{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:54:42Z","timestamp":1777128882870,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":84,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3620665.3640401","type":"proceedings-article","created":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T14:18:06Z","timestamp":1713795486000},"page":"37-54","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["A Quantitative Analysis and Guidelines of Data Streaming Accelerator in Modern Intel Xeon Scalable Processors"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3071-7086","authenticated-orcid":false,"given":"Reese","family":"Kuper","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana Champaign, Urbana, Illinois, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7513-2858","authenticated-orcid":false,"given":"Ipoom","family":"Jeong","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8389-2133","authenticated-orcid":false,"given":"Yifan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Intel Labs, Hillsboro, Oregon, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2937-5804","authenticated-orcid":false,"given":"Ren","family":"Wang","sequence":"additional","affiliation":[{"name":"Intel Labs, Hillsboro, Oregon, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8998-8551","authenticated-orcid":false,"given":"Narayan","family":"Ranganathan","sequence":"additional","affiliation":[{"name":"Intel Labs, Bangalore, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9997-0436","authenticated-orcid":false,"given":"Nikhil","family":"Rao","sequence":"additional","affiliation":[{"name":"Intel Labs, Bangalore, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0974-3535","authenticated-orcid":false,"given":"Jiayu","family":"Hu","sequence":"additional","affiliation":[{"name":"Tencent, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7985-2444","authenticated-orcid":false,"given":"Sanjay","family":"Kumar","sequence":"additional","affiliation":[{"name":"Intel Labs, Hillsboro, Oregon, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5257-8287","authenticated-orcid":false,"given":"Philip","family":"Lantz","sequence":"additional","affiliation":[{"name":"Intel Labs, Hillsboro, Oregon, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0442-5634","authenticated-orcid":false,"given":"Nam Sung","family":"Kim","sequence":"additional","affiliation":[{"name":"UIUC, Urbana, Illinois, United States of America"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2013.6702659"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00042"},{"key":"e_1_3_2_1_4_1","volume-title":"2020 IEEE International Symposium on Performance Analysis of Systems and Software, (ISPASS'20)","author":"Alian Mohammad","year":"2020","unstructured":"Mohammad Alian, Yifan Yuan, Jie Zhang, Ren Wang, Myoungsoo Jung, and Nam Sung Kim. Data direct I\/O characterization for future I\/O system exploration. In 2020 IEEE International Symposium on Performance Analysis of Systems and Software, (ISPASS'20), 2020."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536358"},{"key":"e_1_3_2_1_6_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation, (OSDI'20)","author":"Anderson Thomas E.","year":"2020","unstructured":"Thomas E. Anderson, Marco Canini, Jongyul Kim, Dejan Kosti\u0107, Youngjin Kwon, Simon Peter, Waleed Reda, Henry N. Schuh, and Emmett Witchel. Assise: Performance and availability via client-local NVM in a distributed file system. In 14th USENIX Symposium on Operating Systems Design and Implementation, (OSDI'20), 2020."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942101"},{"key":"e_1_3_2_1_8_1","volume-title":"IEEE\/ACM International Symposium on Microarchitecture, (MICRO'19)","author":"Baek Eunjin","year":"2019","unstructured":"Eunjin Baek, Hunjun Lee, Youngsok Kim, and Jangwoo Kim. FlexLearn: Fast and highly efficient brain simulations using flexible on-chip learning. In IEEE\/ACM International Symposium on Microarchitecture, (MICRO'19), 2019."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation, (OSDI'20)","author":"Berg Benjamin","year":"2020","unstructured":"Benjamin Berg, Daniel S. Berger, Sara McAllister, Isaac Grosof, Sathya Gunasekar, Jimmy Lu, Michael Uhlar, Jim Carrig, Nathan Beckmann, Mor Harchol-Balter, and Gregory R. Ganger. The CacheLib caching engine: Design and experiences at scale. In Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation, (OSDI'20), 2020."