H. Jonkers, Fac. of Electr. Eng., Delft Univ. of Technol., Netherlands
G.L. Reijns, Fac. of Electr. Eng., Delft Univ. of Technol., Netherlands
The spectrum of approaches to performance prediction of parallel systems ranges from low-cost, low-precision compile-time methods to high-cost, high-precision methods with an equal variety of underlying modeling formalisms (e.g., task graphs, queueing networks, simulation languages) which are mutually incompatible. A performance prediction technique is described which unifies a number of existing approaches within one formalism. As the analysis is based on a model reduction calculus the approach allows for a flexible trade-off between precision and cost, effectively ranging from simulation to static analysis.
Index Terms:
software performance evaluation; program compilers; parallel processing; system monitoring; simulation languages; performance modeling; parallel systems; flexible precision; performance prediction; low-precision compile-time methods; high-cost high-precision methods; modeling formalisms; task graphs; queueing networks; simulation languages; performance prediction technique; model reduction calculus; static analysis; simulation
Citation:
A.J.C. Van Gemund, H. Jonkers, G.L. Reijns, "Performance modeling of parallel systems with flexible precision," hicss, pp.444, 28th Hawaii International Conference on System Sciences (HICSS'95), 1995
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb