{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:16:47Z","timestamp":1750220207318,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T00:00:00Z","timestamp":1667088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["1908793, 1763681, 2028929, 2008398, 2011146, 1931531"],"award-info":[{"award-number":["1908793, 1763681, 2028929, 2008398, 2011146, 1931531"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,30]]},"DOI":"10.1145\/3508352.3549386","type":"proceedings-article","created":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T12:10:54Z","timestamp":1671711054000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Granular Computation and Data Layout Reorganization for Improving Locality"],"prefix":"10.1145","author":[{"given":"Mahmut","family":"Kandemir","sequence":"first","affiliation":[{"name":"Penn State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xulong","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Pittsburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jagadish","family":"Kotra","sequence":"additional","affiliation":[{"name":"AMD Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mustafa","family":"Karakoy","sequence":"additional","affiliation":[{"name":"TUBITAK-BILGEM, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,12,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Junwhan Arm Sungpack Hong Sungjoo Yoo Onur Mutlu and Kiyoung Choi. 2015. A Scalable Processing-in-memory Accelerator for Parallel Graph Processing. In ISCA."},{"key":"e_1_3_2_1_2_1","unstructured":"Junwhan Ahn Sungjoo Yoo Onur Mutlu and Kiyoung Choi. 2015. PIM-enabled Instructions: A Low-overhead Locality-aware Processing-in-memory Architecture. In ISCA."},{"key":"e_1_3_2_1_3_1","volume-title":"Hoe","author":"Akin Berkin","year":"2015","unstructured":"Berkin Akin, Franz Franchetti, and James C. Hoe. 2015. Data Reorganization in Memory Using 3D-stacked DRAM. In ISCA."},{"key":"e_1_3_2_1_4_1","volume-title":"Lam","author":"Anderson Jennifer M.","year":"1993","unstructured":"Jennifer M. Anderson and Monica S. Lam. 1993. Global Optimizations for Parallelism and Locality on Scalable Parallel Machines. In PLDI."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Vishal Aslot Max J. Domeika Rudolf Eigenmann Greg Gaertner Wesley B. Jones and Bodo Parady. 2001. SPEComp: A New Benchmark Suite for Measuring Parallel Computer Performance. In WOMPAT.","DOI":"10.1007\/3-540-44587-0_1"},{"key":"e_1_3_2_1_6_1","volume-title":"Near-data processing: Insights from a MICRO-46 Workshop. Micro","author":"Balasubramonian Rajeev","year":"2014","unstructured":"Rajeev Balasubramonian, Jichuan Chang, Troy Manning, Jaime H Moreno, Richard Murphy, Ravi Nair, and Steven Swanson. 2014. Near-data processing: Insights from a MICRO-46 Workshop. Micro, IEEE (2014)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/195473.195557"},{"key":"e_1_3_2_1_10_1","volume-title":"Lebeck Shyam Mundhra, and Mithuna Thottethodi","author":"Chatterjee Siddhartha","year":"1999","unstructured":"Siddhartha Chatterjee, Vibhor V. Jain, Alvin R. Lebeck Shyam Mundhra, and Mithuna Thottethodi. 1999. Nonlinear array layouts for hierarchical memory systems. In Proc. of ICS."},{"key":"e_1_3_2_1_11_1","unstructured":"G. Chen and M. Kandemir. 2005. Code Restructuring for Improving Cache Performance of MPSoCs. In DAC."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Michal Cierniak and Wei Li. 1995. Unifying Data and Control Transformations for Distributed Shared-memory Machines. In PLDI.","DOI":"10.1145\/207110.207145"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"G.B. Dantzig and B.C. Eaves. 1973. Fourier-Motzkin elimination and its dual. Journal of Combinatorial Theory 14 A (1973) 288--297.","DOI":"10.1016\/0097-3165(73)90004-6"},{"key":"e_1_3_2_1_14_1","volume-title":"Traffic Management: A Holistic Approach to Memory Placement on NUMA Systems. In ASPLOS.","author":"Dashti Mohammad","year":"2013","unstructured":"Mohammad Dashti, Alexandra Fedorova, Justin Funston, Fabien Gaud, Renaud Lachaize, Baptiste Lepers, Vivien Quema, and Mark Roth. 2013. Traffic Management: A Holistic Approach to Memory Placement on NUMA Systems. In ASPLOS."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Wei Ding Xulong Tang Mahmut Kandemir Yuanrui Zhang and Emre Kultursay. 