Ripple: Asynchronous Programming for Spatial Dataflow Architectures
Proceedings of the ACM on Programming Languages · 10.06.2025 · 9 (PLDI) · 249-276
DOI: 10.1145/3729256 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Programming Languages, online erschienen am 13.06.2025. Verfasst von Souradip Ghosh und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 90 Literaturangaben. Gefördert von: NSF, U.S. Department of Energy Computational Science Graduate Fellowship.
Abstract (Originalsprache)
Spatial dataflow architectures (SDAs) are a promising and versatile accelerator platform. They are software-programmable and achieve near-ASIC performance and energy efficiency, beating CPUs by orders of magnitude. Unfortunately, many SDAs struggle to efficiently implement irregular computations because they suffer from an abstraction inversion: they fail to capture coarse-grain dataflow semantics in the application — namely asynchronous communication, pipelining, and queueing — that are naturally supported by the dataflow execution model and existing SDA hardware. Ripple is a language and architecture that corrects the abstraction inversion by preserving dataflow semantics down the stack. Ripple provides asynchronous iterators , shared-memory atomics , and a familiar task-parallel interface to concisely express the asynchronous pipeline parallelism enabled by an SDA. Ripple efficiently implements deadlock-free, asynchronous task communication by exposing hardware token queues in its ISA. Across nine important workloads, compared to a recent ordered-dataflow SDA, Ripple shrinks programs by 1.9×, improves performance by 3×, increases IPC by 58%, and reduces dynamic instructions by 44%.
Förderung
- NSF
- U.S. Department of Energy Computational Science Graduate Fellowship
Zitieren
APA
Ghosh, S., Shi, Y., Lucia, B., & Beckmann, N. (2025). Ripple: Asynchronous Programming for Spatial Dataflow Architectures. Proceedings of the ACM on Programming Languages, 9(PLDI), 249-276. https://doi.org/10.1145/3729256
Vancouver
Ghosh S, Shi Y, Lucia B, Beckmann N. Ripple: Asynchronous Programming for Spatial Dataflow Architectures. Proceedings of the ACM on Programming Languages. 2025;9(PLDI):249-276. doi:10.1145/3729256
BibTeX
@article{Ghosh2025,
author = {Ghosh, Souradip and Shi, Yufei and Lucia, Brandon and Beckmann, Nathan},
title = {Ripple: Asynchronous Programming for Spatial Dataflow Architectures},
journal = {Proceedings of the ACM on Programming Languages},
year = {2025},
volume = {9},
number = {PLDI},
pages = {249--276},
doi = {10.1145/3729256}
}
EUVIMED