{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T13:14:31Z","timestamp":1725455671400},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540637660"},{"type":"electronic","value":"9783540696445"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1997]]},"DOI":"10.1007\/bfb0024210","type":"book-chapter","created":{"date-parts":[[2005,11,19]],"date-time":"2005-11-19T02:51:07Z","timestamp":1132368667000},"page":"119-130","source":"Crossref","is-referenced-by-count":1,"title":["Data dependence path reduction with tunneling load instructions"],"prefix":"10.1007","author":[{"given":"Toshinori","family":"Sato","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2005,6,9]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"T.M.Austin et al., \u201cStreamlining data cache access with fast address calculation\u201d, Proc. of ISCA22, pp.369\u2013380, 1995.","DOI":"10.1145\/223982.224447"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"T.M.Austin et al., \u201cZero-cycle loads: microarchitecture support for reducing load latency\u201d, Proc. of MICRO28, pp.82\u201392, 1995.","DOI":"10.1109\/MICRO.1995.476815"},{"key":"11_CR3","unstructured":"D.Burger et al., \u201cEvaluating future microprocessors: the SimpleScalar tool set\u201d, Technical Report CS-TR-96-1308, University of Wisconsin Madison, July 1996."},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"A.Capitanio et al., \u201cPartitioned register files for VLIWs: a preliminary analysis of tradeoffs\u201d, Proc. of MICRO25, pp.292\u2013300, 1992.","DOI":"10.1145\/144965.145839"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"P.P.Chang et al., \u201cIMPACT: an architectural framework for multiple-instruction-issue processors\u201d, Proc. of ISCA18, pp.266\u2013275, 1991.","DOI":"10.1145\/115952.115979"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"P.P.Chang et al., \u201cComparing static and dynamic code scheduling for multiple-instruction-issue processors\u201d, Proc. of MICRO24, pp.25\u201333, 1991.","DOI":"10.1145\/123465.123471"},{"issue":"5","key":"11_CR7","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1109\/12.381947","volume":"44","author":"T-F. Chen","year":"1995","unstructured":"T-F.Chen et al., \u201cEffective hardware-based data prefetching for high-performance processors\u201d, IEEE Trans. Computers, vol.44, no.5, pp.609\u2013623, May 1995.","journal-title":"IEEE Trans. Computers"},{"issue":"4","key":"11_CR8","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1147\/rd.374.0547","volume":"37","author":"R.J. Eickemeyer","year":"1993","unstructured":"R.J.Eickemeyer et al., \u201cA load-instruction unit for pipelined processors\u201d, IBM J. Res. Develop., Vol.37, No.4, pp.547\u2013564, July 1993.","journal-title":"IBM J. Res. Develop."},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"K.I.Farkas et al., \u201cComplexity \/performance tradeoffs with non-blocking loads\u201d, Proc. of ISCA21, pp.211\u2013222, 1994.","DOI":"10.1109\/ISCA.1994.288148"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"M.Franklin et al., \u201cRegister traffic analysis for streamlining inter-operation communication in fine-grain parallel processors\u201d, Proc. of MICRO25, pp.236\u2013245, 1992.","DOI":"10.1109\/MICRO.1992.697025"},{"key":"11_CR11","unstructured":"M.Golden et al., \u201cHardware support for hiding cache latency\u201d, Technical Report CSE-TR-152-93, University of Michigan, Feb. 1993."},{"issue":"4","key":"11_CR12","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1145\/356654.356657","volume":"7","author":"R.M. Keller","year":"1975","unstructured":"R.M.Keller, \u201cLook-ahead processors\u201d, ACM Computing Surveys, vol.7, No.4, pp.177\u2013195, Dec. 1975.","journal-title":"ACM Computing Surveys"},{"key":"11_CR13","unstructured":"S.McFarling, \u201cCombining branch predictors\u201d, WRL Technical Note TN-36, Digital Western Research Laboratory, 1993."},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"T.C.Mowry et al., \u201cDesign and evaluation of a compiler algorithm for prefetching\u201d, Proc. of ASPLOS V, pp.62\u201373, 1992.","DOI":"10.1145\/143365.143488"},{"issue":"11","key":"11_CR15","first-page":"1523","volume":"E79-D","author":"T. Sato","year":"1996","unstructured":"T.Sato et al., \u201cHiding data cache latency with load address prediction\u201d, IEICE Trans. Inf. & Syst., vol.E79-D, no.11, pp.1523\u20131532, Nov. 1996.","journal-title":"IEICE Trans. Inf. & Syst."},{"key":"11_CR16","unstructured":"T.Sato, \u201cData dependence speculation combining memory disambiguation with address prediction\u201d, Proc. of SWoPP'97 (IPSJ SIG Notes, Aug. 1997."},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"S.Wallace et al., \u201cA scalable register file architecture for dynamically scheduled processors\u201d, Proc. of PACT'96, pp.179\u2013184, 1996.","DOI":"10.1109\/PACT.1996.552666"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/BFb0024210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,2,4]],"date-time":"2019-02-04T17:32:39Z","timestamp":1549301559000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/BFb0024210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1997]]},"ISBN":["9783540637660","9783540696445"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/bfb0024210","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[1997]]}}}