2015. Optimizing Off-chip Accesses in Multicores. In PLDI.","DOI":"10.1145\/2737924.2737989"},{"key":"e_1_3_2_1_16_1","volume-title":"Fan Yao, Milo\u0161 Doroslova\u010dki, and Guru Venkataramani.","author":"Fang Hongyu","year":"2018","unstructured":"Hongyu Fang, Sai Santosh Dayapule, Fan Yao, Milo\u0161 Doroslova\u010dki, and Guru Venkataramani. 2018. Prefetch-guard: Leveraging hardware prefetches to defend against cache timing channels. In HOST."},{"key":"e_1_3_2_1_17_1","volume-title":"Katherine Morrow, and Nam Sung Kim.","author":"Farmahini-Farahani Amin","year":"2015","unstructured":"Amin Farmahini-Farahani, Jung Ho Ahn, Katherine Morrow, and Nam Sung Kim. 2015. NDA: Near-DRAM acceleration architecture leveraging commodity DRAM devices and standard memory modules. In HPCA."},{"volume-title":"Flows in networks","author":"Ford Lester Randolph","key":"e_1_3_2_1_18_1","unstructured":"Lester Randolph Ford Jr and Delbert Ray Fulkerson. 2015. Flows in networks. Princeton university press."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Antonio Gonz\u00e1lez Carlos Aliagas and Mateo Valero. 2014. A Data Cache with Multiple Caching Strategies Tuned to Different Types of Locality. In ICS.","DOI":"10.1145\/2591635.2667170"},{"key":"e_1_3_2_1_20_1","volume-title":"Lam","author":"Hall Mary H.","year":"1995","unstructured":"Mary H. Hall, Saman P. Amarasinghe, Brian R. Murphy, Shih-Wei Liao, and Monica S. Lam. 1995. Detecting Coarse-grain Parallelism Using an Interprocedural Parallelizing Compiler. In Supercomputing."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Kevin Hsieh Eiman Ebrahimi Gwangsun Kim Niladrish Chatterjee Mike O'Connor Nandita Vijaykumar Onur Mutlu and Stephen W Keckler. 2016. Transparent Offloading and Mapping (TOM): Enabling Programmer-Transparent Near-Data Processing in GPU Systems. In ISCA.","DOI":"10.1109\/ISCA.2016.27"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02278710"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/290940.290999"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Mahmut Kandemir Alok Choudhary J Ramanujam and Prith Banerjee. 1999. A matrix-based approach to global locality optimization. In Journal of Parallel and Distributed Computing.","DOI":"10.1006\/jpdc.1999.1552"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.752779"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/500001.500004"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263650"},{"volume-title":"A layout-conscious iteration space transformation technique","author":"Kandemir Mahmut","key":"e_1_3_2_1_28_1","unstructured":"Mahmut Kandemir, J. Ramanujam, Alok Choudhary, and Prithviraj Banerjee. 2001. A layout-conscious iteration space transformation technique. In IEEE Transactions on Computers."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3192366.3192386"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Induprakas Kodukula Nawaaz Ahmed and Keshav Pingali. 1997. Data-centric Multi-level Blocking. In PLDI.","DOI":"10.1145\/258915.258946"},{"volume-title":"Proceedings of the Fourth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS).","author":"Lam Monica D.","key":"e_1_3_2_1_31_1","unstructured":"Monica D. Lam, Edward E. Rothberg, and Michael E. Wolf. 1991. The Cache Performance and Optimizations of Blocked Algorithms. In Proceedings of the Fourth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"volume-title":"Optimizing data locality by array restructuring. Department of Computer Science and Engineering","author":"Leung Shun-Tak","key":"e_1_3_2_1_33_1","unstructured":"Shun-Tak Leung and John Zahorjan. 1995. Optimizing data locality by array restructuring. Department of Computer Science and Engineering, University of Washington, Seattle, WA."},{"key":"e_1_3_2_1_35_1","volume-title":"Lam","author":"Lim Amy W.","year":"1999","unstructured":"Amy W. Lim, Gerald I. Cheong, and Monica S. Lam. 1999. An Affine Partitioning Algorithm to Maximize Parallelism and Minimize Communication. In ICS."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-012-0378-3"},{"key":"e_1_3_2_1_37_1","unstructured":"Qingda Lu C. Alias U. Bondhugula T. Henretty S. Krishnamoorthy J. Ramanujam A. Rountev P. Sadayappan Yongjian Chen Haibo Lin and Tin-Fook Ngai. 2009. Data Layout Transformation for Enhancing Data Locality on NUCA Chip Multiprocessors. In PACT."