. We describe multi-resolution analysis for locations vs. operations, accesses vs. spatio-temporal reuse, and reuse (distance, rate, volume) vs. access patterns. Both trace size and resolution are controllable. We use MemGaze to elucidate the memory effects of different data structures and algorithms. For sampled traces that are ˜ 1 % of a full one, analysis metrics have 1-25% MAPE for histograms of varying dynamic sequence lengths. With current suboptimal kernel support (PT runs continuously), MemGaze's time overhead is typically 10-95%; 7x at worst. However, when PT runs only during samples, overhead is 10-35 % on memory intensive regions and correlates with executed ptwrites.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE International Conference on Cluster Computing, CLUSTER 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages484-495
Number of pages12
ISBN (Electronic)9781665498562
DOIs
StatePublished - 2022
Externally publishedYes
Event2022 IEEE International Conference on Cluster Computing, CLUSTER 2022 - Heidelberg, Germany
Duration: 6 Sep 20229 Sep 2022

Publication series

NameProceedings - IEEE International Conference on Cluster Computing, ICCC
Volume2022-September
ISSN (Print)1552-5244

Conference

Conference2022 IEEE International Conference on Cluster Computing, CLUSTER 2022
Country/TerritoryGermany
CityHeidelberg
Period6/09/229/09/22

Keywords

  • MemGaze
  • footprint
  • memory access patterns
  • memory access tracing
  • processor tracing
  • spatio-temporal reuse

Fingerprint

Dive into the research topics of 'MemGaze: Rapid and Effective Load-Level Memory Trace Analysis'. Together they form a unique fingerprint.

Cite this