dc.contributor.author | Ahmed Khan, Tanvir | |
dc.contributor.author | Brown, Nathan | |
dc.contributor.author | Sriraman, Akshitha | |
dc.contributor.author | Soundararajan, Niranjan | |
dc.contributor.author | Kumar, Rakesh | |
dc.contributor.author | Devietti, Joseph | |
dc.contributor.author | Subramoney, Sreenivas | |
dc.contributor.author | Pokam, Gilles | |
dc.contributor.author | Litz, Heiner | |
dc.contributor.author | Kasikci, Baris | |
dc.date.accessioned | 2022-03-25T12:56:07Z | |
dc.date.available | 2022-03-25T12:56:07Z | |
dc.date.created | 2022-01-04T15:10:32Z | |
dc.date.issued | 2021 | |
dc.identifier.isbn | 978-1-4503-8557-2 | |
dc.identifier.uri | https://hdl.handle.net/11250/2987667 | |
dc.description.abstract | Modern data center applications have deep software stacks, with instruction footprints that are orders of magnitude larger than typical instruction cache (I-cache) sizes. To efficiently prefetch instructions into the I-cache despite large application footprints, modern server-class processors implement a decoupled frontend with Fetch Directed Instruction Prefetching (FDIP). In this work, we first characterize the limitations of a decoupled frontend processor with FDIP and find that FDIP suffers from significant Branch Target Buffer (BTB) misses. We also find that existing techniques (e.g., stream prefetchers and predecoders) are unable to mitigate these misses, as they rely on an incomplete understanding of a program’s branching behavior. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Association for Computing Machinery (ACM) | en_US |
dc.relation.ispartof | MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture | |
dc.title | Twig: Profile-Guided BTB Prefetching for Data Center Applications | en_US |
dc.type | Chapter | en_US |
dc.description.version | acceptedVersion | en_US |
dc.source.pagenumber | 816-829 | en_US |
dc.identifier.doi | 10.1145/3466752.3480124 | |
dc.identifier.cristin | 1974535 | |
dc.description.localcode | © ACM. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. | en_US |
cristin.ispublished | true | |
cristin.fulltext | preprint | |
cristin.qualitycode | 1 | |