RT info:eu-repo/semantics/conferenceObject
T1 Four abstract array distribution operators
A1 Moretón, Ana
A1 González Escribano, Arturo
A1 Llanos Ferraris, Diego Rafael
K1 Informática
K1 Distributed-memory systems
K1 Data redistributions
K1 External libraries
K1 1203 Ciencia de Los Ordenadores
K1 3304 Tecnología de Los Ordenadores
AB Programming for distributed-memory systems imposes specific challenges. In these systems, minimizing synchronization and communication overheads is key for performance improvement. A typical approach is to use a message-passing paradigm to exploit static partition policies and to generate coarse-grain computations with aggregated communication phases. However, irregular or data-dependent programs that need dynamic data redistributions become more complicated to develop and debug. In this paper we present four abstract array distribution operators that allow to efficiently implement programs on distributed-memory systems, making the data partition, relocation, and data movement transparent to the programmer. Our experimental results show that our approach does not imply significant overheads, while achieving good scalability for combinations of data-dependent, irregular, or recursive parallel structures on distributed-memory systems.
YR 2016
FD 2016
LK https://uvadoc.uva.es/handle/10324/70445
UL https://uvadoc.uva.es/handle/10324/70445
LA eng
NO Intl. Symp. on High Level Parallel Programming and Applications (HLPP 2016), Münster, Germany.
NO Producción Científica
DS UVaDOC
RD 18-nov-2024