{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T08:24:41Z","timestamp":1769502281751,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":90,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF 2107470 and CCF 2316233"],"award-info":[{"award-number":["CCF 2107470 and CCF 2316233"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IBM-Illinois Discovery Accelerator Institute"},{"name":"NSF ACCESS","award":["#2138259, #2138286, #2138307, #2137603, and #2138296"],"award-info":[{"award-number":["#2138259, #2138286, #2138307, #2137603, and #2138296"]}]},{"name":"DARPA","award":["ACE, one of the seven centers in JUMP 2.0, a Semiconductor Research Corporation (SRC) program"],"award-info":[{"award-number":["ACE, one of the seven centers in JUMP 2.0, a Semiconductor Research Corporation (SRC) program"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756076","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"958-974","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["NetSparse: In-Network Acceleration of Distributed Sparse Kernels"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7946-2683","authenticated-orcid":false,"given":"Gerasimos","family":"Gerogiannis","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8046-7545","authenticated-orcid":false,"given":"Dimitrios","family":"Merkouriadis","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7770-003X","authenticated-orcid":false,"given":"Charles","family":"Block","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0612-4939","authenticated-orcid":false,"given":"Annus","family":"Zulfiqar","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, Michigan, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7305-6748","authenticated-orcid":false,"given":"Filippos","family":"Tofalos","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5168-9045","authenticated-orcid":false,"given":"Muhammad","family":"Shahbaz","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, Michigan, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2595-5228","authenticated-orcid":false,"given":"Josep","family":"Torrellas","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","author":"Adiletta Matthew","year":"2023","unstructured":"Matthew Adiletta, Jesmin\u00a0Jahan Tithi, Emmanouil-Ioannis Farsarakis, Gerasimos Gerogiannis, Robert Adolf, Robert Benke, Sidharth Kashyap, Samuel Hsia, Kartik Lakhotia, Fabrizio Petrini, Gu-Yeon Wei, and David Brooks. 2023. Characterizing the Scalability of Graph Convolutional Networks on Intel\u00ae PIUMA. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS). Raleigh, North Carolina."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS49909.2020.9220636"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654101"},{"key":"e_1_3_3_1_5_2","unstructured":"AMD. last accessed: 10\/18\/2024. Pensando. https:\/\/www.amd.com\/en\/accelerators\/pensando."},{"key":"e_1_3_3_1_6_2","unstructured":"AMD. last accessed: 10\/18\/2024. Performance of a Multi-Stage SDN Pipeline on Arm\u00ae vs AMD Pensando\u2122 Programmable Silicon. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/pensando-technical-docs\/white-papers\/pensando-comparison-of-dpu-hardware-strategies.pdf."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2015.75"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Ariful Azad Oguz Selvitopi Md\u00a0Taufique Hussain John\u00a0R Gilbert and Ayd\u0131n Bulu\u00e7. 2021. Combinatorial BLAS 2.0: Scaling combinatorial algorithms on distributed-memory systems. IEEE Transactions on Parallel and Distributed Systems 33 4 (2021) 989\u20131001.","DOI":"10.1109\/TPDS.2021.3094091"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Rajeev Balasubramonian Andrew\u00a0B Kahng Naveen Muralimanohar Ali Shafiee and Vaishnav Srinivas. 2017. CACTI 7: New tools for interconnect exploration in innovative off-chip memories. ACM Transactions on Architecture and Code Optimization (TACO) 14 2 (2017) 1\u201325.","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00014"},{"key":"e_1_3_3_1_11_2","volume-title":"Hot Chips","author":"Biswas Arijit","year":"2021","unstructured":"Arijit Biswas and Sailesh Kottapalli. 2021. Next-Gen Intel Xeon CPU-Sapphire Rapids. In Hot Chips , Vol.\u00a033."