{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:52:13Z","timestamp":1782996733353,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":105,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"name":"US Army Research Office","award":["W911NF22C0082"],"award-info":[{"award-number":["W911NF22C0082"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3800534","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"603-617","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["UpDown: Efficient Manycore based on Many Threading and Scalable Memory Parallelism"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1600-1459","authenticated-orcid":false,"given":"Andronicus","family":"Rajasukumar","sequence":"first","affiliation":[{"name":"University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7269-9155","authenticated-orcid":false,"given":"Ruiqi","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7469-6130","authenticated-orcid":false,"given":"Tianchi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3548-5652","authenticated-orcid":false,"given":"Yuqing (Ivy)","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1275-2918","authenticated-orcid":false,"given":"Tianshuo","family":"Su","sequence":"additional","affiliation":[{"name":"Google LLC, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5124-8283","authenticated-orcid":false,"given":"Marziyeh","family":"Nourian","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5282-1379","authenticated-orcid":false,"given":"Jianru","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4952-1486","authenticated-orcid":false,"given":"Jiya","family":"Su","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5452-3218","authenticated-orcid":false,"given":"Rajat","family":"Khandelwal","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9955-2643","authenticated-orcid":false,"given":"Alexander","family":"Fell","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8107-6474","authenticated-orcid":false,"given":"David F.","family":"Gleich","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0124-0463","authenticated-orcid":false,"given":"Yanjing","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University, Oakland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0816-8150","authenticated-orcid":false,"given":"Henry","family":"Hoffmann","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1204-206X","authenticated-orcid":false,"given":"Andrew A.","family":"Chien","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, USA and Argonne National Laboratory, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2022. AGILE: ADVANCED GRAPHIC INTELLIGENCE LOGICAL COMPUTING ENVIRONMENT Program. https:\/\/www.iarpa.gov\/research-programs\/agile."},{"key":"e_1_3_3_2_3_2","unstructured":"Sriram Aananthakrishnan Shamsul Abedin Vincent Cave Fabio Checconi Kristof\u00a0Du Bois Stijn Eyerman Joshua\u00a0B. Fryman Wim Heirman Jason Howard Ibrahim Hur Samkit Jain Marek\u00a0M. Landowski Kevin Ma Jarrod Nelson Robert Pawlowski Fabrizio Petrini\u00a0Sebastian Szkoda Sanjaya Tayal Jesmin\u00a0Jahan Tithi and Yves Vandriessche. 2025. PIUMA: Programmable Integrated Unified Memory Architecture. arxiv:https:\/\/arXiv.org\/abs\/2010.06277\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2010.06277"},{"key":"e_1_3_3_2_4_2","unstructured":"Advanced Micro Devices Inc.2025. 5th Generation AMD EPYC\u2122 9005 Series Processors. https:\/\/www.amd.com\/en\/products\/processors\/server\/epyc\/9005-series.html"},{"key":"e_1_3_3_2_5_2","unstructured":"Advanced Micro Devices Inc.2025. AMD64 Technology AMD64 Architecture Programmer\u2019s Manual Volumes 1\u20135. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/processor-tech-docs\/programmer-references\/40332.pdf."},{"key":"e_1_3_3_2_6_2","volume-title":"Introducing AMD CDNATM 3 Architecture","author":"Inc. Advanced Micro Devices,","year":"2025","unstructured":"Advanced Micro Devices, Inc.2025. Introducing AMD CDNATM 3 Architecture. White Paper. Advanced Micro Devices, Inc.https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-tech-docs\/white-papers\/amd-cdna-3-white-paper.pdf"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Masab Ahmad Halit Dogan Jos\u00e9\u00a0A. Joao and Omer Khan. 2020. In-Hardware Moving Compute to Data Model to Accelerate Thread Synchronization on Large Multicores. IEEE Micro 40 1 (2020) 83\u201392. 10.1109\/MM.2019.2955079","DOI":"10.1109\/MM.2019.2955079"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Tero Aittokallio and Benno Schwikowski. 