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/233561.233564"},{"key":"e_1_3_2_1_39_1","volume-title":"Active Memory Cube: A processing-in-memory architecture for exascale systems. IBM Journal of Research and Development","author":"Nair R","year":"2015","unstructured":"R Nair, SF Antao, C Bertolli, P Bose, JR Brunheroto, T Chen, C-Y Cher, CHA Costa, C Evangelinos, and BM Fleischer. 2015. Active Memory Cube: A processing-in-memory architecture for exascale systems. IBM Journal of Research and Development (2015)."},{"key":"e_1_3_2_1_40_1","volume-title":"Integrating Loop and Data Transformations for Global Optimization. J. Parallel Distribute Computer","author":"O'Boyle M.F.P.","year":"2002","unstructured":"M.F.P. O'Boyle and P.M.W. Knijnenburg. 2002. Integrating Loop and Data Transformations for Global Optimization. J. Parallel Distribute Computer (2002)."},{"key":"e_1_3_2_1_41_1","volume-title":"Quint\u00e3o Pereira","author":"Piccoli Guilherme","year":"2014","unstructured":"Guilherme Piccoli, Henrique N. Santos, Raphael E. Rodrigues, Christiane Pousa, Edson Borin, and Fernando M. Quint\u00e3o Pereira. 2014. Compiler Support for Selective Page Migration in NUMA Architectures. In PACT."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196070"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"William Simon Juan Galicia Alexandre Levisse Marina Zapater and David Atienza. 2019. A fast reliable and wide-voltage-range in-memory computing architecture. In DAC.","DOI":"10.1145\/3316781.3317741"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317867"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/301618.301668"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314599"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Kelefouras Vasilios Keramidas Georgios and Voros Nikolaos. 2018. Combining Software Cache Partitioning and Loop Tiling for Effective Shared Cache Management. ACM Transactions on Embedded Computing System. (2018).","DOI":"10.1145\/3202663"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Ben Verghese Scott Devine Anoop Gupta and Mendel Rosenblum. 1996. Operating System Support for Improving Data Locality on CC-NUMA Compute Servers. In ASPLOS.","DOI":"10.1145\/237090.237205"},{"key":"e_1_3_2_1_49_1","volume-title":"Lam","author":"Wolf Michael E.","year":"1991","unstructured":"Michael E. Wolf and Monica S. Lam. 1991. A Data Locality Optimizing Algorithm. In PLDI."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2002.805823"},{"key":"e_1_3_2_1_51_1","volume-title":"Jaswinder Pal Singh, and Anoop Gupta","author":"Woo Steven Cameron","year":"1995","unstructured":"Steven Cameron Woo, Moriyoshi Ohara, Evan Torrie, Jaswinder Pal Singh, and Anoop Gupta. 1995. The SPLASH-2 Programs: Characterization and Methodological Considerations. In ISCA."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 3rd Workshop on Near-Data Processing.","author":"Xu Lifan","year":"2015","unstructured":"Lifan Xu, Dong Ping Zhang, and Nuwan Jayasena. 2015. Scaling Deep Learning on Multiple In-Memory Processors. In Proceedings of the 3rd Workshop on Near-Data Processing."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Dongping Zhang Nuwan Jayasena Alexander Lyashevsky Joseph L. Greathouse Lifan Xu and Michael Ignatowski. 2014. TOP-PIM: Throughput-oriented Programmable Processing in Memory. In HPDC.","DOI":"10.1145\/2600212.2600213"}],"event":{"name":"ICCAD '22: IEEE\/ACM International Conference on Computer-Aided Design","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-EDS Electronic Devices Society","IEEE CAS","IEEE CEDA"],"location":"San Diego California","acronym":"ICCAD '22"},"container-title":["Proceedings of the 41st IEEE\/ACM International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3508352.3549386","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3508352.3549386","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3508352.3549386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:57Z","timestamp":1750186977000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3508352.3549386"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,30]]},"references-count":51,"alternative-id":["10.1145\/3508352.3549386","10.1145\/3508352"],"URL":"https:\/\/doi.org\/10.1145\/3508352.3549386","relation":{},"subject":[],"published":{"date-parts":[[2022,10,30]]},"assertion":[{"value":"2022-12-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}