This preview shows page 1. Sign up to view the full content.
Unformatted text preview: rations
computation Lines of Code 800
600 More important than the
size difference 400that it
is easier to write, read,
modify, and maintain 202 200 0
F+MPI 87 95 70 242 77 ZPL A-ZPL Language NAS MG Linecounts
0 MPI Java HPF OpenMP Serial A-ZPL NAS MG Speedup: ZPL vs.
Fortran + MPI ZPL scales better than MPI
since its communication is
expressed in an
way; this permits the
compiler to use SHMEM on
this Cray T3E but MPI on a
commodity cluster ZPL also performs better at smaller
scales where communication is not
the bottleneck ⇒ new languages need
not imply performance sacrifices
Similar observations—and more dramatic
ones—have been made using more recent
architectures, languages, and benchmarks Cray T3E Generality Notes
Each ZPL binary supports:
• an arbitrary load-time problem size
• an arbitrary load-time # of processors
• 1D/2D/3D data decompositions This MPI binary only supports:
• a static 2**k problem size
• a static 2**j # of processors
• a 3D data decomposition
The code could be rewritten to relax
these assumptions, but at what cost?
- in performance?
- in development effort? Cray T3E Global-view models can benefit Productivity
communication 1000 declarations Lines of Code 800 computation 566
400 202 200
77 F+MPI ZPL A-ZPL 0 Language
Cray T3E • more programmable, flexible
• able to achieve competitive perfor...
View Full Document
- Winter '09