{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:16:21Z","timestamp":1763468181392},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,10,24]],"date-time":"2013-10-24T00:00:00Z","timestamp":1382572800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1007\/s11227-013-1033-5","type":"journal-article","created":{"date-parts":[[2013,10,23]],"date-time":"2013-10-23T17:00:10Z","timestamp":1382547610000},"page":"157-182","source":"Crossref","is-referenced-by-count":11,"title":["A workload independent energy reduction strategy for D-NUCA caches"],"prefix":"10.1007","volume":"68","author":[{"given":"Pierfrancesco","family":"Foglia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Comparetti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,10,24]]},"reference":[{"key":"1033_CR1","first-page":"211","volume-title":"Proc 10th ASPLOS","author":"C Kim","year":"2002","unstructured":"Kim C, Burger D, Keckler SW (2002) An adaptive, non-uniform cache structure for wire-delay dominated on-chip caches. In: Proc 10th ASPLOS, San Jose, CA, USA, Oct 2002, pp 211\u2013222"},{"issue":"3\/4","key":"1033_CR2","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1504\/IJHPSA.2010.034542","volume":"2","author":"A Bardine","year":"2010","unstructured":"Bardine A, Comparetti M, Foglia P, Gabrielli G, Prete CA (2010) Way-adaptable D-NUCA caches. Int J High Perform Syst Archit 2(3\/4):215\u2013228","journal-title":"Int J High Perform Syst Archit"},{"key":"1033_CR3","unstructured":"Standard Performance Evaluation Corporation (2000) Available: http:\/\/www.spec.org\/cpu2000\/"},{"key":"1033_CR4","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1145\/125826.125925","volume-title":"Proceedings of the 1991 ACM\/IEEE conference on supercomputing","author":"DH Bailey","year":"1991","unstructured":"Bailey DH, Barszcz E et al (1991) The NAS parallel benchmarks\u2014summary and preliminary results. In: Proceedings of the 1991 ACM\/IEEE conference on supercomputing. ACM, New York, pp 158\u2013165. Available http:\/\/www.nas.nasa.gov\/Resources\/Software\/npb.html"},{"key":"1033_CR5","first-page":"90","volume-title":"Proc int symp low power electronics and design","author":"M Powell","year":"2000","unstructured":"Powell M, Yangh S, Falsafi B, Roy K, Vijaykumar TN (2000) Gated-Vdd: a\u00a0circuit technique to reduce leakage in deep-submicron cache memories. In: Proc int symp low power electronics and design, Rapallo, Italy, July 2000, pp 90\u201395"},{"key":"1033_CR6","unstructured":"Desikan R et\u00a0al (2001) Sim-Alpha: a validated execution-driven alpha2164 simulator. Tech Report TR-01-23, Dept of Computer Sciences, Univ Texas at Austin"},{"key":"1033_CR7","unstructured":"Muralimanohar N, Balasubramonian R, Jouppi N (2009) CACTI 6.0: a tool to model large caches. HP Tech Rep, HPL-2009-85, April 2009"},{"key":"1033_CR8","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1145\/378993.379244","volume-title":"Proc of the 9th ASPLOS","author":"A Snavely","year":"2000","unstructured":"Snavely A, Tullsen DM (2000) Symbiotic jobscheduling for a simultaneous multithreading processor. In: Proc of the 9th ASPLOS, Cambridge, MA, Nov 2000, pp 234\u2013244"},{"key":"1033_CR9","first-page":"55","volume-title":"Proc 36th int symp on microarchitecture","author":"Z Chisti","year":"2003","unstructured":"Chisti Z, Powell MD, Vijaykumar TN (2003) Distance associativity for high-performance energy-efficient non-uniform cache architectures. In: Proc 36th int symp on microarchitecture, San Diego, CA, Dec 2003, pp 55\u201366"},{"key":"1033_CR10","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/ESTMED.2005.1518068","volume-title":"IEEE 2005 workshop on embedded systems for real-time multimedia (ESTIMEDIA)","author":"P Foglia","year":"2005","unstructured":"Foglia P, Mangano D, Prete CA (2005) A\u00a0NUCA model for embedded systems cache design. In: IEEE 2005 workshop on embedded systems for real-time multimedia (ESTIMEDIA), New York Metropolitan Area, USA, September 2005, pp\u00a041\u201346"},{"key":"1033_CR11","volume-title":"Proc of the 19th