Matches in SemOpenAlex for { <https://semopenalex.org/work/W2090899906> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2090899906 endingPage "385" @default.
- W2090899906 startingPage "375" @default.
- W2090899906 abstract "In the current day wide-issue processors, the size of the instruction scheduling window (also called Issue Queue (IQ)) is limited mainly by the hardware complexity to design the logic, and thus limits the number of instructions scanned every cycle to extract instruction level parallelism (ILP). To exacerbate the problems, instructions depending on long latency load operations continue to reside in the IQ until their source operands are ready. Thus, such delayed instructions block any new instructions from entering the IQ even if potentially they are ready for execution. The growing disparity in processor and memory speeds is further aggravating the delay in dislodging instructions from IQ. To alleviate the problem, in this paper we propose a novel technique to streamline instructions in separate buffers according to the chain of dependencies. Each instruction is streamlined behind a parent instruction while it waits for the source operand to be supplied by the long latency memory operations. These instructions are segregated from the IQ and thus the pressure on IQ is relieved which enables flow of potentially executable instructions in the pipeline. Our analysis of SPEC2000 programs reveals that instructions dependent on load cache misses or their dependents, typically have their first source operand ready within 5-15% of their total wait time in the IQ. Based on the observations, the long latency memory dependent instructions are streamlined into in-order buffers when their first operand is ready. In the proposed architecture, instructions from both the conventional IQ and the heads of the streamline buffers can be selected for execution, while the wakeup logic complexity remains same as in the conventional design. Our results show that the performance speedup of 32-entry IQ supplemented by 32 in-order buffers is 15.7% and 2% for FP and integer benchmark respectively, which is very much comparable to that of a conventional 64-entry IQ. A 64-entry IQ design can gain performance over a 32-entry IQ, albeit with a large overhead in circuit delay complexity of wakeup logic, while streamline buffers can gain performance over 32-entry IQ without any such overhead." @default.
- W2090899906 created "2016-06-24" @default.
- W2090899906 creator A5048592666 @default.
- W2090899906 creator A5090366405 @default.
- W2090899906 date "2008-10-01" @default.
- W2090899906 modified "2023-10-18" @default.
- W2090899906 title "Streamlining long latency instructions for seamlessly combined out-of-order and in-order execution" @default.
- W2090899906 cites W2043649403 @default.
- W2090899906 cites W2104225326 @default.
- W2090899906 cites W2108039095 @default.
- W2090899906 cites W2133809341 @default.
- W2090899906 cites W2149379863 @default.
- W2090899906 cites W2156174665 @default.
- W2090899906 cites W2156263417 @default.
- W2090899906 cites W2161046276 @default.
- W2090899906 cites W2611258316 @default.
- W2090899906 cites W4230657362 @default.
- W2090899906 cites W4230658192 @default.
- W2090899906 cites W4232096869 @default.
- W2090899906 cites W4244330651 @default.
- W2090899906 cites W4253086812 @default.
- W2090899906 doi "https://doi.org/10.1016/j.micpro.2008.04.003" @default.
- W2090899906 hasPublicationYear "2008" @default.
- W2090899906 type Work @default.
- W2090899906 sameAs 2090899906 @default.
- W2090899906 citedByCount "1" @default.
- W2090899906 countsByYear W20908999062013 @default.
- W2090899906 crossrefType "journal-article" @default.
- W2090899906 hasAuthorship W2090899906A5048592666 @default.
- W2090899906 hasAuthorship W2090899906A5090366405 @default.
- W2090899906 hasConcept C10138342 @default.
- W2090899906 hasConcept C162324750 @default.
- W2090899906 hasConcept C173608175 @default.
- W2090899906 hasConcept C1793878 @default.
- W2090899906 hasConcept C182306322 @default.
- W2090899906 hasConcept C41008148 @default.
- W2090899906 hasConcept C76155785 @default.
- W2090899906 hasConcept C82876162 @default.
- W2090899906 hasConceptScore W2090899906C10138342 @default.
- W2090899906 hasConceptScore W2090899906C162324750 @default.
- W2090899906 hasConceptScore W2090899906C173608175 @default.
- W2090899906 hasConceptScore W2090899906C1793878 @default.
- W2090899906 hasConceptScore W2090899906C182306322 @default.
- W2090899906 hasConceptScore W2090899906C41008148 @default.
- W2090899906 hasConceptScore W2090899906C76155785 @default.
- W2090899906 hasConceptScore W2090899906C82876162 @default.
- W2090899906 hasIssue "7" @default.
- W2090899906 hasLocation W20908999061 @default.
- W2090899906 hasOpenAccess W2090899906 @default.
- W2090899906 hasPrimaryLocation W20908999061 @default.
- W2090899906 hasRelatedWork W1472213334 @default.
- W2090899906 hasRelatedWork W1531780705 @default.
- W2090899906 hasRelatedWork W1971506073 @default.
- W2090899906 hasRelatedWork W2051246013 @default.
- W2090899906 hasRelatedWork W2078081736 @default.
- W2090899906 hasRelatedWork W2139514495 @default.
- W2090899906 hasRelatedWork W2991043486 @default.
- W2090899906 hasRelatedWork W2993622056 @default.
- W2090899906 hasRelatedWork W3005600352 @default.
- W2090899906 hasRelatedWork W4247773078 @default.
- W2090899906 hasVolume "32" @default.
- W2090899906 isParatext "false" @default.
- W2090899906 isRetracted "false" @default.
- W2090899906 magId "2090899906" @default.
- W2090899906 workType "article" @default.