{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:41:21Z","timestamp":1773247281745,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":91,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T00:00:00Z","timestamp":1737331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2235276"],"award-info":[{"award-number":["2235276"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2349144"],"award-info":[{"award-number":["2349144"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2349143"],"award-info":[{"award-number":["2349143"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2349582"],"award-info":[{"award-number":["2349582"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2349141"],"award-info":[{"award-number":["2349141"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,1,20]]},"DOI":"10.1145\/3658617.3697551","type":"proceedings-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T14:43:12Z","timestamp":1741099392000},"page":"1031-1040","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["HyperG: Multilevel GPU-Accelerated k-way Hypergraph Partitioner"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2156-2765","authenticated-orcid":false,"given":"Wan Luan","family":"Lee","sequence":"first","affiliation":[{"name":"The University of Wisconsin at Madison, Madison, Wisconsin, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3075-7437","authenticated-orcid":false,"given":"Dian-Lun","family":"Lin","sequence":"additional","affiliation":[{"name":"The University of Wisconsin at Madison, Madison, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0406-885X","authenticated-orcid":false,"given":"Cheng-Hsiang","family":"Chiu","sequence":"additional","affiliation":[{"name":"The University of Wisconsin at Madison, Madison, Wisconsin, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4431-7619","authenticated-orcid":false,"given":"Ulf","family":"Schlichtmann","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9768-3378","authenticated-orcid":false,"given":"Tsung-Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Wisconsin at Madison, Madison, Wisconsin, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"2017 Proceedings of the Ninteenth Workshop on Algorithm Engineering and Experiments (ALENEX). SIAM, 28--42","author":"Akhremtsev Yaroslav","year":"2017","unstructured":"Yaroslav Akhremtsev, Tobias Heuer, Peter Sanders, and Sebastian Schlag. 2017. Engineering a direct k-way hypergraph partitioning algorithm. In 2017 Proceedings of the Ninteenth Workshop on Algorithm Engineering and Experiments (ALENEX). SIAM, 28--42."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/274535.274546"},{"key":"e_1_3_2_1_3_1","volume-title":"An Open-Source Constraints-Driven General Partitioning Multi-Tool for VLSI Physical Design","unstructured":"Author(s). 2023. An Open-Source Constraints-Driven General Partitioning Multi-Tool for VLSI Physical Design. In IEEE\/ACM ICCAD."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.780863"},{"key":"e_1_3_2_1_5_1","unstructured":"\u00dcmit V \u00c7ataly\u00fcrek and Cevdet Aykanat. 2011. PaToH (Partitioning Tool for Hypergraphs)."},{"key":"e_1_3_2_1_6_1","volume-title":"Article 253 (mar","author":"\u00c7ataly\u00fcrek \u00dcmit","year":"2023","unstructured":"\u00dcmit \u00c7ataly\u00fcrek, Karen Devine, Marcelo Faraj, Lars Gottesb\u00fcren, Tobias Heuer, Henning Meyerhenke, Peter Sanders, Sebastian Schlag, Christian Schulz, Daniel Seemaier, and Dorothea Wagner. 2023. More Recent Advances in (Hyper)Graph Partitioning. ACM Comput. Surv. 55, 12, Article 253 (mar 2023), 38 pages."