Matches in SemOpenAlex for { <https://semopenalex.org/work/W4258857> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4258857 endingPage "152" @default.
- W4258857 startingPage "152" @default.
- W4258857 abstract "As the gap between processor and memory speed increases, using powerful processors in shared-memory multiprocessors will not be productive if they often stall waiting for the memory system to supply data and instructions. Moreover, as technology advances, data coherence-induced misses will become more important due to the larger and more integrated local memories that will make conflict misses relatively inexpensive.We make several contributions to cope with the problem of coherence-induced misses. First, we propose four producer-initiated data forwarding primitives designed to reduce the impact of coherence-induced misses. The primitives try to hide the latency by enabling the producers to send data to consumers right at the time that the data is written. Second, we present a compiler algorithm that replaces some of the regular writes by one of the proposed primitives and evaluate its performance effect. Finally, we compare our primitives with data prefetching and propose new techniques to integrate them.Using execution-driven simulations, we found that our algorithm for data forwarding reduces the execution time by an average of 30%-40%, depending on the size of the local memory hierarchy. Several optimizations helped increase the performance. In particular, we found that forwards should always be delayed and combined, both locally and in the directory. Also, forwards do not need to either update the memory of the home node or send the data all the way up to the second level cache.Our evaluation of data prefetching resulted in performance improvements of about 30%, regardless of the memory size. For the applications studied, while for the the average improvement of data forwarding is smaller than in data forwarding, neither technique outperforms the other in all cases. The proposed integrated techniques are able to further improve on the performance of either case, resulting in speedups of 48% on average, regardless of the size of the local memories." @default.
- W4258857 created "2016-06-24" @default.
- W4258857 creator A5016656726 @default.
- W4258857 creator A5055909708 @default.
- W4258857 date "1997-11-01" @default.
- W4258857 modified "2023-09-26" @default.
- W4258857 title "Architectural and compiler support to hide coherence misses in distributed shared-memory multiprocessors" @default.
- W4258857 hasPublicationYear "1997" @default.
- W4258857 type Work @default.
- W4258857 sameAs 4258857 @default.
- W4258857 citedByCount "0" @default.
- W4258857 crossrefType "journal-article" @default.
- W4258857 hasAuthorship W4258857A5016656726 @default.
- W4258857 hasAuthorship W4258857A5055909708 @default.
- W4258857 hasConcept C100800780 @default.
- W4258857 hasConcept C111919701 @default.
- W4258857 hasConcept C115537543 @default.
- W4258857 hasConcept C133875982 @default.
- W4258857 hasConcept C136085584 @default.
- W4258857 hasConcept C141917322 @default.
- W4258857 hasConcept C169590947 @default.
- W4258857 hasConcept C173608175 @default.
- W4258857 hasConcept C176649486 @default.
- W4258857 hasConcept C189783530 @default.
- W4258857 hasConcept C189930140 @default.
- W4258857 hasConcept C201148951 @default.
- W4258857 hasConcept C2778100165 @default.
- W4258857 hasConcept C3720319 @default.
- W4258857 hasConcept C38556500 @default.
- W4258857 hasConcept C39528615 @default.
- W4258857 hasConcept C41008148 @default.
- W4258857 hasConcept C51290061 @default.
- W4258857 hasConcept C91481028 @default.
- W4258857 hasConcept C98986596 @default.
- W4258857 hasConceptScore W4258857C100800780 @default.
- W4258857 hasConceptScore W4258857C111919701 @default.
- W4258857 hasConceptScore W4258857C115537543 @default.
- W4258857 hasConceptScore W4258857C133875982 @default.
- W4258857 hasConceptScore W4258857C136085584 @default.
- W4258857 hasConceptScore W4258857C141917322 @default.
- W4258857 hasConceptScore W4258857C169590947 @default.
- W4258857 hasConceptScore W4258857C173608175 @default.
- W4258857 hasConceptScore W4258857C176649486 @default.
- W4258857 hasConceptScore W4258857C189783530 @default.
- W4258857 hasConceptScore W4258857C189930140 @default.
- W4258857 hasConceptScore W4258857C201148951 @default.
- W4258857 hasConceptScore W4258857C2778100165 @default.
- W4258857 hasConceptScore W4258857C3720319 @default.
- W4258857 hasConceptScore W4258857C38556500 @default.
- W4258857 hasConceptScore W4258857C39528615 @default.
- W4258857 hasConceptScore W4258857C41008148 @default.
- W4258857 hasConceptScore W4258857C51290061 @default.
- W4258857 hasConceptScore W4258857C91481028 @default.
- W4258857 hasConceptScore W4258857C98986596 @default.
- W4258857 hasLocation W42588571 @default.
- W4258857 hasOpenAccess W4258857 @default.
- W4258857 hasPrimaryLocation W42588571 @default.
- W4258857 hasRelatedWork W1829481772 @default.
- W4258857 hasRelatedWork W1967092422 @default.
- W4258857 hasRelatedWork W1970077382 @default.
- W4258857 hasRelatedWork W2004578231 @default.
- W4258857 hasRelatedWork W2023522701 @default.
- W4258857 hasRelatedWork W2025597060 @default.
- W4258857 hasRelatedWork W2071474824 @default.
- W4258857 hasRelatedWork W2099880310 @default.
- W4258857 hasRelatedWork W2110807363 @default.
- W4258857 hasRelatedWork W2118788272 @default.
- W4258857 hasRelatedWork W2118839770 @default.
- W4258857 hasRelatedWork W2126233252 @default.
- W4258857 hasRelatedWork W2168887341 @default.
- W4258857 hasRelatedWork W2294192910 @default.
- W4258857 hasRelatedWork W2368622417 @default.
- W4258857 hasRelatedWork W2396497149 @default.
- W4258857 hasRelatedWork W2473283183 @default.
- W4258857 hasRelatedWork W2799398768 @default.
- W4258857 hasRelatedWork W5593215 @default.
- W4258857 hasRelatedWork W810194388 @default.
- W4258857 isParatext "false" @default.
- W4258857 isRetracted "false" @default.
- W4258857 magId "4258857" @default.
- W4258857 workType "article" @default.