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446095"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"e_1_3_2_1_13_1","volume-title":"Olivier Temam. DaDianNao: A Machine-Learning Supercomputer. In IEEE\/ACM International Symposium on Microarchitecture, (MICRO'14)","author":"Chen Yunji","year":"2014","unstructured":"Yunji Chen, Tao Luo, Shaoli Liu, Shijin Zhang, Liqiang He, Jia Wang, Ling Li, Tianshi Chen, Zhiwei Xu, Ninghui Sun, and Olivier Temam. DaDianNao: A Machine-Learning Supercomputer. In IEEE\/ACM International Symposium on Microarchitecture, (MICRO'14), 2014."},{"key":"e_1_3_2_1_14_1","volume-title":"Dual-core Intel Xeon Processor 5100 Series. https:\/\/www.sas.com\/partners\/directory\/intel\/XeonProcessorProdBrief.pdf","author":"Intel Corporation","year":"2006","unstructured":"Intel Corporation. Dual-core Intel Xeon Processor 5100 Series. https:\/\/www.sas.com\/partners\/directory\/intel\/XeonProcessorProdBrief.pdf, 2006. (Accessed on 12\/02\/2022)."},{"key":"e_1_3_2_1_15_1","volume-title":"https:\/\/www.intel.com\/content\/www\/us\/en\/wireless-network\/accel-technology.html","author":"Intel Corporation","year":"2006","unstructured":"Intel Corporation. Intel I\/O Acceleration Technology. https:\/\/www.intel.com\/content\/www\/us\/en\/wireless-network\/accel-technology.html, 2006."},{"key":"e_1_3_2_1_16_1","volume-title":"White paper: Accelerating high-speed networking with Intel I\/OAT. https:\/\/www.intel.com\/content\/www\/us\/en\/io\/i-o-acceleration-technology-paper.html","author":"Intel Corporation","year":"2006","unstructured":"Intel Corporation. White paper: Accelerating high-speed networking with Intel I\/OAT. https:\/\/www.intel.com\/content\/www\/us\/en\/io\/i-o-acceleration-technology-paper.html, 2006."},{"key":"e_1_3_2_1_17_1","volume-title":"Intel QuickData Technology software guide for Linux. https:\/\/www.intel.com\/content\/dam\/doc\/white-paper\/quickdata-technology-software-guide-for-linux-paper.pdf","author":"Intel Corporation","year":"2008","unstructured":"Intel Corporation. Intel QuickData Technology software guide for Linux. https:\/\/www.intel.com\/content\/dam\/doc\/white-paper\/quickdata-technology-software-guide-for-linux-paper.pdf, 2008."},{"key":"e_1_3_2_1_18_1","volume-title":"Github - intel\/intel-cmt-cat: User space software for Intel Resource Director Technology. https:\/\/github.com\/intel\/intel-cmt-cat","author":"Intel Corporation","year":"2016","unstructured":"Intel Corporation. Github - intel\/intel-cmt-cat: User space software for Intel Resource Director Technology. https:\/\/github.com\/intel\/intel-cmt-cat, 2016."},{"key":"e_1_3_2_1_19_1","volume-title":"Intel Data Direct I\/O Technology. https:\/\/www.intel.com\/content\/www\/us\/en\/io\/data-direct-i-o-technology.html","author":"Intel Corporation","year":"2018","unstructured":"Intel Corporation. Intel Data Direct I\/O Technology. https:\/\/www.intel.com\/content\/www\/us\/en\/io\/data-direct-i-o-technology.html, 2018."},{"key":"e_1_3_2_1_20_1","volume-title":"Introducing Intel Scalable I\/O Virtualization. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/introducing-intel-scalable-io-virtualization.html","author":"Intel Corporation","year":"2018","unstructured":"Intel Corporation. Introducing Intel Scalable I\/O Virtualization. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/introducing-intel-scalable-io-virtualization.html, 2018."},{"key":"e_1_3_2_1_21_1","volume-title":"Introducing the Intel Data Streaming Accelerator (Intel DSA) | 01.org. https:\/\/01.org\/blogs\/2019\/introducing-intel-data-streaming-accelerator","author":"Intel Corporation","year":"2019","unstructured":"Intel Corporation. Introducing the Intel Data Streaming Accelerator (Intel DSA) | 01.org. https:\/\/01.org\/blogs\/2019\/introducing-intel-data-streaming-accelerator, 2019."},{"key":"e_1_3_2_1_22_1","volume-title":"GNA - gaussian & neural accelerator library repository. https:\/\/github.com\/intel\/gna","author":"Intel Corporation","year":"2022","unstructured":"Intel Corporation. GNA - gaussian & neural accelerator library repository. https:\/\/github.com\/intel\/gna, 2022."