Practical Temporal Prefetching With Compressed On-Chip Metadata

Autor:	Krishnendra Nathella, Hao Wu, Calvin Lin, Matthew Pabst, Dam Sunwoo, Akanksha Jain
Rok vydání:	2022
Předmět:	Instruction prefetch Hardware_MEMORYSTRUCTURES Database Computer science computer.software_genre Theoretical Computer Science Temporal database Metadata Computational Theory and Mathematics Hardware and Architecture Data_FILES computer Software Dram
Zdroj:	IEEE Transactions on Computers. 71:2858-2871
ISSN:	2326-3814 0018-9340
Popis:	Temporal prefetchers are powerful because they can prefetch irregular sequences of memory accesses, but temporal prefetchers are commercially infeasible because they store large amounts of metadata in DRAM. This paper presents Triage, the first temporal data prefetcher that does not require off-chip metadata. Triage builds on two insights: (1) Metadata are not equally useful, so the less useful metadata need not be saved, and (2) for irregular workloads, it is more profitable to use portions of the LLC to store metadata than data. We also introduce novel schemes to identify useful metadata, to compress metadata, and to determine the fraction of the LLC to dedicate for metadata.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::87d23d7d2e1da31596e94d155f5b32d4 https://doi.org/10.1109/tc.2021.3065909 Zobrazit plný text záznamu