PARALLEL PERFORMANCE OF STOCHASTIC ALGORITHMS
Annotation
Issues of parallel algorithm performance models construction for various task classes are discussed. Parametric approach which allows parallel speedup description in form of deterministic function is proposed. Parameters of this function are stochastic variables that characterize objective properties of algorithm and are independent of software and hardware implementation. This makes possible analytical study of dependences between performance probabilistic characteristics, algorithm and parallel architecture.
Keywords
Постоянный URL
Articles in current issue
- EFFICIENCY ESTIMATION OF THE SCANNING ROBOT APPLICATION FOR INFORMATION SEARCH IN THE INFORMATION NETWORKS
- ADAPTIVE PROTECTION OF INFORMATION SYSTEMS
- METHOD OF SEGMENTATION OF THE IMAGE FOR RECOGNITION OF PRINTED DOCUMENTS
- PERIODIC MODES IN SYSTEMS OF AUTOMATIC CONTROL WITH PULSE-WIDTH MODULATIONS OF THE SECOND KIND
- SUFFICIENT CONDITION FOR NONLINEAR SAMPLING SYSTEM ASYMPTOTIC STABILITY OF DISCRETE SYSTEM WITH CHANGING PARAMETERS
- ESTIMATION OF APPLICATION TASK RESPONSE TIME IN THE MULTIPROCESSOR SYSTEMS
- VERIFICATION OF FILTERING RULES OF SECURITY POLICY BY MODEL CHECKING
- PENDULUM PULSE-REBALANCE ACCELEROMETER UNIT PARAMETER ESTIMATION USING A SINGLE AXIS TURNTABLE
- IDENTIFICATION OF SOME PARAMETERS OF THE ENGINE MEMBRANE TYPE
- EXPERIMENTAL COMPLEX FOR STUDYING OF HIGH-SPEED EFFECT OF FLOWS OF METEORIC PARTICLES ON A SPACE VEHICLE SURFACE
- BALLISTIC CONSTRUCTION OF COMMUNICATION SYSTEMS AND PASSIVE RADIOLOCATION OF LUNAR SURFACE
- EQUIPMENT FOR RESEARCH OF HF IONOSPHERIC MULTIPATH PROPAGATION EFFECTS