ICS","author":"J Huh","year":"2005","unstructured":"Huh J, Kim C, Shafi H, Zhang L, Bourger D, Keckler SW (2005) A\u00a0NUCA substrate for flexible CMP cache sharing. In: Proc of the 19th ICS, Cambridge, MA, 20\u201322 June 2005"},{"key":"1033_CR12","first-page":"55","volume-title":"Proc of 37th int symp on microarchitecture","author":"BM Beckmann","year":"2003","unstructured":"Beckmann BM, Wood DA (2003) Managing wire delay in large chip-multiprocessors caches. In: Proc of 37th int symp on microarchitecture, San Diego, CA, Dec 2003, pp 55\u201366"},{"issue":"6","key":"1033_CR13","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1016\/j.cad.2012.01.009","volume":"44","author":"A Annoni","year":"2012","unstructured":"Annoni A et al (2012) A real-time configurable NURBS interpolator with bounded acceleration, Jerk and Chord error. Comput Aided Des 44(6):509\u2013521. doi: 10.1016\/j.cad.2012.01.009","journal-title":"Comput Aided Des"},{"issue":"5","key":"1033_CR14","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1049\/iet-cdt.2008.0078","volume":"3","author":"A Bardine","year":"2009","unstructured":"Bardine A et al (2009) Impact of on-chip network parameters on NUCA cache performance. IET Comput Digit Tech 3(5):501\u2013512. doi: 10.1049\/ietcdt.2008.0078","journal-title":"IET Comput Digit Tech"},{"key":"1033_CR15","first-page":"105","volume-title":"Proc of the MEDEA 2007 workshop","author":"A Bardine","year":"2007","unstructured":"Bardine A, Foglia P, Gabrielli G, Prete CA (2007) Analysis of static and dynamic energy consumption in NUCA caches: initial results. In: Proc of the MEDEA 2007 workshop, Brasov, Romania, Sep 2007, pp 105\u2013112"},{"issue":"3","key":"1033_CR16","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1145\/1108956.1108957","volume":"37","author":"V Venkatachalam","year":"2005","unstructured":"Venkatachalam V, Franz M (2005) Power reduction techniques for microprocessor systems. ACM Comput Surv 37(3):195\u2013237","journal-title":"ACM Comput Surv"},{"key":"1033_CR17","first-page":"248","volume-title":"Proc 32nd int symp on microarchitecture","author":"DH Albonesi","year":"1999","unstructured":"Albonesi DH (1999) Selective cache ways: on-demand cache resource allocation. In: Proc 32nd int symp on microarchitecture, Israel, Nov 1999, pp 248\u2013259"},{"key":"1033_CR18","first-page":"245","volume-title":"Proc 33rd int symp on microarchitecture","author":"R Balasubramonian","year":"2000","unstructured":"Balasubramonian R et al (2000) Memory hierarchy reconfiguration for energy and performance in general purpose processor architectures. In: Proc 33rd int symp on microarchitecture, Monterey, CA, Dec 2000, pp 245\u2013257"},{"key":"1033_CR19","author":"A Bardine","year":"2013","unstructured":"Bardine A et al (2013) Evaluation of leakage reduction alternatives for deep sub-micron D-NUCA caches. IEEE Trans Very Large Scale Integr (VLSI) Syst. doi: 10.1109\/TVLSI.2012.2231949 , published on-line Feb 2013","journal-title":"IEEE Trans Very Large Scale Integr (VLSI) Syst"},{"issue":"3","key":"1033_CR20","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/TVLSI.2003.812370","volume":"11","author":"H Hanson","year":"2003","unstructured":"Hanson H et al (2003) Static energy reduction techniques for microprocessor caches. IEEE Trans Very Large Scale Integr (VLSI) Syst 11(3):303\u2013313","journal-title":"IEEE Trans Very Large Scale Integr (VLSI) Syst"},{"key":"1033_CR21","first-page":"148","volume-title":"Proc 29th ISCA","author":"K Flautner","year":"2002","unstructured":"Flautner K, Kim NS, Blaauw SMD, Mudge T (2002) Drowsy caches: simple techniques for reducing leakage power. In: Proc 29th ISCA, Anchorage, AK, May 2002, pp 148\u2013157"},{"key":"1033_CR22","first-page":"161","volume-title":"Proc 2nd conf on computing frontiers","author":"N Mohyuddin","year":"2005","unstructured":"Mohyuddin N, Bhatti R, Dubois M (2005) Controlling leakage power with the replacement policy in slumberous cache. In: Proc 2nd conf on computing frontiers, Ischia, Italy, May 2005, pp 