{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:03:47Z","timestamp":1766066627335,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,6,1]],"date-time":"2016-06-01T00:00:00Z","timestamp":1464739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1145\/2925426.2926282","type":"proceedings-article","created":{"date-parts":[[2016,6,10]],"date-time":"2016-06-10T13:04:07Z","timestamp":1465563847000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Prefetching Techniques for Near-memory Throughput Processors"],"prefix":"10.1145","author":[{"given":"Reena","family":"Panda","sequence":"first","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuko","family":"Eckert","sequence":"additional","affiliation":[{"name":"AMD Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nuwan","family":"Jayasena","sequence":"additional","affiliation":[{"name":"AMD Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Onur","family":"Kayiran","sequence":"additional","affiliation":[{"name":"AMD Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Boyer","sequence":"additional","affiliation":[{"name":"AMD Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizy Kurian","family":"John","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,6]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Advancing Moore's Law on 2014! http:\/\/www.intel.com\/content\/dam\/www\/public\/us\/en\/documents\/presentation\/advancing-moores-law-in-2014-presentation.pdf.  Advancing Moore's Law on 2014! http:\/\/www.intel.com\/content\/dam\/www\/public\/us\/en\/documents\/presentation\/advancing-moores-law-in-2014-presentation.pdf."},{"key":"e_1_3_2_1_2_1","volume-title":"Fermi","author":"A's","year":"2009","unstructured":"NVIDI A's next generation CUDA compute architecture , Fermi , 2009 . NVIDIA's next generation CUDA compute architecture, Fermi, 2009."},{"volume-title":"CUDA c\/c++ sdk code samples","year":"2011","key":"e_1_3_2_1_3_1","unstructured":"Nvidia. CUDA c\/c++ sdk code samples , 2011 . Nvidia. CUDA c\/c++ sdk code samples, 2011."},{"key":"e_1_3_2_1_4_1","volume-title":"Hybrid Memory Cube Specification 1.0","author":"Hybrid","year":"2013","unstructured":"Hybrid memory cube consortium. Hybrid Memory Cube Specification 1.0 , 2013 . Hybrid memory cube consortium. Hybrid Memory Cube Specification 1.0, 2013."},{"key":"e_1_3_2_1_5_1","volume-title":"High Bandwidth Memory (HBM) DRAM","author":"Jedec","year":"2013","unstructured":"Jedec standard jesd235. High Bandwidth Memory (HBM) DRAM , 2013 . Jedec standard jesd235. High Bandwidth Memory (HBM) DRAM, 2013."},{"key":"e_1_3_2_1_6_1","volume-title":"High Bandwidth Memory (HBM) 2 DRAM","author":"Jedec","year":"2016","unstructured":"Jedec standard jesd235a. High Bandwidth Memory (HBM) 2 DRAM , 2016 . Jedec standard jesd235a. High Bandwidth Memory (HBM) 2 DRAM, 2016."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145820"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2499968.2499973"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/520549.822749"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2485288.2485348"},{"key":"e_1_3_2_1_14_1","unstructured":"K. Chandrasekar C. Weis Y. Li S. Goossens M. Jung O. Naji B. Akesson N. Wehn and K. Goossens. Drampower: Open-source dram power and energy estimation tool.  K. Chandrasekar C. Weis Y. Li S. Goossens M. Jung O. Naji B. Akesson N. Wehn and K. Goossens. Drampower: Open-source dram power and energy estimation tool."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2013.6509675"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2013.6704684"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/514191.514197"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2009.4798232"},{"key":"e_1_3_2_1_21_1","volume-title":"WoNDP: 2nd Workshop on Near-Data Processing","author":"Eckert Y.","year":"2014","unstructured":"Y. Eckert , N. Jayasena , and G. H. Loh . Thermal feasibility of die-stacked processing in memory . In WoNDP: 2nd Workshop on Near-Data Processing , 2014 . Y. Eckert, N. Jayasena, and G. H. Loh. Thermal feasibility of die-stacked processing in memory. In WoNDP: 2nd Workshop on Near-Data Processing, 2014."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1274971.1275004"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/545215.545239"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485951"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/264107.264207"},{"key":"e_1_3_2_1_28_1","first-page":"157","volume-title":"Proceedings of the 22Nd International Conference on Parallel Architectures and Compilation Techniques","author":"Kayiran O.","year":"2013","unstructured":"O. Kayiran , A. Jog , M. T. Kandemir , and C. R. Das . Neither more nor less: Optimizing thread-level parallelism for GPGPUs . In Proceedings of the 22Nd International Conference on Parallel Architectures and Compilation Techniques , pages 157 -- 166 , 2013 . O. Kayiran, A. Jog, M. T. Kandemir, and C. R. Das. Neither more nor less: Optimizing thread-level parallelism for GPGPUs. In Proceedings of the 22Nd International Conference on Parallel Architectures and Compilation Techniques, pages 157--166, 2013."