{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:00:46Z","timestamp":1776931246359,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":83,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92373205"],"award-info":[{"award-number":["92373205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756068","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"1347-1362","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LEGOSim: A Unified Parallel Simulation Framework for Multi-chiplet Heterogeneous Integration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9305-1962","authenticated-orcid":false,"given":"Tiantian","family":"Lin","sequence":"first","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University and Hangzhou High-Tech Zone (Binjiang), Institute of Blockchain and Data Security, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3291-7806","authenticated-orcid":false,"given":"Cheng","family":"Qiu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2263-5643","authenticated-orcid":false,"given":"Xiaohang","family":"Wang","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University and Hangzhou High-Tech Zone (Binjiang), Institute of Blockchain and Data Security, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1233-9557","authenticated-orcid":false,"given":"Ling","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Western Australia, Western Australia, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1875-0730","authenticated-orcid":false,"given":"Zhulin","family":"Zheng","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University and Hangzhou High-Tech Zone (Binjiang), Institute of Blockchain and Data Security, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7453-9365","authenticated-orcid":false,"given":"Yingtao","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Nevada, Las Vegas, Las Vegas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2056-0569","authenticated-orcid":false,"given":"Amit Kumar","family":"Singh","sequence":"additional","affiliation":[{"name":"University of Essex, Essex, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2878-1853","authenticated-orcid":false,"given":"Jieming","family":"Yin","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5619-8226","authenticated-orcid":false,"given":"Sihai","family":"Qiu","sequence":"additional","affiliation":[{"name":"Beijing Smart-chip Microelectronics Technology Co., Ltd,, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8330-2041","authenticated-orcid":false,"given":"Xiaodong","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0241-8138","authenticated-orcid":false,"given":"Xin","family":"Tang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4802-9587","authenticated-orcid":false,"given":"Jie","family":"Song","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6440-7550","authenticated-orcid":false,"given":"Mingzhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3441-6277","authenticated-orcid":false,"given":"Kui","family":"Ren","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Blockchain and Data Security, Zhejiang University and Hangzhou High-Tech Zone (Binjiang), Institute of Blockchain and Data Security, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"[n. d.]. HBM3 IP technical bulletin. https:\/\/www.synopsys.com\/designware-ip\/technical-bulletin\/hbm3-ip-dwtb.html"},{"key":"e_1_3_3_1_3_2","unstructured":"[n. d.]. Intel Distribution of OpenVINO toolkit. https:\/\/software.intel.com\/en-us\/openvino-toolkit"},{"key":"e_1_3_3_1_4_2","unstructured":"[n. d.]. NVIDIA H100 parameter. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/gtcs22\/data-center\/h100\/PB-11133-001_v01.pdf"},{"key":"e_1_3_3_1_5_2","unstructured":"[n. d.]. SK Hynix details its DDR5-6400 DRAM dhip. https:\/\/www.anandtech.com\/show\/13999\/sk-hynix-details-its-ddr56400-dram-chip"},{"key":"e_1_3_3_1_6_2","unstructured":"[n. d.]