},{"key":"e_1_3_2_1_23_1","unstructured":"Intel Corporation. Optimized real-time video transport using Intel Data Streaming Accelerator. https:\/\/networkbuilders.intel.com\/solutionslibrary\/optimized-real-time-video-transport-using-intel-data-streaming-accelerator 2023."},{"key":"e_1_3_2_1_24_1","volume-title":"Intel DSA Performance Micros. https:\/\/github.com\/intel\/dsa-perf-micros, accessed","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. Intel DSA Performance Micros. https:\/\/github.com\/intel\/dsa-perf-micros, accessed in 2023."},{"key":"e_1_3_2_1_25_1","volume-title":"Intel\u00ae Agilex\u2122 7 FPGA I-Series Development Kit. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/fpga\/development-kits\/agilex\/i-series\/dev-agi027.html, accessed","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. Intel\u00ae Agilex\u2122 7 FPGA I-Series Development Kit. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/fpga\/development-kits\/agilex\/i-series\/dev-agi027.html, accessed in 2023."},{"key":"e_1_3_2_1_26_1","volume-title":"Intel\u00ae Data Mover Library (Intel\u00ae DML). https:\/\/github.com\/intel\/DML, accessed","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. Intel\u00ae Data Mover Library (Intel\u00ae DML). https:\/\/github.com\/intel\/DML, accessed in 2023."},{"key":"e_1_3_2_1_27_1","volume-title":"Intel\u00ae Data Streaming Accelerator Architecture Specification. https:\/\/software.intel.com\/en-us\/download\/intel-data-streaming-accelerator-preliminary-architecture-specification, accessed","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. Intel\u00ae Data Streaming Accelerator Architecture Specification. https:\/\/software.intel.com\/en-us\/download\/intel-data-streaming-accelerator-preliminary-architecture-specification, accessed in 2023."},{"key":"e_1_3_2_1_28_1","volume-title":"Intel\u00ae Intelligent Storage Acceleration Library (Intel\u00ae ISA-L). https:\/\/github.com\/intel\/isa-l, accessed","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. Intel\u00ae Intelligent Storage Acceleration Library (Intel\u00ae ISA-L). https:\/\/github.com\/intel\/isa-l, accessed in 2023."},{"key":"e_1_3_2_1_29_1","volume-title":"Intel\u00ae Performance Counter Monitor (Intel\u00ae PCM). https:\/\/github.com\/intel\/pcm, accessed","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. Intel\u00ae Performance Counter Monitor (Intel\u00ae PCM). https:\/\/github.com\/intel\/pcm, accessed in 2023."},{"key":"e_1_3_2_1_30_1","volume-title":"Compute Express Link (CXL). https:\/\/www.computeexpresslink.org, accessed","author":"CXL Consortium","year":"2021","unstructured":"CXL Consortium. Compute Express Link (CXL). https:\/\/www.computeexpresslink.org, accessed in 2021."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358276"},{"key":"e_1_3_2_1_32_1","first-page":"1","volume-title":"Slides from Linux Kongress","author":"De Melo Arnaldo Carvalho","year":"2010","unstructured":"Arnaldo Carvalho De Melo. The new Linux \"perf\" tools. In Slides from Linux Kongress, volume 18, pages 1--42, 2010."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.848475"},{"key":"e_1_3_2_1_34_1","volume-title":"Vhost library. https:\/\/doc.dpdk.org\/guides\/prog_guide\/vhost_lib.html","author":"Dpdk DPDK.","year":"2019","unstructured":"DPDK. Dpdk: Vhost library. https:\/\/doc.dpdk.org\/guides\/prog_guide\/vhost_lib.html, 2019."},{"key":"e_1_3_2_1_35_1","volume-title":"wrk - a HTTP benchmarking tool. https:\/\/github.com\/wg\/wrk, accessed","author":"Silva Felipe Dutra","year":"2023","unstructured":"Felipe Dutra Tine e Silva. wrk - a HTTP benchmarking tool. https:\/\/github.com\/wg\/wrk, accessed in 2023."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000108"},{"key":"e_1_3_2_1_37_1","volume-title":"Cachebench: Benchmark and stress testing tool to evaluate cache performance with real hardware and real cache workloads. https:\/\/cachelib.org\/docs\/Cache_Library_User_Guides\/Cachebench_Overview","year":"2020","unstructured":"Facebook. Cachebench: Benchmark and stress testing tool to evaluate cache performance with real hardware and real cache workloads. https:\/\/cachelib.org\/docs\/Cache_Library_User_Guides\/Cachebench_Overview, 2020."