},{"key":"e_1_3_2_1_7_1","volume-title":"Incremental Critical Path Generation for Dynamic Graphs. In IEEE Computer Society Annual Symposium on VLSI (ISVLSI).","author":"Chang Che","year":"2024","unstructured":"Che Chang, Cheng-Hsiang Chiu, Boyang Zhang, and Tsung-Wei Huang. 2024. Incremental Critical Path Generation for Dynamic Graphs. In IEEE Computer Society Annual Symposium on VLSI (ISVLSI)."},{"key":"e_1_3_2_1_8_1","volume-title":"Ink: Efficient Incremental k-Critical Path Generation","author":"Chang Che","year":"2024","unstructured":"Che Chang, Tsung-Wei Huang, Dian-Lun Lin, Guannan Guo, and Shiju Lin. 2024. Ink: Efficient Incremental k-Critical Path Generation. In ACM\/IEEE DAC."},{"key":"e_1_3_2_1_9_1","volume-title":"PathGen: An Efficient Parallel Critical Path Generation Algorithm. In IEEE\/ACM Asia and South Pacific Design Automation Conference (ASP-DAC).","author":"Chang Che","year":"2025","unstructured":"Che Chang, Boyang Zhang, Cheng-Hsiang Chiu, Dian-Lun Lin, Yi-Hua Chung, Wan-Luan Lee, Zizheng Guo, Yibo Lin, and Tsung-Wei Huang. 2025. PathGen: An Efficient Parallel Critical Path Generation Algorithm. In IEEE\/ACM Asia and South Pacific Design Automation Conference (ASP-DAC)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363426"},{"key":"e_1_3_2_1_11_1","volume-title":"GSAP: A GPU-Accelerated Stochastic Graph Partitioner. In ACM ICPP. 565--575.","author":"Chang Chih-Chun","year":"2024","unstructured":"Chih-Chun Chang, Boyang Zhang, and Tsung-Wei Huang. 2024. GSAP: A GPU-Accelerated Stochastic Graph Partitioner. In ACM ICPP. 565--575."},{"key":"e_1_3_2_1_12_1","volume-title":"2015 IEEE High Performance Extreme Computing Conference (HPEC). IEEE, 1--7.","author":"Cheng Lin","year":"2015","unstructured":"Lin Cheng, Hyunsu Cho, and Peter Yoon. 2015. An accelerated procedure for hypergraph coarsening on the GPU. In 2015 IEEE High Performance Extreme Computing Conference (HPEC). IEEE, 1--7."},{"key":"e_1_3_2_1_13_1","volume-title":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI).","author":"Chiu Cheng-Hsiang","unstructured":"Cheng-Hsiang Chiu and Tsung-Wei Huang. [n. d.]. In IEEE Computer Society Annual Symposium on VLSI (ISVLSI)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3533714"},{"key":"e_1_3_2_1_15_1","volume-title":"Efficient Timing Propagation with Simultaneous Structural and Pipeline Parallelisms. In ACM\/IEEE Design Automation Conference (DAC).","author":"Chiu Cheng-Hsiang","year":"2022","unstructured":"Cheng-Hsiang Chiu and Tsung-Wei Huang. 2022. Efficient Timing Propagation with Simultaneous Structural and Pipeline Parallelisms. In ACM\/IEEE Design Automation Conference (DAC)."},{"key":"e_1_3_2_1_16_1","volume-title":"An Experimental Study of SYCL Task Graph Parallelism for Large-Scale Machine Learning Workloads. In International Workshop of Asynchronous Many-Task systems for Exascale (AMTE).","author":"Chiu Cheng-Hsiang","year":"2021","unstructured":"Cheng-Hsiang Chiu, Dian-Lun Lin, and Tsung-Wei Huang. 2021. An Experimental Study of SYCL Task Graph Parallelism for Large-Scale Machine Learning Workloads. In International Workshop of Asynchronous Many-Task systems for Exascale (AMTE)."},{"key":"e_1_3_2_1_17_1","volume-title":"Programming Dynamic Task Parallelism for Heterogeneous EDA Algorithms. In IEEE\/ACM International Conference on Computer-aided Design (ICCAD).","author":"Chiu Cheng-Hsiang","year":"2023","unstructured":"Cheng-Hsiang Chiu, Dian-Lun Lin, and Tsung-Wei Huang. 2023. Programming Dynamic Task Parallelism for Heterogeneous EDA Algorithms. In IEEE\/ACM International Conference on Computer-aided Design (ICCAD)."