Implementation of the first version of the TimIt plugin for IC2D, an eclipse based RCP stand-alone application. Screenshot during monitoring of the integralPi application here. Same for the NBody application here

Implementation of a performance critical benchmarking application with an integrated comparative chart generation. See screenshot

Tuesday 21 August 2007

First release of a new benchmark DT from NPB3.2 official implementation. Ported from C/MPI to Java/ProActive. However the implementation of DT is currently not optimized. The communications are quite simple, the send/recv MPI primitives are implemented using tagged requests served as immediate services (the request queue contains only one request during the benchmark which is not ProActive Fault Tolerance and Migration compliant).

In the Readme file of the official C version :
DT is written in C and same executable can run on any number of processors, provided this number is not less than the number of nodes in the communication graph. DT benchmark takes one argument: BH, WH, or SH. This argument specifies the communication graph Black Hole, White Hole, or SHuffle respectively. The current release contains verification numbers for CLASSES S, W, A, and B only. Classes C and D are defined, but verification numbers are not provided in this release.

Example of DT output :