2006. Graph-based methods for analysing networks in cell biology. Briefings in Bioinformatics 7 3 (09 2006) 243\u2013255. 10.1093\/bib\/bbl022","DOI":"10.1093\/bib\/bbl022"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/77726.255132"},{"key":"e_1_3_3_2_10_2","unstructured":"Amazon Web Services Inc.2025. AWS Graviton Processors. https:\/\/aws.amazon.com\/ec2\/graviton"},{"key":"e_1_3_3_2_11_2","unstructured":"Ampere Computing LLC. 2025. Ampere Processing Platforms. https:\/\/amperecomputing.com\/products\/processors"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_3_3_2_13_2","unstructured":"Scott Beamer Krste Asanovi\u0107 and David Patterson. 2017. The GAP Benchmark Suite. http:\/\/arxiv.org\/abs\/1508.03619 arXiv:https:\/\/arXiv.org\/abs\/1508.03619 [cs]."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Trevor\u00a0E. Carlson Wim Heirman Osman Allam Stefanos Kaxiras and Lieven Eeckhout. 2015. The load slice core microarchitecture. SIGARCH Comput. Archit. News 43 3S (June 2015) 272\u2013284. 10.1145\/2872887.2750407","DOI":"10.1145\/2872887.2750407"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Tien-Fu Chen and Jean-Loup Baer. 1995. Effective hardware-based data prefetching for high-performance processors. IEEE Trans. Comput. 44 5 (1995) 609\u2013623. 10.1109\/12.381947","DOI":"10.1109\/12.381947"},{"key":"e_1_3_3_2_16_2","volume-title":"UpDown Accelerator Instruction Set Architecture (ISA) v2.4","author":"Chien Andrew","year":"2024","unstructured":"Andrew Chien, Andronicus Rajasukumar, Marziyeh Nourian, Yuqing Wang, Tianshuo Su, Chen Zou, and Yuanwei Fang. 2024. UpDown Accelerator Instruction Set Architecture (ISA) v2.4. Technical Report TR-2024-03. University of Chicago. https:\/\/newtraell.cs.uchicago.edu\/research\/publications\/techreports\/TR-2024-03"},{"key":"e_1_3_3_2_17_2","unstructured":"Andrew\u00a0A. Chien Charles Colley Jianru Ding Alexander Fell David\u00a0F. Gleich Henry Hoffmann Moubarak Jeje Rajat Khandelwal Yanjing Li Jose\u00a0M Monsalve-Diaz Marziyeh Nourian Andronicus Rajasukumar Jiya Su Tianshuo Su Yuqing\u00a0(Ivy) Wang Wenyi Wang Ruiqi Xu and Tianchi Zhang. under review. UpDown: A Supercomputer Co-designed for Scalable Graph Processing. IEEE Trans. Parallel Distrib. Syst. (under review)."},{"key":"e_1_3_3_2_18_2","volume-title":"cuGraph: GPU-accelerated Graph Analytics Library (RAPIDS)","author":"Development\u00a0Team cuGraph","year":"2025","unstructured":"cuGraph Development\u00a0Team. 2025. cuGraph: GPU-accelerated Graph Analytics Library (RAPIDS). https:\/\/github.com\/rapidsai\/cugraph"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00053"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/30350.30372"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/285930.285953"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Scott Davidson Shaolin Xie Christopher Torng Khalid Al-Hawai Austin Rovinski Tutu Ajayi Luis Vega Chun Zhao Ritchie Zhao Steve Dai Aporva Amarnath Bandhav Veluri Paul Gao Anuj Rao Gai Liu Rajesh\u00a0K. Gupta Zhiru Zhang Ronald Dreslinski Christopher Batten and Michael\u00a0Bedford Taylor. 2018. The Celerity Open-Source 511-Core RISC-V Tiered Accelerator Fabric: Fast Architectures and Design Methodologies for Fast Chips. IEEE Micro 38 2 (2018) 30\u201341. 10.1109\/MM.2018.022071133","DOI":"10.1109\/MM.2018.022071133"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Timothy\u00a0A. Davis and Yifan Hu. 2011. The university of Florida sparse matrix collection. 25\u00a0pages. 10.1145\/2049662.2049663","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.434"},{"key":"e_1_3_3_2_25_2","unstructured":"Saurabh Dighe Sriram Vangal Nitin Borkar and Shekhar Borkar. 2009. LESSONS LEARNED FROM THE 80-CORE TERA-SCALE RESEARCH PROCESSOR. Intel technology journal 13 4 (2009)."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"David\u00a0R. Ditzel and the Esperanto\u00a0team. 2022. Accelerating ML Recommendation With Over 1 000 RISC-V\/Tensor Processors on Esperanto\u2019s ET-SoC-1 Chip. IEEE Micro 42 3 (2022) 31\u201338. 10.1109\/MM.2022.3140674","DOI":"10.1109\/MM.2022.3140674"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/IA3.2016.007"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"S.J. Eggers J.S. Emer H.M. Levy J.L. Lo R.L. Stamm and D.M. Tullsen. 1997. Simultaneous multithreading: a platform for next-generation processors. IEEE Micro 17 5 (1997) 12\u201319. 