dc.contributor.author | Asheim, Truls | |
dc.contributor.author | Grot, Boris | |
dc.contributor.author | Kumar, Rakesh | |
dc.date.accessioned | 2023-03-02T14:04:20Z | |
dc.date.available | 2023-03-02T14:04:20Z | |
dc.date.created | 2023-01-18T10:25:02Z | |
dc.date.issued | 2022 | |
dc.identifier.isbn | 978-1-6654-4278-7 | |
dc.identifier.uri | https://hdl.handle.net/11250/3055448 | |
dc.description.abstract | Contemporary server applications feature massive instruction footprints stemming from deeply layered software stacks. These footprints far exceed the capacity of the branch target buffer (BTB) and instruction cache (L1-I), resulting in the so-called front-end bottleneck. BTB misses may lead to wrong-path execution, triggering a pipeline flush when misspeculation is detected. Such pipeline flushes not only throw away tens of cycles of work but also expose the fill latency of the pipeline. Similarly, L1-I misses cause the core front-end to stall for tens of cycles while the miss is being served from lower-level caches. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | ACM | en_US |
dc.relation.ispartof | The 31st International Conference on Parallel Architectures and Compilation Techniques (PACT) | |
dc.rights | Navngivelse 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/deed.no | * |
dc.title | A Specialized BTB Organization for Servers | en_US |
dc.title.alternative | A Specialized BTB Organization for Servers | en_US |
dc.type | Chapter | en_US |
dc.description.version | acceptedVersion | en_US |
dc.identifier.doi | 10.1145/3559009.3569692 | |
dc.identifier.cristin | 2109152 | |
cristin.ispublished | true | |
cristin.fulltext | postprint | |