Continuous Path and Edge Profiling

Microarchitectures increasingly rely on dynamic optimization to improve performance in ways that are dif- ficult or impossible for ahead-of-time compilers. Dynamic optimizers in turn require continuous, portable, low cost, and accurate control-flow profiles to inform their decisions, but prior appro...

Full description

Saved in:
Bibliographic Details
Published in:38th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO'05) pp. 130 - 140
Main Authors: Bond, Michael D., McKinley, Kathryn S.
Format: Conference Proceeding
Language:English
Published: Washington, DC, USA IEEE Computer Society 12.11.2005
IEEE
Series:ACM Conferences
Subjects:
Bonding
Computer systems organization > Architectures > Serial architectures > Pipeline computing
Dynamic compiler
Hardware
Hardware > Integrated circuits
Instruments
Java
Microarchitecture
Optimizing compilers
Runtime
Sampling methods
Software and its engineering > Software organization and properties > Contextual software domains > Operating systems > Process management > Multiprocessing > multiprogramming > multitasking
Virtual machining
ISBN:9780769524405, 0769524400
ISSN:1072-4451
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Microarchitectures increasingly rely on dynamic optimization to improve performance in ways that are dif- ficult or impossible for ahead-of-time compilers. Dynamic optimizers in turn require continuous, portable, low cost, and accurate control-flow profiles to inform their decisions, but prior approaches have struggled to meet these goals simultaneously. This paper presents PEP, a hybrid instrumentation and sampling approach for continuous path and edge profiling that is efficient, accurate, and portable. PEP uses a subset of Ball-Larus path profiling to identify paths with low overhead, and uses sampling to mitigate the expense of storing paths. PEP further reduces overhead by using profiling to guide instrumentation placement. PEP improves profile accuracy with a modified version of Arnold-Grove sampling. The resulting system has 1.2% average and 4.3% maximum overhead, 94% path profile accuracy, and 96% edge profile accuracy on a set of Java benchmarks.
Bibliography:SourceType-Conference Papers & Proceedings-1
ObjectType-Conference Paper-1
content type line 25
ISBN:9780769524405
0769524400
ISSN:1072-4451
DOI:10.1109/MICRO.2005.16