. The SR-71 of computing: Intel Ponte Vecchio retires after five years. https:\/\/www.jonpeddie.com\/news\/the-sr-71-of-computing-intel-ponte-vecchio-retires-after-five-years\/"},{"key":"e_1_3_3_1_7_2","unstructured":"2022. PCI express base specification revision 6.0 version 1.0."},{"key":"e_1_3_3_1_8_2","unstructured":"2025. LEGOSim. https:\/\/github.com\/FCAS-LAB\/LEGOSIM_MICRO."},{"key":"e_1_3_3_1_9_2","unstructured":"2025. LEGOSim User Manual. https:\/\/github.com\/FCAS-LAB\/LEGOSIM_MICRO\/blob\/main\/LEGOSim_Manual.pdf."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919636"},{"key":"e_1_3_3_1_11_2","volume-title":"Zen 5 architecture overview","year":"2023","unstructured":"AMD. 2023. Zen 5 architecture overview. Whitepaper."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Yehia Arafa Abdel-Hameed\u00a0A Badawy Gopinath Chennupati Nandakishore Santhi and Stephan Eidenbenz. 2019. PPT-GPU: scalable GPU performance modeling. IEEE Comput. Archit. Lett. 18 1 (2019) 55\u201358.","DOI":"10.1109\/LCA.2019.2904497"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Todd Austin Eric Larson and Dan Ernst. 2002. SimpleScalar: an infrastructure for computer system modeling. Computer 35 2 (2002) 59\u201367.","DOI":"10.1109\/2.982917"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Grey Ballard Christopher Siefert and Jonathan Hu. 2016. Reducing communication costs for sparse matrix multiplication within algebraic multigrid. SIAM J. Sci. Comput. 38 3 (2016) 203\u2013231.","DOI":"10.1137\/15M1028807"},{"key":"e_1_3_3_1_15_2","first-page":"241","volume-title":"Proc. Great Lakes Symp. VLSI","author":"Haozhe\u00a0Zhu Jinshan Zhang Shunli Wang Xiaoyang Kang Lhua Zhang Mingyu\u00a0Wang Bo\u00a0Jiao,","year":"2021","unstructured":"Jinshan Zhang Shunli Wang Xiaoyang Kang Lhua Zhang Mingyu\u00a0Wang Bo\u00a0Jiao, Haozhe\u00a0Zhu and Chixiao Chen. 2021. Computing utilization enhancement for chiplet-based homogeneous processing-in-memory deep learning processors. In Proc. Great Lakes Symp. VLSI. 241\u2013246."},{"key":"e_1_3_3_1_16_2","first-page":"1","volume-title":"Proc. SC Conf.","author":"Bulu\u00e7 A.","year":"2011","unstructured":"A. Bulu\u00e7 and K. Madduri. 2011. Parallel breadth-first search on distributed memory systems. In Proc. SC Conf.1\u201312."},{"key":"e_1_3_3_1_17_2","first-page":"4","volume-title":"UTM Lab Meeting","author":"Carneiro G.","year":"2010","unstructured":"G. Carneiro. 2010. NS-3: Network simulator 3. In UTM Lab Meeting. 4\u20135."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2015.7245728"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"P.\u00a0Y. Chen X. Peng and S. Yu. 2018. NeuroSim: a circuit-level macro model for benchmarking neuro-inspired architectures in online learning. IEEE Trans. Comput.-Aided Design Integr. Circuits Syst. 37 12 (2018) 3067\u20133080.","DOI":"10.1109\/TCAD.2018.2789723"},{"key":"e_1_3_3_1_20_2","first-page":"772","volume-title":"PDPTA","author":"Cortes Toni","year":"1999","unstructured":"Toni Cortes and Jes\u00fas Labarta. 1999. HRaid: A Flexible Storage-system Simulator.. In PDPTA. 772\u2013778."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-46077-7_12"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"K. Deb A. Pratap S. Agarwal and T. Meyarivan. 2002. A fast and elitist multi-objective genetic algorithm: NSGA-II. IEEE Trans. Evolutionary Computation 6 2 (2002) 182\u2013197.","DOI":"10.1109\/4235.996017"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Yanchi Dong Xueping Liu Xiaochen Hao Yun Liang Ru Huang Le Ye and Tianyu Jia. 2024. Hierarchical power co-Optimization and management for LLM chiplet designs. ICCAD \u201924 (2024) 1\u20139.","DOI":"10.1145\/3676536.3676740"},{"key":"e_1_3_3_1_24_2","unstructured":"Jan Edler. 1994. Dinero IV: trace-driven uniprocessor cache simulator. (1994). https:\/\/pages.cs.wisc.edu\/\u00a0markhill\/DineroIV\/"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.5555\/1855084"},{"key":"e_1_3_3_1_26_2","first-page":"731","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Feng Yinxiao","year":"2024","unstructured":"Yinxiao Feng, Yuchen Wei, Dong Xiang, and Kaisheng Ma. 2024. Evaluating chiplet-based large-scale interconnection networks via cycle-accurate packet-parallel simulation. In Proc. USENIX Annu. Tech. Conf.731\u2013747."