Matches in SemOpenAlex for { <https://semopenalex.org/work/W1544472241> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W1544472241 abstract "The widely acknowledged performance gap between processors and memory has been the subject of much research. In the Explicitly Parallel Instruction Computing (EPIC) paradigm, the combination of in-order issue and the presence of a large number of parallel function units has further worsen the problem. Prefetching, by hardware, software or a combination of both, has been one of the primary mechanisms to alleviate this problem. In this talk, we will discuss two prefetching mechanisms, one hardware and other software, suitable for implementation in EPIC processors. Both methods rely on the off-line learning of Markovian predictors. In the hardware mechanism, the predictors are loaded into a table that is used by a prefetch engine. We have shown that the method is particularly effective for prefetching into the L2 cache. Our software mechanism which we called predicated prefetch leverages on informing loads. This is used in conjunction with data remapping and offline learning of Markovian predictors. This distinguishes our approach from early software prefetching techniques that only involves static program analysis. Our experiments show that this framework, together with the algorithms used in it, can effectively remove, in the best instance, 30% of the stall cycles due to cache misses. The results also show that the framework performs better than pure hardware stride predictors and has lower bandwidth and instruction overheads than that of pure software approaches. [Full Text Not Available]" @default.
- W1544472241 created "2016-06-24" @default.
- W1544472241 creator A5060709175 @default.
- W1544472241 date "2003-01-01" @default.
- W1544472241 modified "2023-09-27" @default.
- W1544472241 title "Data Prefetching via Off-line Learning" @default.
- W1544472241 hasPublicationYear "2003" @default.
- W1544472241 type Work @default.
- W1544472241 sameAs 1544472241 @default.
- W1544472241 citedByCount "0" @default.
- W1544472241 crossrefType "journal-article" @default.
- W1544472241 hasAuthorship W1544472241A5060709175 @default.
- W1544472241 hasConcept C111919701 @default.
- W1544472241 hasConcept C115519274 @default.
- W1544472241 hasConcept C115537543 @default.
- W1544472241 hasConcept C124952713 @default.
- W1544472241 hasConcept C133588205 @default.
- W1544472241 hasConcept C142362112 @default.
- W1544472241 hasConcept C173608175 @default.
- W1544472241 hasConcept C189783530 @default.
- W1544472241 hasConcept C2777904410 @default.
- W1544472241 hasConcept C41008148 @default.
- W1544472241 hasConceptScore W1544472241C111919701 @default.
- W1544472241 hasConceptScore W1544472241C115519274 @default.
- W1544472241 hasConceptScore W1544472241C115537543 @default.
- W1544472241 hasConceptScore W1544472241C124952713 @default.
- W1544472241 hasConceptScore W1544472241C133588205 @default.
- W1544472241 hasConceptScore W1544472241C142362112 @default.
- W1544472241 hasConceptScore W1544472241C173608175 @default.
- W1544472241 hasConceptScore W1544472241C189783530 @default.
- W1544472241 hasConceptScore W1544472241C2777904410 @default.
- W1544472241 hasConceptScore W1544472241C41008148 @default.
- W1544472241 hasLocation W15444722411 @default.
- W1544472241 hasOpenAccess W1544472241 @default.
- W1544472241 hasPrimaryLocation W15444722411 @default.
- W1544472241 hasRelatedWork W1509928333 @default.
- W1544472241 hasRelatedWork W1996564291 @default.
- W1544472241 hasRelatedWork W2024043936 @default.
- W1544472241 hasRelatedWork W2063389777 @default.
- W1544472241 hasRelatedWork W2122287586 @default.
- W1544472241 hasRelatedWork W2122963045 @default.
- W1544472241 hasRelatedWork W2131771728 @default.
- W1544472241 hasRelatedWork W2134694138 @default.
- W1544472241 hasRelatedWork W224358607 @default.
- W1544472241 hasRelatedWork W2916093129 @default.
- W1544472241 hasRelatedWork W2941917372 @default.
- W1544472241 hasRelatedWork W2946029344 @default.
- W1544472241 hasRelatedWork W2951689436 @default.
- W1544472241 hasRelatedWork W2956110135 @default.
- W1544472241 hasRelatedWork W2987836911 @default.
- W1544472241 hasRelatedWork W2995759203 @default.
- W1544472241 hasRelatedWork W3043167609 @default.
- W1544472241 hasRelatedWork W3082924504 @default.
- W1544472241 hasRelatedWork W3137433939 @default.
- W1544472241 hasRelatedWork W3091118039 @default.
- W1544472241 isParatext "false" @default.
- W1544472241 isRetracted "false" @default.
- W1544472241 magId "1544472241" @default.
- W1544472241 workType "article" @default.