{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T15:10:09Z","timestamp":1751037009217,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3716368.3735169","type":"proceedings-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T13:58:23Z","timestamp":1751032703000},"page":"746-751","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimal Device Sequencing and Kernel Assignment for Multiple Heterogeneous Machine Learning Accelerators"],"prefix":"10.1145","author":[{"given":"Tejas","family":"Bachhav","sequence":"first","affiliation":[{"name":"SUNY Binghamton, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amol","family":"Kerkar","sequence":"additional","affiliation":[{"name":"SUNY Binghmaton, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rahul","family":"Rana","sequence":"additional","affiliation":[{"name":"SUNY Binghamton, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Madden","sequence":"additional","affiliation":[{"name":"SUNY Binghamton, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,29]]},"reference":[{"key":"e_1_3_3_1_2_2","first-page":"483","volume-title":"Proc. AFIPS Conference","author":"Amdahl G.\u00a0M.","year":"1967","unstructured":"G.\u00a0M. Amdahl. 1967. Validity of the single-processor approach to achieveing large scale computing capabilities. In Proc. AFIPS Conference. 483\u2013485."},{"key":"e_1_3_3_1_3_2","unstructured":"NVIDIA\u00a0Developer Forum. 2024. Challenges in AI Workload Utilization on NVIDIA GPUs. Available at: https:\/\/forums.developer.nvidia.com\/t\/how-to-get-nsight-compute-timeline-of-tensor-cores-and-cuda-cores\/285233."},{"key":"e_1_3_3_1_4_2","volume-title":"Proc. Supercomputing","author":"Fricker J.\u00a0P.","year":"2019","unstructured":"J.\u00a0P. Fricker and A. Hock. 2019. CS-1 Wafer-Scale Deep Learning System. In Proc. Supercomputing."},{"key":"e_1_3_3_1_5_2","unstructured":"Ravi Gupta Liang Chen and Ping Zhao. 2023. Efficient Hardware Architectures for Accelerating Deep Neural Networks. Comput. Surveys 56 2 (2023) 1\u201329."},{"key":"e_1_3_3_1_6_2","unstructured":"K. He X. Zhang S. Ren and J. Sun. 2015. Deep Residual Learning for Image Recognition. (2015). https:\/\/arxiv.org\/pdf\/1512.03385.pdf (online)."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3372780.3380846"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415688"},{"key":"e_1_3_3_1_9_2","unstructured":"Norman\u00a0P. Jouppi Cliff Young Nishant Patil David Patterson and Gaurav Agrawal. 2023. F1: Striking the Balance Between Energy Efficiency and Flexibility in AI Hardware. IEEE Transactions on Computer Architecture 38 4 (2023) 785\u2013801."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"B. Landman and R. Russo. 1971. On a pin versus block relationship for partitioning of logic graphs. IEEE Trans. on Computers C-20 (Dec. 1971) 1469\u20131479.","DOI":"10.1109\/T-C.1971.223159"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Gary Lauterbach. 2021. The Path to Successful Wafer-Scale Integration: The Cerebras Story. IEEE Micro 41 6 (2021) 52\u201357. 10.1109\/MM.2021.3112025","DOI":"10.1109\/MM.2021.3112025"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394885.3431563"},{"key":"e_1_3_3_1_13_2","unstructured":"Gordon\u00a0M Moore. 1965. Cramming more components onto integrated circuits With unit cost. Electronics 38 8 (1965) 114."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"H. Murata K. Fujiyoshi S. Nakatake and Y. Kajitani. 1996. VLSI Module Placement Based on Rectangle-Packing by the Sequence Pair. IEEE Trans. on Computer-Aided Design of Integrated Circuits and Systems 15 12 (1996) 1518\u20131524.","DOI":"10.1109\/43.552084"},{"key":"e_1_3_3_1_15_2","unstructured":"Y\u00a0Combinator News. 2024. Google TPU v5p vs NVIDIA A100: A Power Efficiency Comparison. Available at: https:\/\/news.ycombinator.com\/item?id=39148544."},{"key":"e_1_3_3_1_16_2","unstructured":"NVIDIA. 2025. PROJECT DIGITS. (2025). https:\/\/www.nvidia.com\/en-us\/project-digits\/ (online)."},{"key":"e_1_3_3_1_17_2","first-page":"261","volume-title":"Proc. Design Automation Conference","author":"Otten R.\u00a0H. J.\u00a0M.","year":"1982","unstructured":"R.\u00a0H. J.\u00a0M. Otten. 1982. Automatic Floorplan Design. In Proc. Design Automation Conference. 261\u2013267."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3505170.3506730"},{"key":"e_1_3_3_1_19_2","unstructured":"D. Silver T. Hubert J. Schrittwieser I. Antonoglou M. Lai A. Guez M. Lanctot L. Sifre D. Kumaran T. Graepel T. Lillicrap K. Simonyan and D. Hassabis. 2017. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm. (2017). https:\/\/arxiv.org\/pdf\/1712.01815.pdf (online)."},{"key":"e_1_3_3_1_20_2","unstructured":"Cerebras Systems. 2024. Cerebras CS-2: Wafer-Scale AI Computing. Available at: https:\/\/www.cerebras.net\/products\/cs2."},{"key":"e_1_3_3_1_21_2","unstructured":"Ming Yan Xie Li Wei Zhang and Yang Wu. 2024. HyGCN: A GCN Accelerator with Hybrid Architecture for AI Workloads. IEEE Journal on Emerging and Selected Topics in Circuits and Systems 15 1 (2024) 112\u2013125."}],"event":{"name":"GLSVLSI '25: Great Lakes Symposium on VLSI 2025","sponsor":["SIGDA ACM Special Interest Group on Design Automation"],"location":"New Orleans LA USA","acronym":"GLSVLSI '25"},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2025"],"original-title":[],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T14:39:11Z","timestamp":1751035151000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716368.3735169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,29]]},"references-count":20,"alternative-id":["10.1145\/3716368.3735169","10.1145\/3716368"],"URL":"https:\/\/doi.org\/10.1145\/3716368.3735169","relation":{},"subject":[],"published":{"date-parts":[[2025,6,29]]},"assertion":[{"value":"2025-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}