Scalable Analysis Techniques for Microprocessor Performance Counter Metrics
Dong H. Ahn,Jeffrey S. Vetter +1 more
- 16 Nov 2002
- pp 1-16
TL;DR: Several multivariate statistical techniques can automatically extract important features from the data and be fed directly back to an application developer, or used as input to a more comprehensive performance analysis environment, such as a visualization or an expert system.
read more
Abstract: Contemporary microprocessors provide a rich set of integrated performance counters that allow application developers and system architects alike the opportunity to gather important information about workload behaviors. Current techniques for analyzing data produced from these counters use raw counts, ratios, and visualization techniques help users make decisions about their application performance. While these techniques are appropriate for analyzing data from one process, they do not scale easily to new levels demanded by contemporary computing systems. Very simply, this paper addresses these concerns by evaluating several multivariate statistical techniques on these datasets. We find that several techniques, such as statistical clustering, can automatically extract important features from the data. These derived results can, in turn, be fed directly back to an application developer, or used as input to a more comprehensive performance analysis environment, such as a visualization or an expert system.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Stack Trace Analysis for Large Scale Debugging
Dorian Arnold,Dong H. Ahn,B R de Supinski,Gregory L. Lee,Barton P. Miller,Martin Schulz +5 more
- 26 Mar 2007
TL;DR: The Stack Trace Analysis Tool (STAT) is presented to aid in debugging extreme-scale applications and leverages MRNet, an infrastructure for tool control and data analyses, to overcome scalability barriers faced by heavy-weight debuggers.
Vertical profiling: understanding the behavior of object-priented applications
Matthias Hauswirth,Peter F. Sweeney,Amer Diwan,Michael Hind +3 more
- 01 Oct 2004
TL;DR: By incorporating vertical profiling into a programming environment, the programmer will be able to understand how their program interacts with the underlying abstraction levels, such as application server, VM, operating system, and hardware.
Online performance analysis by statistical sampling of microprocessor performance counters
Reza Azimi,Michael Stumm,Robert W. Wisniewski +2 more
- 20 Jun 2005
TL;DR: A simple model in real-time is built that speculatively associates each stall cycle to a processor component that likely caused the stall and demonstrates that it can effective analyze on-line performance of application and system code running at full speed.
129
Design and implementation of a parallel performance data management framework
Kevin Huck,Allen D. Malony,Robert Bell,A. Morris +3 more
- 14 Jun 2005
TL;DR: PerfDMF addresses objectives of performance tool integration, interoperation, and reuse by providing common data storage, access, and analysis infrastructure for parallel performance profiles by providing an extensible parallel profile data schema and relational database schema.
Scalable compression and replay of communication traces in massively parallel environments
Michael Noeth,Jaydeep Marathe,Frank Mueller,Martin Schulz,Bronis R. de Supinski +4 more
- 11 Nov 2006
TL;DR: This work contributes an approach that provides near constant-size communication traces regardless of the number of nodes while preserving structural information, and discusses its impact on communication tuning and beyond.
78
References
•Book
Applied Multivariate Statistical Analysis
R. A. Johnson,Dean W. Wichern +1 more
- 01 Jan 1982
TL;DR: In this article, the authors present an overview of the basic concepts of multivariate analysis, including matrix algebra and random vectors, as well as a strategy for analyzing multivariate models.
12.6K
Applied Multivariate Statistical Analysis
TL;DR: This chapter discusses the development of the Spatial Point Pattern Analysis Code in S–PLUS, which was developed in 1993 by P. J. Diggle and D. C. Griffith.
5.8K
The GRID: Blueprint for a New Computing Infrastructure
TL;DR: The main purpose is to update the designers and users of parallel numerical algorithms with the latest research in the field and present the novel ideas, results and work in progress and advancing state-of-the-art techniques in the area of parallel and distributed computing for numerical and computational optimization problems in scientific and engineering application.
5K
Continuous profiling: where have all the cycles gone?
Jennifer M. Anderson,Lance M. Berc,Jeffrey Dean,Sanjay Ghemawat,Monika Henzinger,Shun-Tak Albert Leung,Richard L. Sites,Mark T. Vandevoorde,Carl A. Waldspurger,William E. Weihl +9 more
- 01 Oct 1997
TL;DR: The Digital Continuous Profiling Infrastructure is a sampling-based profiling system designed to run continuously on production systems, supporting multiprocessors, works on unmodified executables, and collects profiles for entire systems, including user programs, shared libraries, and the operating system kernel.
ProfileMe: hardware support for instruction-level profiling on out-of-order processors
Jeffrey Dean,James W. Hicks,Carl A. Waldspurger,William E. Weihl,George Z. Chrysos +4 more
- 01 Dec 1997
TL;DR: An inexpensive hardware implementation of ProfileMe is described, a variety of software techniques to extract useful profile information from the hardware are outlined, and several ways in which this information can provide valuable feedback for programmers and optimizers are explained.