161\u2013170"},{"issue":"2","key":"1033_CR23","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1145\/507052.507055","volume":"20","author":"Z Hu","year":"2002","unstructured":"Hu Z, Kaxiras S, Martonosi M (2002) Let caches decay: reducing leakage energy via exploitation of cache generational behavior. ACM Trans Comput Syst 20(2):161\u2013190","journal-title":"ACM Trans Comput Syst"},{"issue":"3","key":"1033_CR24","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MM.2008.44","volume":"28","author":"S Eyerman","year":"2008","unstructured":"Eyerman S, Eeckhout L (2008) System-level performance metrics for multiprogram workloads. IEEE MICRO 28(3):42\u201353","journal-title":"IEEE MICRO"},{"key":"1033_CR25","volume-title":"Proceedings of the 56th international solid state circuits conference (ISSCC)","author":"R Kumar","year":"2009","unstructured":"Kumar R, Hinton G (2009) A\u00a0family of 45 nm IA processors. In: Proceedings of the 56th international solid state circuits conference (ISSCC), February 2009"},{"issue":"1","key":"1033_CR26","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1109\/JSSC.2010.2079430","volume":"46","author":"NA Kurd","year":"2010","unstructured":"Kurd NA, Bhamidipati S, Mozak C et al (2010) A\u00a0family of 32 nm IA processors. IEEE J Solid-State Circuits 46(1):119\u2013130","journal-title":"IEEE J Solid-State Circuits"},{"key":"1033_CR27","unstructured":"Agny R, DeLano E, Kumar M, Nachimutu M, Shiveley R (2010) The Intel Itanium processor 9300 series. Intel White Paper"},{"key":"1033_CR28","first-page":"8","volume-title":"Proc IEEE symposium on low power electronics","author":"M Horowitz","year":"1994","unstructured":"Horowitz M, Indermaur T, Gonzales R (1994) Low-power digital design. In: Proc IEEE symposium on low power electronics, pp 8\u201311"},{"key":"1033_CR29","first-page":"49","volume-title":"21st int symp on computer architecture and high performance computing","author":"P Foglia","year":"2009","unstructured":"Foglia P, Panicucci F, Prete CA, Solinas M (2009) Analysis of performance dependencies in NUCA-based CMP systems. In: 21st int symp on computer architecture and high performance computing, Sao Paulo, Brazil, 28\u201331 October 2009, pp 49\u201356"},{"key":"1033_CR30","first-page":"9","volume-title":"Proc of 9th MEDEA workshop","author":"I Kotera","year":"2008","unstructured":"Kotera I, Egawa R, Takizawa H, Kobayashi H (2008) Modeling of cache access behavior based on Zipf\u2019s law. In: Proc of 9th MEDEA workshop, Toronto, Canada, October 2008, pp 9\u201315"},{"issue":"3","key":"1033_CR31","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1145\/1101868.1101874","volume":"33","author":"H Kobayashi","year":"2004","unstructured":"Kobayashi H, Kotera I, Takizawa H (2004) Locality analysis to control dynamically way-adaptable caches. Comput Archit News 33(3):25\u201332","journal-title":"Comput Archit News"},{"key":"1033_CR32","unstructured":"S.I.A. Int. Technology Roadmap for Semiconductors (2005) http:\/\/public.itrs.net\/Links\/2005ITRS\/Home2005.htm"},{"issue":"12","key":"1033_CR33","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1109\/MC.2003.1250885","volume":"36","author":"NS Kim","year":"2003","unstructured":"Kim NS et al (2003) Leakage current: Moore\u2019s law meets static power. Computer 36(12):68\u201375","journal-title":"Computer"},{"key":"1033_CR34","first-page":"199","volume-title":"Proc 13th EUROMICRO conference on digital system design, architectures, methods and tools","author":"P Foglia","year":"2010","unstructured":"Foglia P, Monni G, Prete CA, Solinas M (2010) Re-nuca: boosting CMP performances through block replication. In: Proc 13th EUROMICRO conference on digital system design, architectures, methods and tools, Lille, France, 1\u20133 September 2010, pp 199\u2013206"},{"key":"1033_CR35","doi-asserted-by":"crossref","unstructured":"Foglia P, Solinas M (2013) Exploiting replication to improve performances of NUCA-based CMP systems. ACM Trans Embed Comput Syst. Accepted September 2013, to appear","DOI":"10.1145\/2566568"},{"key":"1033_CR36","volume-title":"Proc of the 39th