},{"key":"e_1_3_2_1_18_1","volume-title":"Reinforcement Learning-generated Topological Order for Dynamic Task Graph Scheduling. In IEEE High-performance and Extreme Computing Conference (HPEC).","author":"Chiu Cheng-Hsiang","year":"2024","unstructured":"Cheng-Hsiang Chiu, Chedi Morchdi, Yi Zhou, Boyang Zhang, Che Chang, and Tsung-Wei Huang. 2024. Reinforcement Learning-generated Topological Order for Dynamic Task Graph Scheduling. In IEEE High-performance and Extreme Computing Conference (HPEC)."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium. IEEE, 10--pp.","author":"Devine Karen D","year":"2006","unstructured":"Karen D Devine, Erik G Boman, Robert T Heaphy, Rob H Bisseling, and Umit V Catalyurek. 2006. Parallel hypergraph partitioning for scientific computing. In Proceedings 20th IEEE International Parallel & Distributed Processing Symposium. IEEE, 10--pp."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW59300.2023.00150"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"e_1_3_2_1_22_1","volume-title":"Mattheyses","author":"Fiduccia Charles M.","year":"1982","unstructured":"Charles M. Fiduccia and Robert M. Mattheyses. 1982. A linear-time heuristic for improving network partitions. In ACM\/IEEE DAC. 175--181."},{"key":"e_1_3_2_1_23_1","volume-title":"High performance multilevel graph partitioning on GPU","author":"Goodarzi Bahareh","unstructured":"Bahareh Goodarzi, Farzad Khorasani, Vivek Sarkar, and Dhrubajyoti Goswami. 2019. High performance multilevel graph partitioning on GPU. In HPCS. IEEE."},{"key":"e_1_3_2_1_24_1","volume-title":"Scalable Shared-Memory Hypergraph Partitioning. In 2021 Proceedings of the Workshop on Algorithm Engineering and Experiments (ALENEX). SIAM, 16--30","author":"Gottesb\u00fcren Lars","year":"2021","unstructured":"Lars Gottesb\u00fcren, Tobias Heuer, Peter Sanders, and Sebastian Schlag. 2021. Scalable Shared-Memory Hypergraph Partitioning. In 2021 Proceedings of the Workshop on Algorithm Engineering and Experiments (ALENEX). SIAM, 16--30."},{"key":"e_1_3_2_1_25_1","volume-title":"An Efficient Critical Path Generation Algorithm Considering Extensive Path Constraints. In ACM\/IEEE Design Automation Conference (DAC).","author":"Guo Guannan","year":"2020","unstructured":"Guannan Guo, Tsung-Wei Huang, Chun-Xun Lin, and Martin Wong. 2020. An Efficient Critical Path Generation Algorithm Considering Extensive Path Constraints. In ACM\/IEEE Design Automation Conference (DAC)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3272274"},{"key":"e_1_3_2_1_27_1","volume-title":"GPU-accelerated Critical Path Generation with Path Constraints. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD).","author":"Guo Guannan","year":"2021","unstructured":"Guannan Guo, Tsung-Wei Huang, Yibo Lin, and Martin Wong. 2021. GPU-accelerated Critical Path Generation with Path Constraints. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)."},{"key":"e_1_3_2_1_28_1","volume-title":"GPU-accelerated Path-based Timing Analysis. In IEEE\/ACM Design Automation Conference (DAC).","author":"Guo Guannan","year":"2021","unstructured":"Guannan Guo, Tsung-Wei Huang, Yibo Lin, and Martin Wong. 2021. GPU-accelerated Path-based Timing Analysis. In IEEE\/ACM Design Automation Conference (DAC)."},{"key":"e_1_3_2_1_29_1","volume-title":"Automation and Test in Europe Conference (DATE).","author":"Guo Guannan","unstructured":"Guannan Guo, Tsung-Wei Huang, and Martin D. F. Wong. 2023. Fast STA Graph Partitioning Framework for Multi-GPU Acceleration. In IEEE\/ACM Design, Automation and Test in Europe Conference (DATE)."