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614310"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2001.977259"},{"key":"e_1_3_3_1_29_2","unstructured":"Chaoyang He Shen Li Mahdi Soltanolkotabi and Salman Avestimehr. 2021. PipeTransformer: automated elastic pipelining for distributed training of transformers. arXiv (2021)."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_31_2","first-page":"91","volume-title":"Proc. Int\u2019l Summer School Adv. Comput. Archit.","author":"Heirman W.","year":"2012","unstructured":"W. Heirman, T. Carlson, and L. Eeckhout. 2012. Sniper: scalable and accurate parallel multi-core simulation. In Proc. Int\u2019l Summer School Adv. Comput. Archit.91\u201394."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"e_1_3_3_1_33_2","volume-title":"OpenCL Beignet Project","year":"2018","unstructured":"Intel. 2018. OpenCL Beignet Project. Technical Report. Intel."},{"key":"e_1_3_3_1_34_2","first-page":"519","volume-title":"Proc. USENIX Technical Conference","author":"Jiang C.","year":"2023","unstructured":"C. Jiang, A. Jayarajan, and H. Lu. 2023. Arbitor: a numerically accurate hardware emulation tool for DNN accelerators. In Proc. USENIX Technical Conference. 519\u2013536."},{"key":"e_1_3_3_1_35_2","first-page":"1","volume-title":"Proc. IEEE Hot Chips Symp.","author":"Jiang H.","year":"2022","unstructured":"H. Jiang. 2022. Intel\u2019s Ponte Vecchio GPU: Architecture, Systems & Software. In Proc. IEEE Hot Chips Symp.1\u201329."},{"key":"e_1_3_3_1_36_2","volume-title":"BookSim 2.0 user\u2019s guide","author":"Jiang Nan","year":"2010","unstructured":"Nan Jiang, George Michelogiannakis, Daniel Becker, Brian Towles, and William\u00a0J Dally. 2010. BookSim 2.0 user\u2019s guide. Technical Report. Stanford Univ."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"M. Jung J. Zhang and A. Abulila. 2017. SimpleSSD: modeling solid state drives for holistic system simulation. IEEE Computer Architecture Letters 17 1 (2017) 37\u201341.","DOI":"10.1109\/LCA.2017.2750658"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC47756.2020.9045734"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Ivan Khokhlov Egor Davydenko and Ilya Osokin. 2020. Tiny-YOLO object detection supplemented with geometrical data. arXiv.","DOI":"10.1109\/VTC2020-Spring48590.2020.9128749"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78713-4_7"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Abbas\u00a0Eslami Kiasari Zhonghai Lu and Axel Jantsch. 2013. An Analytical Latency Model for Networks-on-Chip. IEEE Trans. VLSI Syst. 21 1 (2013) 113\u2013123.","DOI":"10.1109\/TVLSI.2011.2178620"},{"key":"e_1_3_3_1_43_2","first-page":"1","volume-title":"Macsim: a CPU-GPU heterogeneous simulation framework user guide","author":"Kim Hyesoon","year":"2012","unstructured":"Hyesoon Kim, Jaekyu Lee, Nagesh\u00a0B Lakshminarayana, Jaewoong Sim, Jieun Lim, and Tri Pho. 2012. Macsim: a CPU-GPU heterogeneous simulation framework user guide. Technical Report. Georgia Inst. Technol.1\u201357 pages."},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/SIMUL.2009.17"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Y. Kim W. Yang and O. Mutlu. 2015. Ramulator: a fast and extensible DRAM simulator. IEEE Computer Architecture Letters 15 1 (2015) 45\u201349.","DOI":"10.1109\/LCA.2015.2414456"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Chao-Lin Lee Min-Yih Hsu Bing-Sung Lu Ming-Yu Hung and Jenq-Kuen Lee. 2020. Experiment and enabled flow for GPGPU-sim simulators with fixed-point instructions. J. Syst. Archit. 