RT info:eu-repo/semantics/article
T1 Supporting efficient overlapping of host-device operations for heterogeneous programming with CtrlEvents
A1 Torres de la Sierra, Yuri
A1 Andújar Muñoz, Francisco José
A1 González Escribano, Arturo
A1 Llanos Ferraris, Diego Rafael
K1 Informática
K1 Computers
K1 Programación de ordenadores
K1 Parallel programming
K1 Heterogeneous programming
K1 Asynchronous operations
K1 GPUs
K1 Programación paralela
K1 Programación heterogénea
K1 Operaciones asincrónicas
K1 GPU
K1 1203.17 Informática
AB Heterogeneous systems with several kinds of devices, such as multi-core CPUs, GPUs, FPGAs, among others, are now commonplace. Exploiting all these devices with device-oriented programming models, such as CUDA or OpenCL, requires expertise and knowledge about the underlying hardware to tailor the application to each specific device, thus degrading performance portability. Higher-level proposals simplify the programming of these devices, but their current implementations do not have an efficient support to solve problems that include frequent bursts of computation and communication, or input/output operations. In this work we present CtrlEvents, a new heterogeneous runtime solution which automatically overlaps computation and communication whenever possible, simplifying and improving the efficiency of data-dependency analysis and the coordination of both device computations and host tasks that include generic I/O operations. Our solution outperforms other state-of-the-art implementations for most situations, presenting a good balance between portability, programmability and efficiency.
PB Elsevier
SN 0743-7315
YR 2023
FD 2023
LK https://uvadoc.uva.es/handle/10324/59529
UL https://uvadoc.uva.es/handle/10324/59529
LA eng
NO Journal of Parallel and Distributed Computing, 2023, vol. 179, 104708
NO Producción Científica
DS UVaDOC
RD 17-may-2024