10.1109\/40.621209","DOI":"10.1109\/40.621209"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830809"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123983"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3731599.3767499"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Kourosh Gharachorloo Anoop Gupta and John Hennessy. 1992. Hiding memory latency using dynamic scheduling in shared-memory multiprocessors. ACM SIGARCH Computer Architecture News 20 2 (May 1992) 22\u201333. 10.1145\/146628.139678","DOI":"10.1145\/146628.139678"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Fred\u00a0G Gustavson. 1978. Two fast algorithms for sparse matrices: Multiplication and permuted transposition. ACM Transactions on Mathematical Software (TOMS) 4 3 (1978) 250\u2013269.","DOI":"10.1145\/355791.355796"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Maurice Herlihy. 1991. Wait-free synchronization. 13 1 (Jan. 1991) 124\u2013149. 10.1145\/114005.102808","DOI":"10.1145\/114005.102808"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.5555\/1734069"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2003.1183549"},{"key":"e_1_3_3_2_37_2","unstructured":"Intel Corporation. 2024. Intel\u00ae Xeon\u00ae 6960P Processor. Retrieved 2025-07-28 from https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/240775\/intel-xeon-6960p-processor-432m-cache-2-70-ghz\/specifications.html"},{"key":"e_1_3_3_2_38_2","unstructured":"Intel Corporation. 2025. Intel\u00ae VTune\u2122 Profiler. Retrieved 2025-07-28 from https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/vtune-profiler.html"},{"key":"e_1_3_3_2_39_2","unstructured":"Intel Corporation. 2025. Intel\u00ae Math Kernel Library (Intel\u00ae MKL). https:\/\/software.intel.com\/en-us\/intel-mkl."},{"key":"e_1_3_3_2_40_2","unstructured":"Intel Corporation. 2025. Intel\u00ae 64 and IA-32 Architectures Software Developer Manuals. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/intel-sdm.html."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557149"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/IMW.2017.7939084"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00061"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.73"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772751"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626183.3659975"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749720"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/1081870.1081893"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/232973.232993"},{"key":"e_1_3_3_2_50_2","series-title":"(ICCAD \u201911)","first-page":"694","volume-title":"Proceedings of the International Conference on Computer-Aided Design","author":"Li Sheng","year":"2011","unstructured":"Sheng Li, Ke Chen, Jung\u00a0Ho Ahn, Jay\u00a0B. Brockman, and Norman\u00a0P. Jouppi. 2011. CACTI-P: architecture-level modeling for SRAM-based structures with advanced leakage reduction techniques. In Proceedings of the International Conference on Computer-Aided Design (San Jose, California) (ICCAD \u201911). IEEE Press, 694\u2013701."},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Sean Lie. 2023. Cerebras Architecture Deep Dive: First Look Inside the Hardware\/Software Co-Design for Deep Learning. IEEE Micro 43 3 (2023) 18\u201330. 10.1109\/MM.2023.3256384","DOI":"10.1109\/MM.2023.3256384"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2008.4541126"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","unstructured":"Andrew Lumsdaine Douglas Gregor Bruce Hendrickson and Jonathan Berry. 2007. Challenges in Parallel Graph Processing. Parallel Processing Letters 17 (03 2007) 5\u201320. 10.1142\/S0129626407002843","DOI":"10.1142\/S0129626407002843"},{"key":"e_1_3_3_2_54_2","unstructured":"Haocong Luo Yahya\u00a0Can Tu\u011frul F.\u00a0Nisa Bostanc\u0131 Ataberk Olgun A.\u00a0Giray Ya\u011fl\u0131k\u00e7\u0131 and Onur Mutlu. 2023. Ramulator 2.0: A Modern Modular and Extensible DRAM Simulator."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637543.3652879"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40843-4_30"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Daniele Merico David Gfeller and Gary\u00a0D Bader. 2009. How to visually interpret biological data using networks. Nature biotechnology 27 10 (2009) 921\u2013924.","DOI":"10.1038\/nbt.1567"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2003.1183532"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/139669.139715"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/165123.165158"},{"key":"e_1_3_3_2_61_2","volume-title":"NVIDIA Blackwell Architecture","year":"2023","unstructured":"NVIDIA. 