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640427"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2656877.2656890"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Pat Bosshart Glen Gibb Hun-Seok Kim George Varghese Nick McKeown Martin Izzard Fernando Mujica and Mark Horowitz. 2013. Forwarding Metamorphosis: Fast Programmable Match-Action Processing in Hardware for SDN. ACM SIGCOMM CCR (2013).","DOI":"10.1145\/2486001.2486011"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Ulrik Brandes. 2001. A faster algorithm for betweenness centrality. Journal of mathematical sociology 25 2 (2001) 163\u2013177.","DOI":"10.1080\/0022250X.2001.9990249"},{"key":"e_1_3_3_1_16_2","unstructured":"BROADCOM. last accessed: 10\/18\/2024. BCM88690. https:\/\/www.broadcom.com\/products\/ethernet-connectivity\/switching\/stratadnx\/bcm88690."},{"key":"e_1_3_3_1_17_2","unstructured":"BROADCOM. last accessed: 10\/18\/2024. Broadcom Ships Tomahawk 5 Industry\u2019s Highest Bandwidth Switch Chip to Accelerate AI\/ML Workloads. https:\/\/investors.broadcom.com\/news-releases\/news-release-details\/broadcom-ships-tomahawk-5-industrys-highest-bandwidth-switch."},{"key":"e_1_3_3_1_18_2","unstructured":"BROADCOM. last accessed: 10\/18\/2024. Trident 4 \/ BCM56880 Series. https:\/\/www.broadcom.com\/products\/ethernet-connectivity\/switching\/strataxgs\/bcm56880-series."},{"key":"e_1_3_3_1_19_2","unstructured":"BROADCOM. last accessed: 10\/18\/2024. Trident 5 \/ BCM78800 Series. https:\/\/www.broadcom.com\/products\/ethernet-connectivity\/switching\/strataxgs\/bcm78800."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2786572.2786579"},{"key":"e_1_3_3_1_21_2","unstructured":"Cepulis Darren. 2015. CERN OCP & HPC on ARM. https:\/\/indico.cern.ch\/event\/389301\/contributions\/1822797\/attachments\/778382\/1067363\/CERN_OCP_HPC_ARM_1.pdf. Accessed: 2025-06-20. Originally presented at the OCP & HPC on ARM workshop."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00025"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098823"},{"key":"e_1_3_3_1_24_2","unstructured":"The P4\u00a0Language Consortium. last accessed: 11\/20\/2024. P416 Language Specification. https:\/\/p4.org\/p4-spec\/docs\/P4-16-v1.0.0-spec.html."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Timothy\u00a0A Davis. 2019. Algorithm 1000: SuiteSparse: GraphBLAS: Graph algorithms in the language of sparse linear algebra. ACM Transactions on Mathematical Software (TOMS) 45 4 (2019) 1\u201325.","DOI":"10.1145\/3322125"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Timothy\u00a0A Davis and Yifan Hu. 2011. The University of Florida sparse matrix collection. ACM Transactions on Mathematical Software (TOMS) 38 1 (2011) 1\u201325.","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476178"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Michael Galles and Francis Matus. 2021. Pensando distributed services architecture. IEEE Micro 41 2 (2021) 43\u201349.","DOI":"10.1109\/MM.2021.3058560"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00081"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589054"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294869"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Song Han Xingyu Liu Huizi Mao Jing Pu Ardavan Pedram Mark\u00a0A Horowitz and William\u00a0J Dally. 2016. EIE: Efficient inference engine on compressed deep neural network. ACM SIGARCH Computer Architecture News 44 3 (2016) 243\u2013254.","DOI":"10.1145\/3007787.3001163"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"e_1_3_3_1_34_2","volume-title":"Merlin Element Library Deep Dive.","author":"Hemmert Karl\u00a0Scott","year":"2018","unstructured":"Karl\u00a0Scott Hemmert. 2018. Merlin Element Library Deep Dive. Technical Report. Sandia National Lab.(SNL-NM), Albuquerque, NM (United States)."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00053"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2025.11018301"},{"key":"e_1_3_3_1_37_2","volume-title":"Design Compiler User Guide","author":"Inc. Synopsys","year":"2016","unstructured":"Synopsys Inc.2016. Design Compiler User Guide. Synopsys. Version L-2016.03."},{"key":"e_1_3_3_1_38_2","unstructured":"Intel. last accessed: 10\/18\/2024. Intel Ethernet Controller 700 Series - Open vSwitch Hardware Acceleration Application Note. https:\/\/builders.intel.com\/docs\/networkbuilders\/intel-ethernet-controller-700-series-open-vswitch-hardware-acceleration-application-note.pdf."