annual IEEE\/ACM int symp on microarchitecture (MICRO\u00a039)","author":"MK Qureshi","year":"2006","unstructured":"Qureshi MK, Patt YN (2006) Utility-based cache partitioning: a\u00a0low-overhead, high-performance, runtime mechanism to partition shared caches. In: Proc of the 39th annual IEEE\/ACM int symp on microarchitecture (MICRO\u00a039)"},{"key":"1033_CR37","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1007\/978-3-642-11515-8_20","volume-title":"Proc of the int conf on high-performance embedded architectures and compilers (HiPEAC)","author":"Y Xie","year":"2010","unstructured":"Xie Y, Loh GH (2010) Scalable shared cache management by containing thrashing workloads. In: Proc of the int conf on high-performance embedded architectures and compilers (HiPEAC), Pisa, Italy, 25\u201327 January 2010, pp 262\u2013276"},{"key":"1033_CR38","volume-title":"Proc of design automation and test in Europe (DATE)","author":"A Kahng","year":"2009","unstructured":"Kahng A, Li B, Peh L-S, Samadi K (2009) ORION 2.0: a\u00a0fast and accurate NoC power and area model for early-stage design space exploration. In: Proc of design automation and test in Europe (DATE), Nice, France, April 2009"},{"key":"1033_CR39","volume-title":"Proc of 27th ISCA","author":"V Agarwal","year":"2000","unstructured":"Agarwal V, Hrishikesh MS, Keckler S, Burger D (2000) Clock rate versus IPC: the end of the road for conventional microarchitectures. In: Proc of 27th ISCA, June 2000"},{"issue":"4","key":"1033_CR40","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1109\/5.920580","volume":"89","author":"R Ho","year":"2001","unstructured":"Ho R, Mai KW, Horowitz MA (2001) The future of wires. Proc IEEE 89(4):490\u2013504","journal-title":"Proc IEEE"},{"key":"1033_CR41","author":"RL Mattson","year":"1970","unstructured":"Mattson RL, Gecsei J, Slutz D, Traiger I (1970) Evaluation techniques for storage hierarchies. IBM Syst\u00a0J. doi: 10.1147\/sj.92.0078","journal-title":"IBM Syst\u00a0J"},{"key":"1033_CR42","volume-title":"12th intl workshop on languages and compilers for parallel computing","author":"C Cascaval","year":"1999","unstructured":"Cascaval C, DeRose L, Padua DA, Reed D (1999) Compile-time based performance prediction. In: 12th intl workshop on languages and compilers for parallel computing"},{"issue":"2","key":"1033_CR43","first-page":"149","volume":"3","author":"I Kotera","year":"2008","unstructured":"Kotera I, Abe K, Egawa R, Takizawa H, Kobayashi H (2008) Power-aware dynamic cache partitionning for cmps. Trans HiPEAC 3(2):149\u2013167","journal-title":"Trans HiPEAC"},{"key":"1033_CR44","volume-title":"Modern operating systems","author":"AS Tanenbaum","year":"2007","unstructured":"Tanenbaum AS (2007) Modern operating systems, 3rd edn. Prentice Hall Press, Englewood Cliffs","edition":"3"},{"key":"1033_CR45","volume-title":"NOCS","author":"C Fallin","year":"2012","unstructured":"Fallin C, Nazario G, Yuy X, Chang K, Ausavarungnirun R, Mutlu O (2012) MinBD: minimally-buffered deflection routing for energy-efficient interconnect. In: NOCS"},{"key":"1033_CR46","volume-title":"Proc the 45th annual inter symp on microarchitecture","author":"P Lotfi-Kamran","year":"2012","unstructured":"Lotfi-Kamran P, Grot B, Falsafi B (2012) NOC-out: microarchitecting a scale-out processor. In: Proc the 45th annual inter symp on microarchitecture, Vancouver, Canada, December 2012"},{"issue":"12","key":"1033_CR47","doi-asserted-by":"crossref","first-page":"2303","DOI":"10.1109\/TVLSI.2010.2086500","volume":"19","author":"H Homayoun","year":"2011","unstructured":"Homayoun H, Sasan A, Veidenbaum AV, Yao H-C, Golshan S, Heydari P (2011) MZZ-HVS: multiple sleep modes zig-zag horizontal and vertical sleep transistor sharing to reduce leakage power in on-chip SRAM peripheral circuits. IEEE Trans Very Large Scale Integr (VLSI) Syst 19(12):2303\u20132316","journal-title":"IEEE Trans Very Large Scale Integr (VLSI) Syst"},{"key":"1033_CR48","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1109\/HPCA.2005.27","volume-title":"HPCA \u201905: proceedings of the 11th