111 (2020) 101783.","DOI":"10.1016\/j.sysarc.2020.101783"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"D. Lee D. Hong and W. Choi. 2022. MQSim-E: an enterprise SSD simulator. IEEE Computer Architecture Letters 21 1 (2022) 13\u201316.","DOI":"10.1109\/LCA.2022.3144773"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2017.00030"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.2172\/1761619"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544253"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"crossref","unstructured":"Sheng Li Jung\u00a0Ho Ahn Richard\u00a0D. Strong Jay\u00a0B. Brockman Dean\u00a0M. Tullsen and Norman\u00a0P. Jouppi. 2009. McPAT: an integrated power area and timing modeling framework for multicore and manycore architectures. MICRO \u201909 (2009) 469\u2013480.","DOI":"10.1145\/1669112.1669172"},{"key":"e_1_3_3_1_52_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 Comput. Archit. Lett. 19 2 (2020) 106\u2013109.","DOI":"10.1109\/LCA.2020.2973991"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Xiaoyan Li Zizheng Dong and Shuaipeng Li. 2023. MUG5: modeling of universal chiplet interconnect express (UCIe) standard based on gem5. IEEE Int\u2019l Conf. ASIC (2023) 1\u20134.","DOI":"10.1109\/ASICON58565.2023.10396422"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Jian Liu Yuxin Chen and Hao Ding. 2025. CacheSim: a cache simulation framework for evaluating caching algorithms on resource-constrained edge devices. SoftwareX 29 (2025) 102018.","DOI":"10.1016\/j.softx.2024.102018"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"crossref","unstructured":"Q. Liu M. Zapater and D. Atienza. 2025. Gem5-acceSys: enabling system-level exploration of standard interconnects for novel accelerators. arXiv (2025).","DOI":"10.1109\/DAC63849.2025.11133394"},{"key":"e_1_3_3_1_56_2","unstructured":"Jason Lowe-Power Abdul\u00a0Mutaal Ahmad Ayaz Akram Mohammad Alian Rico Amslinger Matteo Andreozzi Adri\u00e0 Armejach Nils Asmussen Brad Beckmann Srikant Bharadwaj et\u00a0al. 2020. The gem5 simulator: version 20.0+. arXiv Preprint (2020)."},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2010.5416635"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"crossref","unstructured":"In\u00a0Jae Myung. 2003. Tutorial on maximum likelihood estimation. J. Mathematical Psychology 47 1 (2003) 90\u2013100.","DOI":"10.1016\/S0022-2496(02)00028-7"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"J. Power J. Hestness and M.\u00a0S. Orr. 2014. Gem5-gpu: a heterogeneous cpu-gpu simulator. IEEE Computer Architecture Letters 14 1 (2014) 34\u201336.","DOI":"10.1109\/LCA.2014.2299539"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.23919\/SpringSim.2019.8732862"},{"key":"e_1_3_3_1_61_2","volume-title":"OSCAR \u201924","author":"Ramadas Vishnu","year":"2024","unstructured":"Vishnu Ramadas, Matthew Poremba, Bradford Beckmann, and Matthew\u00a0D Sinclair. 2024. Simulation support for fast and accurate large-scale GPGPU & accelerator workloads. In OSCAR \u201924."},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00018"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/166955.166979"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"crossref","unstructured":"A.\u00a0F. Rodrigues K.\u00a0S. Hemmert and B.\u00a0W. Barrett. 2011. The structural simulation toolkit. ACM SIGMETRICS Performance Evaluation Review 38 4 (2011) 37\u201342.","DOI":"10.1145\/1964218.1964225"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00047"},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"crossref","unstructured":"M.\u00a0Monchiero J. B.\u00a0Brockman S.\u00a0Thoziyoor J. H.\u00a0Ahn and N.\u00a0P. Jouppi. 2008. A comprehensive memory modeling tool and its application to the design and analysis of future memory hierarchies. (2008) 51\u201362.","DOI":"10.1109\/ISCA.2008.16"},{"key":"e_1_3_3_1_67_2","unstructured":"Ananda Samajdar Yuhao Zhu Paul Whatmough Matthew Mattina and Tushar Krishna. 2018. Scale-sim: systolic CNN accelerator simulator. arXiv Preprint (2018)."},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"crossref","unstructured":"D. Sanchez and C. Kozyrakis. 