6533b85ffe1ef96bd12c1bd5

RESEARCH PRODUCT

VLBI-resolution radio-map algorithms: Performance analysis of different levels of data-sharing on multi-socket, multi-core architectures

Siham TabikPetar MimicaEmilio L. ZapataLuis RomeroOscar Plata

subject

Multi-core processorMemory hierarchy010308 nuclear & particles physicsComputer scienceGeneral Physics and AstronomyParallel computing01 natural sciencesScheduling (computing)Data sharingComputer engineeringHardware and Architecture0103 physical sciencesVery-long-baseline interferometryScalabilityCache010303 astronomy & astrophysicsScaling

description

a b s t r a c t A broad area in astronomy focuses on simulating extragalactic objects based on Very Long Baseline Interferometry (VLBI) radio-maps. Several algorithms in this scope simulate what would be the observed radio-maps if emitted from a predefined extragalactic object. This work analyzes the performance and scaling of this kind of algorithms on multi-socket, multi-core architectures. In particular, we evaluate a sharing approach, a privatizing approach and a hybrid approach on systems with complex memory hierarchy that includes shared Last Level Cache (LLC). In addition, we investigate which manual processes can be systematized and then automated in future works. The experiments show that the data- privatizing model scales efficiently on medium scale multi-socket, multi-core systems (up to 48 cores) while regardless of algorithmic and scheduling optimizations, the sharing approach is unable to reach acceptable scalability on more than one socket. However, the hybrid model with a specific level of data- sharing provides the best scalability over all used multi-socket, multi-core systems.

yearjournalcountryeditionlanguage
2012-09-01Computer Physics Communications, CPC, 1937-1946 (2012)
10.1016/j.cpc.2012.04.016http://dx.doi.org/10.1016/j.cpc.2012.04.016