},{"key":"e_1_3_2_1_30_1","volume-title":"IEEE\/ACM International Conference on Computer-aided Design (ICCAD).","author":"Guo Zizheng","year":"2020","unstructured":"Zizheng Guo, Tsung-Wei Huang, and Yibo Lin. 2020. A Provably Good and Practically Efficient Algorithm for Common Path Pessimism Removal in Large Designs. In IEEE\/ACM International Conference on Computer-aided Design (ICCAD)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586085"},{"key":"e_1_3_2_1_32_1","volume-title":"HeteroCPPR: Accelerating Common Path Pessimism Removal with Heterogeneous CPU-GPU Parallelism. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD).","author":"Guo Zizheng","year":"2021","unstructured":"Zizheng Guo, Tsung-Wei Huang, and Yibo Lin. 2021. HeteroCPPR: Accelerating Common Path Pessimism Removal with Heterogeneous CPU-GPU Parallelism. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3286261"},{"key":"e_1_3_2_1_34_1","volume-title":"Automation and Test in Europe Conference (DATE).","author":"Guo Zizheng","year":"2024","unstructured":"Zizheng Guo, Tsung-Wei Huang, Jin Zhou, Cheng Zhuo, Yibo Lin, Runsheng Wang, and Ru Huang. 2024. Heterogeneous Static Timing Analysis with Advanced Delay Calculator. In IEEE\/ACM Design, Automation and Test in Europe Conference (DATE)."},{"key":"e_1_3_2_1_35_1","volume-title":"HeteroExcept: Heterogeneous Engine for General Timing Path Exception Analysis. In IEEE\/ACM International Conference on Computer-aided Design (ICCAD).","author":"Guo Zizheng","year":"2024","unstructured":"Zizheng Guo, Zuodong Zhang, Wuxi Li, Tsung-Wei Huang, Xizhe Shi, Yufan Du, Yibo Lin, Runsheng Wang, and Ru Huang. 2024. HeteroExcept: Heterogeneous Engine for General Timing Path Exception Analysis. In IEEE\/ACM International Conference on Computer-aided Design (ICCAD)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415750"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ProTools54808.2021.00006"},{"key":"e_1_3_2_1_38_1","volume-title":"Enhancing the Performance Portability of Heterogeneous Circuit Analysis Programs. In IEEE High-Performance Extreme Computing Conference (HPEC).","author":"Huang Tsung-Wei","year":"2022","unstructured":"Tsung-Wei Huang. 2022. Enhancing the Performance Portability of Heterogeneous Circuit Analysis Programs. In IEEE High-Performance Extreme Computing Conference (HPEC)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00080"},{"key":"e_1_3_2_1_40_1","volume-title":"Wong","author":"Huang Tsung-Wei","year":"2021","unstructured":"Tsung-Wei Huang, Guannan Guo, Chun-Xun Lin, and Martin D. F. Wong. 2021. OpenTimer v2: A New Parallel Incremental Timing Analysis Engine. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Task-parallel Programming with Constrained Parallelism. In IEEE High-Performance Extreme Computing Conference (HPEC).","author":"Huang Tsung-Wei","year":"2022","unstructured":"Tsung-Wei Huang and Leslie Hwang. 2022. Task-parallel Programming with Constrained Parallelism. In IEEE High-Performance Extreme Computing Conference (HPEC)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3322470"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3243654"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00105"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3323477"},{"key":"e_1_3_2_1_46_1","volume-title":"DtCraft: A Distributed Execution Engine for Compute-intensive Applications. In IEEE\/ACM International Conference on Computer-aided Design (ICCAD).","author":"Huang Tsung-Wei","year":"2017","unstructured":"Tsung-Wei Huang, Chun-Xun Lin, and Martin Wong. 2017. DtCraft: A Distributed Execution Engine for Compute-intensive Applications. In IEEE\/ACM International Conference on Computer-aided Design (ICCAD)."