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.24"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/379240.379259"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835970"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.44"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485964"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751237"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056024"},{"key":"e_1_3_2_1_36_1","first-page":"42","volume-title":"ISSCC","author":"Lim K.-N.","year":"2012","unstructured":"K.-N. Lim , W.-J. Jang , H.-S. Won , K.-Y. Lee , H. Kim , D.-W. Kim , M.-H. Cho , S.-L. Kim , J.-H. Kang , K.-W. Park , and B.-T. Jeong . A 1.2v 23nm 6f2 4gb ddr3 sdram with local-bitline sense amplifier, hybrid lio sense amplifier and dummy-less array architecture . In ISSCC , pages 42 -- 44 . IEEE, 2012 . K.-N. Lim, W.-J. Jang, H.-S. Won, K.-Y. Lee, H. Kim, D.-W. Kim, M.-H. Cho, S.-L. Kim, J.-H. Kang, K.-W. Park, and B.-T. Jeong. A 1.2v 23nm 6f2 4gb ddr3 sdram with local-bitline sense amplifier, hybrid lio sense amplifier and dummy-less array architecture. In ISSCC, pages 42--44. IEEE, 2012."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2008.4771793"},{"key":"e_1_3_2_1_38_1","volume-title":"WoNDP: 1st Workshop on Near-Data Processing","author":"Loh G. H.","year":"2013","unstructured":"G. H. Loh , N. Jayasena , M. H. Oskin , M. Nutter , D. Roberts , M. Meswani , D. P. Zhang , and M. Ignatowski . A processing in memory taxonomy and a case for studying fixed-function pim . In WoNDP: 1st Workshop on Near-Data Processing , 2013 . G. H. Loh, N. Jayasena, M. H. Oskin, M. Nutter, D. Roberts, M. Meswani, D. P. Zhang, and M. Ignatowski. A processing in memory taxonomy and a case for studying fixed-function pim. In WoNDP: 1st Workshop on Near-Data Processing, 2013."},{"issue":"8","key":"e_1_3_2_1_39_1","first-page":"1803","article-title":"Orchestrating cache management and memory scheduling for GPGPU applications. Very Large Scale Integration (VLSI) Systems","volume":"22","author":"Mu S.","year":"2014","unstructured":"S. Mu , Y. Deng , Y. Chen , H. Li , J. Pan , W. Zhang , and Z. Wang . Orchestrating cache management and memory scheduling for GPGPU applications. Very Large Scale Integration (VLSI) Systems , IEEE Transactions on , 22 ( 8 ): 1803 -- 1814 , Aug 2014 . S. Mu, Y. Deng, Y. Chen, H. Li, J. Pan, W. Zhang, and Z. Wang. Orchestrating cache management and memory scheduling for GPGPU applications. Very Large Scale Integration (VLSI) Systems, IEEE Transactions on, 22(8):1803--1814, Aug 2014.","journal-title":"IEEE Transactions on"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2004.10030"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/279358.279387"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.592312"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844483"},{"key":"e_1_3_2_1_44_1","first-page":"73","volume-title":"Proceedings of the 22Nd International Conference on Parallel Architectures and Compilation Techniques, PACT '13","author":"Sethia A.","year":"2013","unstructured":"A. Sethia , G. Dasika , M. Samadi , and S. Mahlke . Apogee: Adaptive prefetching on GPUs for energy efficiency . In Proceedings of the 22Nd International Conference on Parallel Architectures and Compilation Techniques, PACT '13 , pages 73 -- 82 , Piscataway, NJ, USA , 2013 . IEEE Press. A. Sethia, G. Dasika, M. Samadi, and S. Mahlke. Apogee: Adaptive prefetching on GPUs for energy efficiency. In Proceedings of the 22Nd International Conference on Parallel Architectures and Compilation Techniques, PACT '13, pages 73--82, Piscataway, NJ, USA, 2013. IEEE Press."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2006.38"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2007.346185"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2012.6378607"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806596.1806606"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600213"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2492408.2492418"}],"event":{"name":"ICS '16: 2016 International Conference on Supercomputing","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Istanbul Turkey","acronym":"ICS '16"},"container-title":["Proceedings of the 2016 International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2925426.2926282","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2925426.2926282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:04:25Z","timestamp":1750273465000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2925426.2926282"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6]]},"references-count":51,"alternative-id":["10.1145\/2925426.2926282","10.1145\/2925426"],"URL":"https:\/\/doi.org\/10.1145\/2925426.2926282","relation":{},"subject":[],"published":{"date-parts":[[2016,6]]},"assertion":[{"value":"2016-06-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}