2023. NVIDIA Blackwell Architecture. Technical Brief. NVIDIA. https:\/\/resources.nvidia.com\/en-us-blackwell-architecture"},{"key":"e_1_3_3_2_62_2","unstructured":"NVIDIA Corporation. [n. d.]. NVIDIA Nsight Compute. Retrieved 2025-07-28 from https:\/\/developer.nvidia.com\/nsight-compute"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.25080\/shinma-7f4c6e7-00f"},{"key":"e_1_3_3_2_64_2","unstructured":"Andreas Olofsson. 2016. Epiphany-V: A 1024 processor 64-bit RISC System-On-Chip. arxiv:https:\/\/arXiv.org\/abs\/1610.01832\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/1610.01832"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527400"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071089"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.5555\/79137"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695794.3695801"},{"key":"e_1_3_3_2_69_2","volume-title":"Graph databases: new opportunities for connected data","author":"Robinson Ian","year":"2015","unstructured":"Ian Robinson, Jim Webber, and Emil Eifrem. 2015. Graph databases: new opportunities for connected data. \" O\u2019Reilly Media, Inc.\"."},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/1736020.1736055"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","unstructured":"Paul Scheffler Thomas Benz Viviane Potocnik Tim Fischer Luca Colagrande Nils Wistoff Yichao Zhang Luca Bertaccini Gianmarco Ottavi Manuel Eggimann Matheus Cavalcante Gianna Paulin Frank\u00a0K. G\u00fcrkaynak Davide Rossi and Luca Benini. 2025. Occamy: A 432-Core Dual-Chiplet Dual-HBM2E 768-DP-GFLOP\/s RISC-V System for 8-to-64-bit Dense and Sparse Computing in 12-nm FinFET. IEEE Journal of Solid-State Circuits 60 4 (2025) 1324\u20131338. 10.1109\/JSSC.2025.3529249","DOI":"10.1109\/JSSC.2025.3529249"},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"publisher","unstructured":"Paul Scheffler Florian Zaruba Fabian Schuiki Torsten Hoefler and Luca Benini. 2023. Sparse Stream Semantic Registers: A Lightweight ISA Extension Accelerating General Sparse Linear Algebra. IEEE Transactions on Parallel and Distributed Systems 34 12 (2023) 3147\u20133161. 10.1109\/TPDS.2023.3322029","DOI":"10.1109\/TPDS.2023.3322029"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00095"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527379"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.932535"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","unstructured":"J.E. Smith and A.R. Pleszkun. 1988. Implementing precise interrupts in pipelined processors. IEEE Trans. Comput. 37 5 (1988) 562\u2013573. 10.1109\/12.4607","DOI":"10.1109\/12.4607"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.5555\/800048.801719"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","unstructured":"Aaron Stillmaker and Bevan Baas. 2017. Scaling equations for the accurate prediction of CMOS device performance from 180nm to 7nm. Integration 58 (2017) 74\u201381. 10.1016\/j.vlsi.2017.02.002","DOI":"10.1016\/j.vlsi.2017.02.002"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC67600.2025.11196311"},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"publisher","unstructured":"M.\u00a0Aater Suleman Onur Mutlu Moinuddin\u00a0K. Qureshi and Yale\u00a0N. Patt. 2009. Accelerating critical section execution with asymmetric multi-core architectures. SIGARCH Comput. Archit. News 37 1 (March 2009) 253\u2013264. 10.1145\/2528521.1508274","DOI":"10.1145\/2528521.1508274"},{"key":"e_1_3_3_2_81_2","unstructured":"Synopsys Inc.2025. Synopsys University Program \u2013 Teaching Resources. https:\/\/www.synopsys.com\/community\/university-program\/teaching-resources.html"},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"publisher","unstructured":"M.B. Taylor J. Kim J. Miller D. Wentzlaff F. Ghodrat B. Greenwald H. Hoffman P. Johnson Jae-Wook Lee W. Lee A. Ma A. Saraf M. Seneski N. Shnidman V. Strumpen M. Frank S. Amarasinghe and A. Agarwal. 2002. The Raw microprocessor: a computational fabric for software circuits and general-purpose programs. IEEE Micro 22 2 (2002) 25\u201335. 10.1109\/MM.2002.997877","DOI":"10.1109\/MM.2002.997877"},{"key":"e_1_3_3_2_83_2","volume-title":"RAPIDS: Libraries for End-to-End GPU Data Science","author":"Team RAPIDS\u00a0Development","year":"2023","unstructured":"RAPIDS\u00a0Development Team. 2023. RAPIDS: Libraries for End-to-End GPU Data Science. https:\/\/rapids.ai"},{"key":"e_1_3_3_2_84_2","unstructured":"The Graph 500 Steering Committee. [n. d.]