international symposium on high-performance computer architecture","author":"D Chandra","year":"2005","unstructured":"Chandra D, Guo F, Kim S, Solihin Y (2005) Predicting inter-thread cache contention on a chip multi-processor architecture. In: HPCA \u201905: proceedings of the 11th international symposium on high-performance computer architecture, pp 340\u2013351"},{"issue":"3","key":"1033_CR49","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1145\/1089008.1089009","volume":"2","author":"Y Meng","year":"2005","unstructured":"Meng Y, Sherwood T, Kastner R (2005) Exploring the limits of leakage power reduction in caches. ACM Trans Archit Code Optim 2(3):221\u2013246","journal-title":"ACM Trans Archit Code Optim"},{"key":"1033_CR50","first-page":"590","volume-title":"Proc 7th int symp quality electron design","author":"W Zhao","year":"2006","unstructured":"Zhao W, Cao Y (2006) New generation of predictive technology model for sub-45 nm design exploration. In: Proc 7th int symp quality electron design, Mar 2006, pp 590\u2013596"},{"key":"1033_CR51","volume-title":"Low power methodology manual","author":"M Keating","year":"2007","unstructured":"Keating M, Flynn D, Aitken R, Gibbons A, Shi K (2007) Low power methodology manual. Springer, Berlin"},{"key":"1033_CR52","first-page":"598","volume-title":"Design, automation & test in Europe 2009 (Date 2009)","author":"M Comparetti","year":"2009","unstructured":"Comparetti M, Foglia P et al (2009) A\u00a0power-efficient migration mechanism for D-NUCA caches. In: Design, automation & test in Europe 2009 (Date 2009), Nice, France, 20\u201324 April 2009, pp 598\u2013601"},{"key":"1033_CR53","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1109\/DSD.2011.99","volume-title":"14th EUROMICRO conference on digital system design, architectures, methods and tools (DSD2011)","author":"A Bardine","year":"2011","unstructured":"Bardine A, Foglia P, Panicucci F, Sahuquillo J, Solinas M (2011) Energy behaviour of NUCA caches in CMPs. In: 14th EUROMICRO conference on digital system design, architectures, methods and tools (DSD2011), OULU, Finland, 31\u00a0August\u20132\u00a0September 2011, pp 746\u2013753"},{"key":"1033_CR54","first-page":"184","volume-title":"36th annual international symposium on computer architecture (ISCA \u201909)","author":"N Hardavellas","year":"2009","unstructured":"Hardavellas N et al (2009) Reactive NUCA: near-optimal block placement and replication in distributed caches. In: 36th annual international symposium on computer architecture (ISCA \u201909). ACM, New York, pp 184\u2013195. doi: 10.1145\/1555815.1555779"},{"key":"1033_CR55","first-page":"87","volume-title":"22nd int symp on computer architecture and high performance computing","author":"S Bartolini","year":"2010","unstructured":"Bartolini S et al (2010) Feedback driven restructuring of multi-threaded applications for NUCA cache performance in CMPs. In: 22nd int symp on computer architecture and high performance computing, Petropolis, Brazil, 27\u201330 October 2010, pp 87\u201394. doi: 10.1109\/SBAC-PAD.2010.20"},{"key":"1033_CR56","first-page":"307","volume-title":"11th EUROMICRO conference on digital system design","author":"A Bardine","year":"2008","unstructured":"Bardine A, Comparetti M, Foglia P, Gabrielli G, Prete CA, Stenstrom P (2008) Leveraging data promotion for low power D-NUCA caches. In: 11th EUROMICRO conference on digital system design, Parma, Italy, 3\u20135 September 2008, pp 307\u2013316. doi: 10.1109\/DSD.2008.52"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-1033-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-013-1033-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-1033-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T15:12:16Z","timestamp":1688569936000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-013-1033-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,10,24]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["1033"],"URL":"https:\/\/doi.org\/10.1007\/s11227-013-1033-5","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,10,24]]}}}