Matches in SemOpenAlex for { <https://semopenalex.org/work/W2002058466> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2002058466 abstract "We present a power-aware neural network (PAN) branch prediction (BP) scheme for dynamic branch prediction, and schemes to incorporate anti-aliasing techniques into the neural branch predictor. We avoid incorrectly falling into segments of code that consume much power. By adding lookup table-based hardware, we estimate the power dissipated in the entire processor between successive branches. We consider a processor with a neural net branch predictor and use aggressive training on the neural network (NN) to severely penalize incorrect branch predictions that cause the processor to waste power. Our scheme dynamically learns to dissipate less power during successive calls to a particular branch instruction. Hence, our approach is different from all prior approaches that reduce miss-prediction or use hardware techniques (clock gating, banking) to reduce power dissipation. We also incorporate the conventional anti-aliasing techniques, such as GShare [1] and bimodal [2], into a NN-based BP, implemented in the SimpleScalar v2.0 [3] simulator. This is the first neural net branch predictor that reduces CPU power. Our new technique reduced power consumption by 11.6% on average for the SPEC2000 integer benchmark programs." @default.
- W2002058466 created "2016-06-24" @default.
- W2002058466 creator A5000335998 @default.
- W2002058466 creator A5020404037 @default.
- W2002058466 creator A5025371395 @default.
- W2002058466 creator A5083099798 @default.
- W2002058466 date "2007-01-01" @default.
- W2002058466 modified "2023-09-25" @default.
- W2002058466 title "A Neural Net Branch Predictor to Reduce Power" @default.
- W2002058466 cites W2025106479 @default.
- W2002058466 cites W2032094184 @default.
- W2002058466 cites W2034674049 @default.
- W2002058466 cites W2081211681 @default.
- W2002058466 cites W2127417436 @default.
- W2002058466 cites W2130363691 @default.
- W2002058466 cites W2130829030 @default.
- W2002058466 cites W2156484396 @default.
- W2002058466 cites W2167651816 @default.
- W2002058466 cites W2167691065 @default.
- W2002058466 cites W2782131086 @default.
- W2002058466 cites W4233056919 @default.
- W2002058466 cites W4239314300 @default.
- W2002058466 cites W4247472589 @default.
- W2002058466 doi "https://doi.org/10.1109/vlsid.2007.14" @default.
- W2002058466 hasPublicationYear "2007" @default.
- W2002058466 type Work @default.
- W2002058466 sameAs 2002058466 @default.
- W2002058466 citedByCount "6" @default.
- W2002058466 countsByYear W20020584662015 @default.
- W2002058466 countsByYear W20020584662018 @default.
- W2002058466 countsByYear W20020584662020 @default.
- W2002058466 crossrefType "proceedings-article" @default.
- W2002058466 hasAuthorship W2002058466A5000335998 @default.
- W2002058466 hasAuthorship W2002058466A5020404037 @default.
- W2002058466 hasAuthorship W2002058466A5025371395 @default.
- W2002058466 hasAuthorship W2002058466A5083099798 @default.
- W2002058466 hasConcept C121332964 @default.
- W2002058466 hasConcept C13280743 @default.
- W2002058466 hasConcept C134835016 @default.
- W2002058466 hasConcept C136536468 @default.
- W2002058466 hasConcept C154945302 @default.
- W2002058466 hasConcept C163258240 @default.
- W2002058466 hasConcept C168522837 @default.
- W2002058466 hasConcept C173608175 @default.
- W2002058466 hasConcept C185798385 @default.
- W2002058466 hasConcept C199360897 @default.
- W2002058466 hasConcept C205649164 @default.
- W2002058466 hasConcept C4069607 @default.
- W2002058466 hasConcept C41008148 @default.
- W2002058466 hasConcept C50644808 @default.
- W2002058466 hasConcept C62520636 @default.
- W2002058466 hasConceptScore W2002058466C121332964 @default.
- W2002058466 hasConceptScore W2002058466C13280743 @default.
- W2002058466 hasConceptScore W2002058466C134835016 @default.
- W2002058466 hasConceptScore W2002058466C136536468 @default.
- W2002058466 hasConceptScore W2002058466C154945302 @default.
- W2002058466 hasConceptScore W2002058466C163258240 @default.
- W2002058466 hasConceptScore W2002058466C168522837 @default.
- W2002058466 hasConceptScore W2002058466C173608175 @default.
- W2002058466 hasConceptScore W2002058466C185798385 @default.
- W2002058466 hasConceptScore W2002058466C199360897 @default.
- W2002058466 hasConceptScore W2002058466C205649164 @default.
- W2002058466 hasConceptScore W2002058466C4069607 @default.
- W2002058466 hasConceptScore W2002058466C41008148 @default.
- W2002058466 hasConceptScore W2002058466C50644808 @default.
- W2002058466 hasConceptScore W2002058466C62520636 @default.
- W2002058466 hasLocation W20020584661 @default.
- W2002058466 hasOpenAccess W2002058466 @default.
- W2002058466 hasPrimaryLocation W20020584661 @default.
- W2002058466 hasRelatedWork W112744582 @default.
- W2002058466 hasRelatedWork W1485630101 @default.
- W2002058466 hasRelatedWork W1592260050 @default.
- W2002058466 hasRelatedWork W2002058466 @default.
- W2002058466 hasRelatedWork W2071868606 @default.
- W2002058466 hasRelatedWork W2086475872 @default.
- W2002058466 hasRelatedWork W2498017833 @default.
- W2002058466 hasRelatedWork W3217435224 @default.
- W2002058466 hasRelatedWork W4241263734 @default.
- W2002058466 hasRelatedWork W4384947512 @default.
- W2002058466 isParatext "false" @default.
- W2002058466 isRetracted "false" @default.
- W2002058466 magId "2002058466" @default.
- W2002058466 workType "article" @default.