},{"key":"e_1_3_2_1_47_1","volume-title":"DtCraft: A High-performance Distributed Execution Engine at Scale","author":"Huang Tsung-Wei","year":"2019","unstructured":"Tsung-Wei Huang, Chun-Xun Lin, and Martin Wong. 2019. DtCraft: A High-performance Distributed Execution Engine at Scale. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) (2019)."},{"key":"e_1_3_2_1_48_1","volume-title":"OpenTimer v2: A Parallel Incremental Timing Analysis Engine","author":"Huang Tsung-Wei","year":"2021","unstructured":"Tsung-Wei Huang, Chun-Xun Lin, and Martin Wong. 2021. OpenTimer v2: A Parallel Incremental Timing Analysis Engine. IEEE Design and Test (DAT) (2021)."},{"key":"e_1_3_2_1_49_1","volume-title":"Taskflow: A Lightweight Parallel and Heterogeneous Task Graph Computing System","author":"Huang Tsung-Wei","year":"2022","unstructured":"Tsung-Wei Huang, Dian-Lun Lin, Chun-Xun Lin, and Yibo Lin. 2022. Taskflow: A Lightweight Parallel and Heterogeneous Task Graph Computing System. IEEE Transactions on Parallel and Distributed Systems (TPDS) (2022)."},{"key":"e_1_3_2_1_50_1","volume-title":"Taskflow: A General-purpose Parallel and Heterogeneous Task Programming System","author":"Huang Tsung-Wei","year":"2022","unstructured":"Tsung-Wei Huang, Dian-Lun Lin, Yibo Lin, and Chun-Xun Lin. 2022. Taskflow: A General-purpose Parallel and Heterogeneous Task Programming System. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) (2022)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00099"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2024724.2024891"},{"key":"e_1_3_2_1_53_1","volume-title":"OpenTimer: A High-Performance Timing Analysis Tool. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD).","author":"Huang Tsung-Wei","year":"2015","unstructured":"Tsung-Wei Huang and Martin Wong. 2015. OpenTimer: A High-Performance Timing Analysis Tool. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)."},{"key":"e_1_3_2_1_54_1","volume-title":"An Ultra-Fast Path-Based Timing Analysis Algorithm for CPPR","author":"Huang Tsung-Wei","year":"2016","unstructured":"Tsung-Wei Huang and Martin Wong. 2016. UI-Timer 1.0: An Ultra-Fast Path-Based Timing Analysis Algorithm for CPPR. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) (2016)."},{"key":"e_1_3_2_1_55_1","volume-title":"IEEE\/ACM Design Automation Conference (DAC).","author":"Huang Tsung-Wei","unstructured":"Tsung-Wei Huang, Martin Wong, D. Sinha, K. Kalafala, and N. Venkateswaran. 2016. A Distributed Timing Analysis Framework for Large Designs. In IEEE\/ACM Design Automation Conference (DAC)."},{"key":"e_1_3_2_1_56_1","volume-title":"Fast Path-Based Timing Analysis for CPPR","author":"Huang Tsung-Wei","unstructured":"Tsung-Wei Huang, P.-C. Wu, and Martin Wong. 2014. Fast Path-Based Timing Analysis for CPPR. In IEEE\/ACM ICCAD."},{"key":"e_1_3_2_1_57_1","volume-title":"UI-Route: An Ultra-Fast Incremental Maze Routing Algorithm. In ACM System Level Interconnect Prediction Workshop (SLIP). 1--8.","author":"Huang Tsung-Wei","unstructured":"Tsung-Wei Huang, Pei-Ci Wu, and Martin D. F. Wong. 2014. UI-Route: An Ultra-Fast Incremental Maze Routing Algorithm. In ACM System Level Interconnect Prediction Workshop (SLIP). 1--8."},{"key":"e_1_3_2_1_58_1","volume-title":"Wong","author":"Huang Tsung-Wei","year":"2014","unstructured":"Tsung-Wei Huang, Pei-Ci Wu, and Martin D. F. Wong. 2014. UI-Timer: An ultra-fast clock network pessimism removal algorithm. In IEEE\/ACM ICCAD."