@inproceedings{2f9c561988d042d5bc8ebf6982b59d9e,
title = "Buffets: An Efficient and Composable Storage Idiom for Explicit Decoupled Data Orchestration",
abstract = "Accelerators spend significant area and effort on custom onchip buffering. Unfortunately, these solutions are strongly tied to particular designs, hampering re-usability across other accelerators or domains.We present buffets, an efficient and composable storage idiom for the needs of accelerators that is independent of any particular design. Buffets have several distinguishing characteristics, including efficient decoupled fills and accesses with fine-grained synchronization, hierarchical composition, and efficient multi-casting. We implement buffets in RTL and show that they only add 2% control overhead over an 8KB RAM. When compared with DMAmanaged double-buffered scratchpads and caches across a range of workloads, buffets improve energy-delay-product by 1.53× and 5.39×, respectively.",
keywords = "Accelerators, Data Orchestration, Staging Buffers, Synchronization",
author = "Michael Pellauer and Shao, {Yakun Sophia} and Jason Clemons and Neal Crago and Kartik Hegde and Rangharajan Ventakesan and Keckler, {Stephen W.} and Fletcher, {Christopher W.} and Joel Emer",
note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 24th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2019 ; Conference date: 13-04-2019 Through 17-04-2019",
year = "2019",
month = apr,
day = "4",
doi = "10.1145/3297858.3304025",
language = "English (US)",
series = "International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS",
publisher = "Association for Computing Machinery",
pages = "137--151",
booktitle = "ASPLOS 2019 - 24th International Conference on Architectural Support for Programming Languages and Operating Systems",
address = "United States",
}