{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T09:28:42Z","timestamp":1761989322356,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NS","award":["CNS-1619450"],"award-info":[{"award-number":["CNS-1619450"]}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-1422401","CNS-1619322"],"award-info":[{"award-number":["CNS-1422401","CNS-1619322"]}],"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":[[2019,4,4]]},"DOI":"10.1145\/3297858.3304026","type":"proceedings-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T18:38:43Z","timestamp":1554403123000},"page":"701-714","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["CORF"],"prefix":"10.1145","author":[{"given":"Hodjat","family":"Asghari Esfeden","sequence":"first","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}]},{"given":"Farzad","family":"Khorasani","sequence":"additional","affiliation":[{"name":"Tesla Inc. & Georgia Tech, Palo Alto, CA, USA"}]},{"given":"Hyeran","family":"Jeon","sequence":"additional","affiliation":[{"name":"San Jose State University, San Jose, CA, USA"}]},{"given":"Daniel","family":"Wong","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}]},{"given":"Nael","family":"Abu-Ghazaleh","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522337"},{"volume-title":"Pilot Register File: Energy Efficient Partitioned Register File for GPUs. In 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) .","author":"Abdel-Majeed M.","key":"e_1_3_2_1_2_1","unstructured":"M. Abdel-Majeed, A. Shafaei, H. Jeon, M. Pedram, and M. Annavaram. 2017. Pilot Register File: Energy Efficient Partitioned Register File for GPUs. In 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) ."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540719"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926281"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123976"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/998680.1006719"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289187"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2018.2821144"},{"key":"e_1_3_2_1_10_1","volume-title":"Domino Temporal Data Prefetcher. In International Symposium on High-Performance Computer Architecture (HPCA). IEEE, 131--142","author":"Bakhshalipour Mohammad","year":"2018","unstructured":"Mohammad Bakhshalipour, Pejman Lotfi-Kamran, and Hamid Sarbazi-Azad. 2018a. Domino Temporal Data Prefetcher. In International Symposium on High-Performance Computer Architecture (HPCA). IEEE, 131--142."},{"key":"e_1_3_2_1_11_1","volume-title":"Bingo Spatial Data Prefetcher. In International Symposium on High-Performance Computer Architecture (HPCA) .","author":"Bakhshalipour Mohammad","year":"2019","unstructured":"Mohammad Bakhshalipour, Mehran Shakerinava, Pejman Lotfi-Kamran, and Hamid Sarbazi-Azad. 2019 b. Bingo Spatial Data Prefetcher. In International Symposium on High-Performance Computer Architecture (HPCA) ."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627817.2627951"},{"volume-title":"2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) .","author":"Chatterjee N.","key":"e_1_3_2_1_14_1","unstructured":"N. Chatterjee, M. O'Connor, D. Lee, D. R. Johnson, S. W. Keckler, M. Rhu, and W. J. Dally. 2017. Architecting an Energy-Efficient DRAM System for GPUs. In 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) ."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2004.29"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2024723.2000093"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155675"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/229542.229546"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522330"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830784"},{"key":"e_1_3_2_1_22_1","volume-title":"Tango: A Deep Neural Network Benchmark Suite for Various Accelerators. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS). IEEE Press.","author":"Karki Aajna","year":"2019","unstructured":"Aajna Karki, Chethan Palangotu Keshava, Spoorthi Mysore Shivakumar, Joshua Skow, Goutam Madhukeshwar Hegde, and Hyeran Jeon. 2019. Tango: A Deep Neural Network Benchmark Suite for Various Accelerators. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS). IEEE Press."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967941"},{"key":"e_1_3_2_1_24_1","volume-title":"Nael Abu-Ghazaleh, and Vivek Sarkar.","author":"Khorasani Farzad","year":"2018","unstructured":"Farzad Khorasani, Hodjat Asghari Esfeden, Nael Abu-Ghazaleh, and Vivek Sarkar. 2018a. In-Register Parameter Caching for Dynamic Neural Nets with Virtual Persistent Processor Specialization. In 2018 51st Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). IEEE, 377--389."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00073"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123974"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750417"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508148.2485964"},{"key":"e_1_3_2_1_29_1","first-page":"339","article-title":"Simulating multiported memories using lower port count memories","volume":"7","author":"Lindholm John Erik","year":"2008","unstructured":"John Erik Lindholm, Ming Y Siu, Simon S Moy, Samuel Liu, and John R Nickolls. 2008. Simulating multiported memories using lower port count memories. US Patent 7,339,592.","journal-title":"US Patent"},{"volume-title":"G-Scalar: Cost-Effective Generalized Scalar Execution Architecture for Power-Efficient GPUs. In 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) .","author":"Liu Z.","key":"e_1_3_2_1_30_1","unstructured":"Z. Liu, S. Gilani, M. Annavaram, and N. S. Kim. 2017. G-Scalar: Cost-Effective Generalized Scalar Execution Architecture for Power-Efficient GPUs. In 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) ."