Titlebook: Euro-Par 2007 Parallel Processing; 13th International E Anne-Marie Kermarrec,Luc Bougé,Thierry Priol Conference proceedings 2007 Springer-V

殺死

A Profiling Tool for Detecting Cache-Critical Data Structurest (PMU) provided by modern processors, . is capable of finding cache-critical variables, arrays, or even a segment of an array. It can also locate theses access hotspots to the most concrete position such as individual functions and code lines. This feature allows the user to apply . for efficient cache optimization.

Acupressure

: Low-Overhead Online Parallel Performance Monitoring measurement while Supermon is used to collect the distributed measurement state. Our experiments show that this novel approach leads to very lowoverhead application monitoring as well as other benefits unavailable from using a transport such as NFS.

lobster

Decision Trees and MPI Collective Algorithm Selection Problemmbining experimental data for reduce and broadcast and generating a decision function from the combined decision trees resulted in less than 2.5% relative performance penalty. The results indicate that C4.5 decision trees are applicable to this problem and should be more widely used in this domain.

詞根詞綴法

Automatic Structure Extraction from MPI Applications Tracefiles is a problem. The methodology we have developed and implemented performs an automatic analysis that can be applied to huge tracefiles, which obtains its internal structure and selects meaningful parts of the tracefile. The paper presents the methodology and results we have obtained from real applications.

預(yù)防注射

EVEN

Vaginismus

MERIT

MUT

adipose-tissue

Die Bauarten der Drehmaschinen,ssible to identify critical tasks which prevent scalability and to locate bottlenecks inside the application. We show that the profiling information can be used to determine a coarse estimation of the execution time for a given number of processors.