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626184.3635278"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(93)90115-P"},{"key":"e_1_3_2_1_61_1","volume-title":"GLARE: Accelerating Sparse DNN Inference Kernels with Global Memory Access Reduction. In IEEE High-performance and Extreme Computing Conference (HPEC).","author":"Jiang Shiu","year":"2023","unstructured":"Shiu Jiang, Tsung-Wei Huang, and Tsung-Yi Ho. 2023. GLARE: Accelerating Sparse DNN Inference Kernels with Global Memory Access Reduction. In IEEE High-performance and Extreme Computing Conference (HPEC)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605625"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Jiang Shui and Fu Rongliang and Burgholzer Lukas and Wille Robert and Ho Tsung-Yi and Huang Tsung-Wei. 2024. FlatDD: A High-Performance Quantum Circuit Simulator using Decision Diagram and Flat Array. In ACM ICPP. 388--399.","DOI":"10.1145\/3673038.3673073"},{"key":"e_1_3_2_1_64_1","volume-title":"Multilevel hypergraph partitioning: Application in VLSI domain","author":"Karypis George","unstructured":"George Karypis, Rajat Aggarwal, Vipin Kumar, and Shashi Shekhar. 1997. Multilevel hypergraph partitioning: Application in VLSI domain. In IEEE\/ACM DAC. 526--529."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317744"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394885.3431578"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062274"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658617.3697551"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656238"},{"key":"e_1_3_2_1_70_1","volume-title":"Combinatorial algorithms for integrated circuit layout","author":"Lengauer Thomas","unstructured":"Thomas Lengauer. 2012. Combinatorial algorithms for integrated circuit layout. Springer Science & Business Media."},{"key":"e_1_3_2_1_71_1","volume-title":"Proceedings of the 2024 International Symposium on Physical Design. 3--11","author":"Liang Rongjian","year":"2024","unstructured":"Rongjian Liang, Anthony Agnesina, and Haoxing Ren. 2024. MedPart: A Multi-Level Evolutionary Differentiable Hypergraph Partitioner. In Proceedings of the 2024 International Symposium on Physical Design. 3--11."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350537"},{"key":"e_1_3_2_1_73_1","volume-title":"An Efficient and Composable Parallel Task Programming Library. In IEEE High-performance and Extreme Computing Conference (HPEC).","author":"Lin Chun-Xun","year":"2019","unstructured":"Chun-Xun Lin, Tsung-Wei Huang, Guannan Guo, and Martin Wong. 2019. An Efficient and Composable Parallel Task Programming Library. In IEEE High-performance and Extreme Computing Conference (HPEC)."},{"key":"e_1_3_2_1_74_1","volume-title":"An Efficient Work-Stealing Scheduler for Task Dependency Graph. In IEEE International Conference on Parallel and Distributed Systems (ICPADS).","author":"Lin Chun-Xun","year":"2020","unstructured":"Chun-Xun Lin, Tsung-Wei Huang, and Martin Wong. 2020. An Efficient Work-Stealing Scheduler for Task Dependency Graph. In IEEE International Conference on Parallel and Distributed Systems (ICPADS)."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3194554.3194560"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286218"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-85665-6_27"},{"key":"e_1_3_2_1_78_1","volume-title":"Accelerating Large Sparse Neural Network Inference using GPU Task Graph Parallelism","author":"Lin Dian-Lun","year":"2022","unstructured":"Dian-Lun Lin and Tsung-Wei Huang. 2022. Accelerating Large Sparse Neural Network Inference using GPU Task Graph Parallelism. IEEE Transactions on Parallel and Distributed Systems (TPDS) (2022)."