},{"key":"e_1_3_3_1_39_2","unstructured":"Intel. last accessed: 10\/18\/2024. Tofino: P4-programmable Ethernet switch ASIC that delivers better performance at lower power. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/network-io\/programmable-ethernet-switch\/tofino-series.html."},{"key":"e_1_3_3_1_40_2","unstructured":"Intel. last accessed: 10\/18\/2024. Tofino2: Second-generation P4-programmable Ethernet Switch ASIC that Continues to Deliver Programmability without Compromise. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/network-io\/programmable-ethernet-switch\/tofino-2-series.html."},{"key":"e_1_3_3_1_41_2","volume-title":"Intel oneAPI Math Kernel Library (oneMKL)","author":"Corporation Intel","year":"2025","unstructured":"Intel Corporation. 2025. Intel oneAPI Math Kernel Library (oneMKL)."},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","unstructured":"Hanchen Jin Zichao Yue Zhongyuan Zhao Yixiao Du Chenhui Deng Nitish Srivastava and Zhiru Zhang. 2024. Vesper: A Versatile Sparse Linear Algebra Accelerator With Configurable Compute Patterns. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2024) 1\u20131. 10.1109\/TCAD.2024.3496882","DOI":"10.1109\/TCAD.2024.3496882"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132764"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Mark Karol Michael Hluchyj and Samuel Morgan. 2003. Input versus output queueing on a space-division packet switch. IEEE Transactions on communications 35 12 (2003) 1347\u20131356.","DOI":"10.1109\/TCOM.1987.1096719"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"John Kim Wiliam\u00a0J Dally Steve Scott and Dennis Abts. 2008. Technology-driven highly-scalable Dragonfly topology. ACM SIGARCH Computer Architecture News 36 3 (2008) 77\u201388.","DOI":"10.1145\/1394608.1382129"},{"key":"e_1_3_3_1_47_2","unstructured":"Thomas\u00a0N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1609.02907 (2016)."},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480060"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00062"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00017"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3558481.3591073"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626183.3659975"},{"key":"e_1_3_3_1_53_2","first-page":"387","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Li Jialin","year":"2020","unstructured":"Jialin Li, Jacob Nelson, Ellis Michael, Xin Jin, and Dan\u00a0RK Ports. 2020. Pegasus: Tolerating skewed workloads in distributed storage with in-network coherence directories. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 387\u2013406."},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Shang Li Zhiyuan Yang Dhiraj Reddy Ankur Srivastava and Bruce Jacob. 2020. DRAMsim3: a cycle-accurate thermal-capable DRAM simulator. IEEE Computer Architecture Letters 19 2 (2020) 106\u2013109.","DOI":"10.1109\/LCA.2020.2973991"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322259"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575706"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037731"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651381"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"Patrick MacArthur Qian Liu Robert\u00a0D. Russell Fabrice Mizero Malathi Veeraraghavan and John\u00a0M. Dennis. 2017. An Integrated Tutorial on InfiniBand Verbs and MPI. IEEE Communications Surveys & Tutorials 19 4 (2017) 2894\u20132926.","DOI":"10.1109\/COMST.2017.2746083"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/IA349570.2019.00007"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","unstructured":"N. McKeown. 1999. The iSLIP scheduling algorithm for input-queued switches. IEEE\/ACM Transactions on Networking 7 2 (1999) 188\u2013201. 10.1109\/90.769767","DOI":"10.1109\/90.769767"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582069"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673152"},{"key":"e_1_3_3_1_64_2","unstructured":"National Center for Supercomputing Applications. 2024. Delta User Documentation. Retrieved 2024 from https:\/\/docs.ncsa.illinois.edu\/systems\/delta\/en\/latest\/"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2018.00013"},{"key":"e_1_3_3_1_66_2","unstructured":"NVIDIA. 