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2008.4663775"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589082"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2016.7482101"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2015.19"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783759"},{"key":"e_1_3_2_1_43_1","volume-title":"IEEE\/ACM International Symposium on Microarchitecture, (MICRO'19)","author":"Hegde Kartik","year":"2019","unstructured":"Kartik Hegde, Hadi Asghari-Moghaddam, Michael Pellauer, Neal Crago, Aamer Jaleel, Edgar Solomonik, Joel Emer, and Christopher W Fletcher. Extensor: An accelerator for sparse tensor algebra. In IEEE\/ACM International Symposium on Microarchitecture, (MICRO'19), 2019."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2005.23"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458336.3465274"},{"key":"e_1_3_2_1_46_1","volume-title":"https:\/\/www.intel.com\/content\/www\/us\/en\/content-details\/739269\/fd-io-vpp-accelerate-the-host-stack-with-4th-gen-intel-xeon-scalable-processor-technology-guide.html, accessed","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. FD.io VPP - Accelerate the Host Stack with 4th Gen Intel\u00ae Xeon\u00ae Scalable Processor Technology Guide. https:\/\/www.intel.com\/content\/www\/us\/en\/content-details\/739269\/fd-io-vpp-accelerate-the-host-stack-with-4th-gen-intel-xeon-scalable-processor-technology-guide.html, accessed in 2023."},{"key":"e_1_3_2_1_47_1","volume-title":"Intel\u00ae DSA Transparent Offload","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. Intel\u00ae DSA Transparent Offload (DTO) Library. https:\/\/github.com\/intel\/DTO, accessed in 2023."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2009.31"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421294"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750392"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480051"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_2_1_54_1","volume-title":"Introduction to intel advanced vector extensions. Intel white paper, 23:1--21","author":"Lomont Chris","year":"2011","unstructured":"Chris Lomont. Introduction to intel advanced vector extensions. Intel white paper, 23:1--21, 2011."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322220"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446050"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00074"},{"key":"e_1_3_2_1_58_1","volume-title":"Karthikeyan Sankaralingam. Stream-dataflow Acceleration. In International Symposium on Computer Architecture, (ISCA'17)","author":"Nowatzki Tony","year":"2017","unstructured":"Tony Nowatzki, Vinay Gangadhar, Newsha Ardalani, and Karthikeyan Sankaralingam. Stream-dataflow Acceleration. In International Symposium on Computer Architecture, (ISCA'17), 2017."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.755466"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.526924"},{"key":"e_1_3_2_1_61_1","unstructured":"The Fast Data Project. Fd.io - the world's secure networking data plane. https:\/\/fd.io."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483550"},{"issue":"1","key":"e_1_3_2_1_63_1","first-page":"1","article-title":"Neon technology introduction","volume":"4","author":"Reddy Venu Gopal","year":"2008","unstructured":"Venu Gopal Reddy. Neon technology introduction. ARM Corporation, 4(1):1--33, 2008.","journal-title":"ARM Corporation"},{"issue":"173","key":"e_1_3_2_1_64_1","article-title":"the high-performance web server and reverse proxy","volume":"2008","author":"Reese Will","year":"2008","unstructured":"Will Reese. Nginx: the high-performance web server and reverse proxy. Linux Journal, 2008(173), 2008.","journal-title":"Linux Journal"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540725"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_3_2_1_67_1","volume-title":"Compute express link (CXL): Enabling heterogeneous data-centric computing with heterogeneous memory hierarchy","author":"Sharma Debendra Das","year":"2022","unstructured":"Debendra Das Sharma. Compute express link (CXL): Enabling heterogeneous data-centric computing with heterogeneous memory hierarchy. IEEE Micro, 2022."