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-69583-4_11"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545091"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247942"},{"key":"e_1_3_2_1_82_1","volume-title":"G-PASTA: GPU Accelerated Partitioning Algorithm for Static Timing Analysis","author":"Lin Shiju","unstructured":"Shiju Lin, Guannan Guo, Tsung-Wei Huang, Weihua Sheng, Evangeline Young, and Martin Wong. 2024. G-PASTA: GPU Accelerated Partitioning Algorithm for Static Timing Analysis. In ACM\/IEEE DAC."},{"key":"e_1_3_2_1_83_1","volume-title":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. 161--174","author":"Maleki Sepideh","year":"2021","unstructured":"Sepideh Maleki, Udit Agarwal, Martin Burtscher, and Keshav Pingali. 2021. Bipart: a parallel and deterministic hypergraph partitioner. In Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. 161--174."},{"key":"e_1_3_2_1_84_1","volume-title":"IEEE\/ACM Asia and South Pacific Design Automation Conference (ASP-DAC).","author":"Morchdi Chedi","year":"2024","unstructured":"Chedi Morchdi, Cheng-Hsiang Chiu, Yi Zhou, and Tsung-Wei Huang. 2024. A Resource-efficient Task Scheduling System using Reinforcement Learning. In IEEE\/ACM Asia and South Pacific Design Automation Conference (ASP-DAC)."},{"key":"e_1_3_2_1_85_1","volume-title":"Taskflow-San: Sanitizing Erroneous Control Flow in Taskflow Programs. In IEEE Workshop on Extreme Scale Programming Models and Middleware (ESPM2).","author":"Mower McKay","year":"2021","unstructured":"McKay Mower, Luke Majors, and Tsung-Wei Huang. 2021. Taskflow-San: Sanitizing Erroneous Control Flow in Taskflow Programs. In IEEE Workshop on Extreme Scale Programming Models and Middleware (ESPM2)."},{"key":"e_1_3_2_1_86_1","volume-title":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI).","author":"Tong Jie","year":"2024","unstructured":"Jie Tong, Liangliang Chang, Umit Yusuf Ogras, and Tsung-Wei Huang. 2024. Batch-Sim: Parallel RTL Simulation using Inter-cycle Batching and Task Graph Parallelism. In IEEE Computer Society Annual Symposium on VLSI (ISVLSI)."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2014.2331340"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/CANDAR.2015.78"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622872"},{"key":"e_1_3_2_1_90_1","volume-title":"Chih-Chun Chang, Donghao Fang, and Tsung-Wei Huang.","author":"Zhang Boyang","year":"2024","unstructured":"Boyang Zhang, Dian-Lun Lin, Che Chang, Cheng-Hsiang Chiu, Bojue Wang, Wan Luan Lee, Chih-Chun Chang, Donghao Fang, and Tsung-Wei Huang. 2024. G-PASTA: GPU Accelerated Partitioning Algorithm for Static Timing Analysis. In ACM\/IEEE DAC."},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC52403.2022.9712566"}],"event":{"name":"ASPDAC '25: 30th Asia and South Pacific Design Automation Conference","location":"Tokyo Japan","acronym":"ASPDAC '25","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEICE","IPSJ","IEEE CAS","IEEE CEDA"]},"container-title":["Proceedings of the 30th Asia and South Pacific Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697551","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658617.3697551","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658617.3697551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:18Z","timestamp":1750290258000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697551"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,20]]},"references-count":91,"alternative-id":["10.1145\/3658617.3697551","10.1145\/3658617"],"URL":"https:\/\/doi.org\/10.1145\/3658617.3697551","relation":{},"subject":[],"published":{"date-parts":[[2025,1,20]]},"assertion":[{"value":"2025-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}