Blue Gene/L performance tools

Good performance monitoring is the basis of modern performance analysis tools for application optimization. We are providing a variety of such performance analysis tools for the new Blue Gene®/L supercomputer. Those tools can be divided into two categories: single-node performance tools and multinod...

Full description

Saved in:
Bibliographic Details
Published in:IBM journal of research and development 2005-03, Vol.49 (2-3), p.407-424
Main Authors: Martorell, X, Smeds, N, Walkup, R, Brunheroto, J R
Format: Article
Language:English
Subjects:
Bandwidths
Benchmarks
Cache coherency
Cache memory
Communication
Computer architecture
Computer peripherals
Design
Dynamic random access storage
Embedded dynamic random access storage
Embedded systems
Graphical user interfaces
Information technology
Informationsteknik
Interfaces
Libraries
Message passing interface (MPI)
Microprocessor chips
Microprocessors
Optimization
Packet networks
Parallel processing systems
Random access memory
Semantics
Software
Supercomputers
TECHNOLOGY
TEKNIKVETENSKAP
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Good performance monitoring is the basis of modern performance analysis tools for application optimization. We are providing a variety of such performance analysis tools for the new Blue Gene®/L supercomputer. Those tools can be divided into two categories: single-node performance tools and multinode performance tools. From a single-node perspective, we provide standard interfaces and libraries, such as PAPI and libHPM, that provide access to the hardware performance counters for applications running on the Blue Gene/L compute nodes. From a multinode perspective, we focus on tools that analyze Message Passing Interface (MPI) behavior. Those tools work by first collecting message-passing trace data when a program runs. The trace data is then used by graphical interface tools that analyze the behavior of applications. Using the current prototype tools, we demonstrate their usefulness and applicability with case studies of application optimization. [PUBLICATION ABSTRACT]
ISSN:0018-8646
2151-8556
0018-8646
2151-8556
DOI:10.1147/rd.492.0407