2024. RoCE v2 Considerations. Retrieved 2024 from https:\/\/enterprise-support.nvidia.com\/s\/article\/roce-v2-considerations"},{"key":"e_1_3_3_1_67_2","unstructured":"NVIDIA. last accessed: 10\/18\/2024. CONNECTX-6 DX. https:\/\/www.nvidia.com\/en-us\/networking\/ethernet\/connectx-6-dx\/."},{"key":"e_1_3_3_1_68_2","unstructured":"NVIDIA. last accessed: 10\/18\/2024. NVIDIA Bluefield-3 Datasheet. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/documents\/datasheet-nvidia-bluefield-3-dpu.pdf\/."},{"key":"e_1_3_3_1_69_2","unstructured":"NVIDIA. last accessed: 10\/18\/2024. NVIDIA Bluefield Data Processing Units. https:\/\/www.nvidia.com\/en-us\/networking\/products\/data-processing-unit\/."},{"key":"e_1_3_3_1_70_2","unstructured":"NVIDIA. last accessed: 11\/20\/2024. AllReduce. https:\/\/docs.nvidia.com\/doca\/archive\/doca-v1.3\/allreduce\/index.html."},{"key":"e_1_3_3_1_71_2","volume-title":"The PageRank citation ranking: Bringing order to the web.","author":"Page Lawrence","year":"1999","unstructured":"Lawrence Page, Sergey Brin, Rajeev Motwani, and Terry Winograd. 1999. The PageRank citation ranking: Bringing order to the web. Technical Report. Stanford infolab."},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00076"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00052"},{"key":"e_1_3_3_1_74_2","doi-asserted-by":"publisher","unstructured":"A.\u00a0F. Rodrigues K.\u00a0S. Hemmert B.\u00a0W. Barrett C. Kersey R. Oldfield M. Weston R. Risen J. Cook P. Rosenfeld E. Cooper-Balis and B. Jacob. 2011. The Structural Simulation Toolkit. SIGMETRICS Perform. Eval. Rev. 38 4 (mar 2011) 37\u201342. 10.1145\/1964218.1964225","DOI":"10.1145\/1964218.1964225"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPSR.2001.923655"},{"key":"e_1_3_3_1_76_2","volume-title":"USENIX NSDI","author":"Sapio Amedeo","year":"2021","unstructured":"Amedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson, Panos Kalnis, Changhoon Kim, Arvind Krishnamurthy, Masoud Moshref, Dan Ports, and Peter Richt\u00e1rik. 2021. Scaling Distributed Machine Learning With In-Network Aggregation. In USENIX NSDI."},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00068"},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3461472"},{"key":"e_1_3_3_1_79_2","unstructured":"ServeTheHome. 2020. Pensando Distributed Services Architecture \u2013 SmartNIC. https:\/\/www.servethehome.com\/pensando-distributed-services-architecture-smartnic\/."},{"key":"e_1_3_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491418.3530773"},{"key":"e_1_3_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544269"},{"key":"e_1_3_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490422.3502357"},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00062"},{"key":"e_1_3_3_1_84_2","doi-asserted-by":"crossref","unstructured":"Aaron Stillmaker and Bevan Baas. 2017. Scaling equations for the accurate prediction of CMOS device performance from 180 nm to 7 nm. Integration 58 (2017) 74\u201381.","DOI":"10.1016\/j.vlsi.2017.02.002"},{"key":"e_1_3_3_1_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSE.2007.44"},{"key":"e_1_3_3_1_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507726"},{"key":"e_1_3_3_1_87_2","unstructured":"Wikipedia. 2024. Goodput. Retrieved 2024 from https:\/\/en.wikipedia.org\/wiki\/Goodput"},{"key":"e_1_3_3_1_88_2","unstructured":"Xilinx. last accessed: 10\/18\/2024. Alveo SN1000 SmartNICs. https:\/\/www.xilinx.com\/content\/dam\/xilinx\/publications\/product-briefs\/sn1000-product-brief.pdf."},{"key":"e_1_3_3_1_89_2","unstructured":"Xilinx. last accessed: 10\/18\/2024. Alveo U250 Data Center Accelerator Card. https:\/\/www.xilinx.com\/products\/boards-and-kits\/alveo\/u250.html."},{"key":"e_1_3_3_1_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544262"},{"key":"e_1_3_3_1_91_2","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433815"}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756076","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:43:02Z","timestamp":1769463782000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756076"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":90,"alternative-id":["10.1145\/3725843.3756076","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756076","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}