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195659"},{"key":"e_1_3_2_1_69_1","volume-title":"https:\/\/www.snia.org\/sdxi, accessed","author":"Smart Data Accelerator SNIA.","year":"2023","unstructured":"SNIA. Smart Data Accelerator Interface (SDXI) Specification. https:\/\/www.snia.org\/sdxi, accessed in 2023."},{"key":"e_1_3_2_1_70_1","volume-title":"the 25th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS'20)","author":"Sriraman Akshitha","year":"2020","unstructured":"Akshitha Sriraman and Abhishek Dhanotia. Accelerometer: Understanding acceleration opportunities for data center overheads at hyper-scale. In the 25th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS'20), March 2020."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.35"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.5555\/3585938.3585961"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555050.3569118"},{"key":"e_1_3_2_1_74_1","volume-title":"Data movement accelerator engines on a prototype Power10 processor","author":"Sugawara Yutaka","year":"2022","unstructured":"Yutaka Sugawara, Dong Chen, Ruud A. Haring, Abdullah Kayi, Eugene Ratzlaff, Robert M. Senger, Krishnan Sugavanam, Ralph Bellofatto, Ben J. Nathanson, and Craig Stunkel. Data movement accelerator engines on a prototype Power10 processor. IEEE Micro, 2022."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.809248"},{"key":"e_1_3_2_1_76_1","volume-title":"15th USENIX Symposium on Networked Systems Design and Implementation, (NSDI'18)","author":"Tootoonchian Amin","year":"2018","unstructured":"Amin Tootoonchian, Aurojit Panda, Chang Lan, Melvin Walls, Katerina Argyraki, Sylvia Ratnasamy, and Scott Shenker. ResQ: Enabling SLOs in network function virtualization. In 15th USENIX Symposium on Networked Systems Design and Implementation, (NSDI'18), 2018."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2007.4629228"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370479"},{"key":"e_1_3_2_1_79_1","volume-title":"2007 IEEE International Symposium on Performance Analysis of Systems & Software, (ISPASS'07)","author":"Vaidyanathan Karthikeyan","year":"2007","unstructured":"Karthikeyan Vaidyanathan and Dhabaleswar K Panda. Benefits of I\/O acceleration technology (I\/OAT) in clusters. In 2007 IEEE International Symposium on Performance Analysis of Systems & Software, (ISPASS'07), 2007."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00033"},{"key":"e_1_3_2_1_81_1","volume-title":"Accelerate page migration and use memcg for PMEM management. https:\/\/lwn.net\/Articles\/784925\/, accessed","author":"Yan Zi","year":"2023","unstructured":"Zi Yan. Accelerate page migration and use memcg for PMEM management. https:\/\/lwn.net\/Articles\/784925\/, accessed in 2023."},{"key":"e_1_3_2_1_82_1","volume-title":"An evaluation of edge TPU accelerators for convolutional neural networks. arXiv preprint arXiv:2102.10423","author":"Yazdanbakhsh Amir","year":"2021","unstructured":"Amir Yazdanbakhsh, Kiran Seshadri, Berkin Akin, James Laudon, and Ravi Narayanaswami. An evaluation of edge TPU accelerators for convolutional neural networks. arXiv preprint arXiv:2102.10423, 2021."},{"key":"e_1_3_2_1_83_1","volume-title":"2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture, (ISCA'21)","author":"Yuan Yifan","year":"2021","unstructured":"Yifan Yuan, Mohammad Alian, Yipeng Wang, Ren Wang, Ilia Kurakin, Charlie Tai, and Nam Sung Kim. Don't forget the I\/O when allocating your LLC. In 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture, (ISCA'21), 2021."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071127"}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","location":"La Jolla CA USA","acronym":"ASPLOS '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620665.3640401","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3620665.3640401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:42Z","timestamp":1750291422000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620665.3640401"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":84,"alternative-id":["10.1145\/3620665.3640401","10.1145\/3620665"],"URL":"https:\/\/doi.org\/10.1145\/3620665.3640401","relation":{},"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2024-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}