. Graph 500 Benchmark. Retrieved 2026-03-09 from https:\/\/graph500.org\/"},{"key":"e_1_3_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.5555\/62972.62977"},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"publisher","unstructured":"A. Tumeo and J. Feo. 2015. Irregular Applications: From Architectures to Algorithms [Guest editors; introduction]. Computer 48 08 (aug 2015) 14\u201316. 10.1109\/MC.2015.233","DOI":"10.1109\/MC.2015.233"},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1145\/139669.140382"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","unstructured":"Luming Wang Xu Zhang Songyue Wang Zhuolun Jiang Tianyue Lu Mingyu Chen Siwei Luo and Keji Huang. 2024. Asynchronous Memory Access Unit: Exploiting Massive Parallelism for Far Memory Access. ACM Trans. Archit. Code Optim. 21 3 Article 55 (Sept. 2024) 28\u00a0pages. 10.1145\/3663479","DOI":"10.1145\/3663479"},{"key":"e_1_3_3_2_89_2","unstructured":"Minjie Wang Da Zheng Zihao Ye Quan Gan Mufei Li Xiang Song Jinjing Zhou Chao Ma Lingfan Yu Yu Gai Tianjun Xiao Tong He George Karypis Jinyang Li and Zheng Zhang. 2020. Deep Graph Library: A Graph-Centric Highly-Performant Package for Graph Neural Networks. arxiv:https:\/\/arXiv.org\/abs\/1909.01315\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1909.01315"},{"key":"e_1_3_3_2_90_2","unstructured":"Yuqing Wang Charles Colley Brian Wheatman Jiya Su David\u00a0F. Gleich and Andrew\u00a0A. Chien. 2025. How Fast Can Graph Computations Go on Fine-grained Parallel Architectures. arxiv:https:\/\/arXiv.org\/abs\/2507.00949\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2507.00949"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"publisher","unstructured":"Yangzihao Wang Andrew Davidson Yuechao Pan Yuduo Wu Andy Riffel and John\u00a0D. Owens. 2016. Gunrock: a high-performance graph processing library on the GPU. SIGPLAN Not. 51 8 Article 11 (feb 2016) 12\u00a0pages. 10.1145\/3016078.2851145","DOI":"10.1145\/3016078.2851145"},{"key":"e_1_3_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00141"},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-02436-7_6"},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967954"},{"key":"e_1_3_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322229"},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC67600.2025.11196373"},{"key":"e_1_3_3_2_97_2","unstructured":"x86-Guide. n. d.. Intel\u00ae Xeon\u00ae Gold 6138 \u2014 CPU specifications (x86-Guide). https:\/\/www.x86-guide.net\/en\/cpu\/Intel-Xeon-Gold-6138-cpu-no6271.html"},{"key":"e_1_3_3_2_98_2","unstructured":"Ruiqi Xu. 2025. Accelerating GNN Aggregation Using a Vertex-Centric Approach. https:\/\/people.cs.uchicago.edu\/\u00a0aachien\/lssg\/research\/10x10\/Ruiqi_Xu_MS.pdf"},{"key":"e_1_3_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/2350190.2350193"},{"key":"e_1_3_3_2_100_2","doi-asserted-by":"publisher","unstructured":"Shimeng Yu and Tae-Hyeon Kim. 2024. Semiconductor Memory Technologies: State-of-the-Art and Future Trends. Computer 57 4 (2024) 150\u2013154. 10.1109\/MC.2024.3363269","DOI":"10.1109\/MC.2024.3363269"},{"key":"e_1_3_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830807"},{"key":"e_1_3_3_2_102_2","doi-asserted-by":"publisher","unstructured":"Florian Zaruba Fabian Schuiki Torsten Hoefler and Luca Benini. 2021. Snitch: A Tiny Pseudo Dual-Issue Processor for Area and Energy Efficient Execution of Floating-Point Intensive Workloads. IEEE Trans. Comput. 70 11 (Nov. 2021) 1845\u20131860. 10.1109\/tc.2020.3027900","DOI":"10.1109\/tc.2020.3027900"},{"key":"e_1_3_3_2_103_2","doi-asserted-by":"publisher","unstructured":"Dan Zhang Xiaoyu Ma Michael Thomson and Derek Chiou. 2018. Minnow: Lightweight Offload Engines for Worklist Management and Worklist-Directed Prefetching. ACM SIGPLAN Notices 53 2 (March 2018) 593\u2013607. 10.1145\/3296957.3173197","DOI":"10.1145\/3296957.3173197"},{"key":"e_1_3_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8257937"},{"key":"e_1_3_3_2_105_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00039"},{"key":"e_1_3_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1109\/NoCArc57472.2022.9911299"}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3797905.3800534","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:42:32Z","timestamp":1782996152000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3800534"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":105,"alternative-id":["10.1145\/3797905.3800534","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3800534","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}