2013. ZSim: fast and accurate microarchitectural simulation of thousand-core systems. ACM SIGARCH Comput. Archit. News 41 3 (2013) 475\u2013486.","DOI":"10.1145\/2508148.2485963"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3642921.3642956"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"crossref","unstructured":"Debendra\u00a0Das Sharma Gerald Pasdast Zhiguo Qian and Kemal Aygun. 2022. Universal Chiplet Interconnect Express (UCIe): an open industry standard for innovations with chiplets at package level. IEEE Trans. Compon. Packag. Manuf. Technol. 12 9 (2022) 1423\u20131431.","DOI":"10.1109\/TCPMT.2022.3207195"},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"crossref","unstructured":"Chen Sun Chia-Hsin\u00a0Owen Chen George Kurian Lan Wei Jason Miller Anant Agarwal Li-Shiuan Peh Stojanovic and Vladimir. 2012. DSENT - a tool connecting emerging photonics with electronics for opto-Electronic networks-on-Chip modeling. NOCS \u201912 (2012) 201\u2013210.","DOI":"10.1109\/NOCS.2012.31"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322230"},{"key":"e_1_3_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370865"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12331-3_3"},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844466"},{"key":"e_1_3_3_1_77_2","first-page":"541","volume-title":"NSDI \u201925","author":"Wang Xizheng","year":"2025","unstructured":"Xizheng Wang, Qingxu Li, Yichi Xu, Gang Lu, Dan Li, Li Chen, Heyang Zhou, Linkang Zheng, Sen Zhang, Yikai Zhu, et\u00a0al. 2025. SimAI: unifying Architecture Design and Performance Tuning for Large-Scale Large Language Model Training with Scalability and Precision. In NSDI \u201925. 541\u2013558."},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"crossref","unstructured":"X. Wang M. Xu A.\u00a0K. Singh Y. Jiang and M. Yang. 2025. On optimizing inter-and intra-chiplet interconnection topologies for robust multi-chiplet systems. IEEE Trans. Computer-Aided Design of Integrated Circuits and Systems (2025).","DOI":"10.1109\/TCAD.2025.3550432"},{"key":"e_1_3_3_1_79_2","doi-asserted-by":"crossref","unstructured":"Sheng Xu Xiaoming Chen Ying Wang Yinhe Han Xuehai Qian and Xiaowei Li. 2018. PIMSim: a flexible and detailed processing-in-memory simulator. IEEE Computer Architecture Letters 18 1 (2018) 6\u20139.","DOI":"10.1109\/LCA.2018.2885752"},{"key":"e_1_3_3_1_80_2","doi-asserted-by":"crossref","unstructured":"Yinglin Yang Yunzhengmao Wang Tengyue Yi Chixiao Chen and Qi Liu. 2024. A 6.4-Gbps 0.41-pJ\/b fully-digital die-to-die interconnect PHY for silicon interposer based 2.5D integration. Integration (2024) 102170.","DOI":"10.1016\/j.vlsi.2024.102170"},{"key":"e_1_3_3_1_81_2","doi-asserted-by":"crossref","unstructured":"Bingyi Ye Kai Sheng and Weixin Gai. 2023. A 2.29-pJ\/b 112-Gb\/s wireline transceiver with RX Four-Tap FFE for Medium-Reach applications in 28-nm CMOS. IEEE J. Solid-State Circuits 58 1 (2023) 19\u201329.","DOI":"10.1109\/JSSC.2022.3223052"},{"key":"e_1_3_3_1_82_2","unstructured":"H. Zhang. 2018. Distributed deep learning training with Horovod. arXiv (2018)."},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"crossref","unstructured":"Zhenhua Zhu Hanbo Sun Tongxin Xie Yu Zhu Guohao Dai Lixue Xia Dimin Niu Xiaoming Chen Xiaobo\u00a0Sharon Hu Yu Cao et\u00a0al. 2023. MNSIM 2.0: a behavior-level modeling tool for processing-in-memory architectures. IEEE Trans. Comput.-Aided Design Integr. Circuits Syst. 42 11 (2023) 4112\u20134125.","DOI":"10.1109\/TCAD.2023.3251696"},{"key":"e_1_3_3_1_84_2","doi-asserted-by":"crossref","unstructured":"L. Zuolo C. Zambelli and R. Micheloni. 2017. SSDexplorer: a virtual platform for SSD simulations. Solid-State-Drives (SSDs) Modeling: Simulation Tools & Strategies (2017) 41\u201365.","DOI":"10.1007\/978-3-319-51735-3_3"}],"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\/3725843.3756068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:43:24Z","timestamp":1769463804000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":83,"alternative-id":["10.1145\/3725843.3756068","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756068","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"}}]}}