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3218603.3218626"},{"volume-title":"Dynamic GPGPU Power Management Using Adaptive Model Predictive Control. In 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) .","author":"Majumdar A.","key":"e_1_3_2_1_32_1","unstructured":"A. Majumdar, L. Piga, I. Paul, J. L. Greathouse, W. Huang, and D. H. Albonesi. 2017. Dynamic GPGPU Power Management Using Adaptive Model Predictive Control. In 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) ."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130218.3130222"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2636342"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2435788"},{"key":"e_1_3_2_1_36_1","unstructured":"NCSU. 2014. The FreePDK process design kit. Available: http:\/\/www.eda.ncsu.edu\/wiki\/FreePDK."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2018.2873679"},{"key":"e_1_3_2_1_38_1","unstructured":"Nvidia. 2009a. \"Whitepaper: Nvidia's Next Generation CUDA Compute Architecture: Fermi\"."},{"key":"e_1_3_2_1_39_1","unstructured":"Nvidia. 2009b. Nvidia CUDA SDK 2.3. {Online}. Available: http:\/\/developer.nvidia.com\/cuda-toolkit-23-downloads ."},{"key":"e_1_3_2_1_40_1","unstructured":"Nvidia. 2012. \"Whitepaper: Nvidia's Next Generation CUDA Compute Architecture: KeplerGK110\"."},{"key":"e_1_3_2_1_41_1","unstructured":"Nvidia. 2014. \"Whitepaper: Nvidia GeForce GTX 980\"."},{"key":"e_1_3_2_1_42_1","volume-title":"FineReg: Fine-Grained Register File Management for Augmenting GPU Throughput. In 2018 51st Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). IEEE, 364--376","author":"Oh Yunho","year":"2018","unstructured":"Yunho Oh, Myung Kuk Yoon, William J Song, and Won Woo Ro. 2018. FineReg: Fine-Grained Register File Management for Augmenting GPU Throughput. In 2018 51st Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). IEEE, 364--376."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1011508.1011512"},{"volume-title":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA) .","author":"Pekhimenko G.","key":"e_1_3_2_1_44_1","unstructured":"G. Pekhimenko, E. Bolotin, N. Vijaykumar, O. Mutlu, T. C. Mowry, and S. W. Keckler. 2016. A case for toggle-aware compression for GPU systems. In 2016 IEEE International Symposium on High Performance Computer Architecture (HPCA) ."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370870"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3291606"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173211"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195657"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5555\/2523721.2523735"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.16"},{"volume-title":"2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA) .","author":"Shafiee A.","key":"e_1_3_2_1_51_1","unstructured":"A. Shafiee, M. Taassori, R. Balasubramonian, and A. Davis. 2014. MemZip: Exploring unconventional benefits from memory compression. In 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA) ."},{"key":"e_1_3_2_1_53_1","volume-title":"Geng Daniel Liu, and Wen-Mei W Hwu","author":"Stratton John A","year":"2012","unstructured":"John A Stratton, Christopher Rodrigues, I-Jui Sung, Nady Obeid, Li-Wen Chang, Nasser Anssari, Geng Daniel Liu, and Wen-Mei W Hwu. 2012. Parboil: A revised benchmark suite for scientific and commercial throughput computing. Center for Reliable and High-Performance Computing , Vol. 127 (2012)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00058"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750399"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"X. Wang and W. Zhang. 2017. GPU Register Packing: Dynamically Exploiting Narrow-Width Operands to Improve Performance. In 2017 IEEE Trustcom\/BigDataSE\/ICESS .","DOI":"10.1109\/Trustcom\/BigDataSE\/ICESS.2017.308"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446063"},{"volume-title":"2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA) .","author":"Wu G.","key":"e_1_3_2_1_58_1","unstructured":"G. Wu, J. L. Greathouse, A. Lyashevsky, N. Jayasena, and D. Chiou. 2015. GPGPU performance and power estimation using machine learning. In 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA) ."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628105"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/360128.360154"},{"volume-title":"Study of the Bipartite Edge Frustration of Graphs","author":"Yarahmadi Zahra","key":"e_1_3_2_1_61_1","unstructured":"Zahra Yarahmadi. 2016. Study of the Bipartite Edge Frustration of Graphs .Springer International Publishing, Cham, 249--267."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/378993.379235"}],"event":{"name":"ASPLOS '19: Architectural Support for Programming Languages and Operating Systems","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"],"location":"Providence RI USA","acronym":"ASPLOS '19"},"container-title":["Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304026","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304026","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:14Z","timestamp":1750204394000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304026"}},"subtitle":["Coalescing Operand Register File for GPUs"],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":60,"alternative-id":["10.1145\/3297858.3304026","10.1145\/3297858"],"URL":"https:\/\/doi.org\/10.1145\/3297858.3304026","relation":{},"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"2019-04-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}