[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81740-en":3,"doc-seo-81740-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},81740,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","HySpecPro Scalable Hypergraph Partitioning via Spectral Projection Optimization","Modern VLSI designs can involve tens of billions of interconnected components, making scalable hypergraph partitioning essential for parallel and hierarchical optimization. Multilevel partitioning is widely used, but its coarsening step can distort structural information, especially for hypergraphs with many high-degree hyperedges, increasing refinement overhead and reducing scalability. HySpecPro is introduced as a single-level hypergraph partitioner that performs end-to-end optimization in a spectral embedding space. It builds embeddings from a bipartite Laplacian and uses projection-based search with a fully GPU-accelerated implementation, achieving state-of-the-art cut quality while scaling linearly with total hyperedge degree.","HySpecPro: Scalable Hypergraph Partitioning via Spectral  \nProjection Optimization  \nRongjian Liang  \n[rliang@nvidia.com](rliang@nvidia.com)[ ](rliang@nvidia.com)NVIDIA Santa Clara, USA  \nZhuo Feng  \n[zfeng12@stevens.edu](zfeng12@stevens.edu)[ ](zfeng12@stevens.edu)Stevens Institute of Technology Hoboken, USA NVIDIA Santa Clara, USA  \nHaoxing Ren  \n[haoxingr@nvidia.com](haoxingr@nvidia.com)[ ](haoxingr@nvidia.com)NVIDIA Santa Clara, USA  \narXiv :2607 .00055v1 [ cs .AR] 30 Jun 2026  \nAbstract  \nModern VLSI designs comprise tens of billions of components, making scalable hypergraph partitioning critical for parallel and hierarchical optimization. Although multilevel partitioning remains the dominant paradigm, its coarsening stage can distort structural information—especially in hypergraphs with many high-degree hyperedges—leading to increased refinement overhead and limited scalability. Recent approaches incorporate spectral information to guide coarsening, but only in a heuristic manner, without directly optimizing the partitioning objectives. We introduce HySpecPro, a single-level hypergraph partitioner that performsend-to-end optimization in a spectral embedding space. HySpecPro constructs embeddings from a bipartite Laplacian and performs efficient projection-based search, supported by a fully GPU-accelerated implementation. Experiments show that HySpecPro delivers cut quality comparable to state-of-the-art multilevel methods while scaling linearly with the total hyperedge degree.  \nACM Reference Format:  \nRongjian Liang, Zhuo Feng, and Haoxing Ren. 2026. HySpecPro: Scalable Hypergraph Partitioning via Spectral Projection Optimization. In . ACM, New York, NY, USA, 7 pages. [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \n1 Introduction  \nModern VLSI designs comprise tens of billions of interconnected components, making full-chip optimization computationally prohibitive and often requiring weeks to months to complete. To improvescalability, circuit netlists are typically decomposed into smaller sub-blocks for parallel or hierarchical optimization. Hypergraphs provide a natural representation of netlists by capturing multi-way connectivity among circuit elements. A central task in this context is hypergraph partitioning [13], which divides vertices into balanced parts while minimizing objectives such as cut size. However, the problem is NP-hard due to its discrete and highly combinatorial nature [11], necessitating scalable and high-quality approximation algorithms for modern chip design.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nConference’17, Washington, DC, USA  \n© 2026 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-x-xxxx-xxxx-x/YYYY/MM [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \nFigure 1: Analysis of LU230 and its partitioning results.  \n1.1 Motivations  \nState-of-the-art (SOTA) hypergraph partitioners predominantly follow the multilevel paradigm [12, 14, 15, 19, 20]. KaHyPar [20], for example,(1) coarsens the hypergraph into successively smaller ones while attempting to preserve structure; (2) computes an initial partition on the coarsest hypergraph; and (3) uncoarsens and refines the solution at progressively finer levels. While highly effective, this workflow depends critically on coarsening quality. Whe","cbCaijbtRjtrDITh","https://ap.wps.com/l/cbCaijbtRjtrDITh","pdf",1770795,4,1,7,"English","en",105,"# Introduction\n## Motivations","[{\"question\":\"Why is scalable hypergraph partitioning important for modern VLSI designs?\",\"answer\":\"Modern VLSI netlists are extremely large, so full-chip optimization becomes computationally prohibitive. Partitioning enables parallel or hierarchical optimization by decomposing circuits into smaller sub-blocks.\"},{\"question\":\"What problem in multilevel partitioning limits scalability in certain hypergraphs?\",\"answer\":\"The coarsening stage can distort structural information, particularly for hypergraphs with many high-degree hyperedges. This forces the refinement stage to spend excessive time performing local search to recover solution quality.\"},{\"question\":\"How does HySpecPro differ from traditional multilevel hypergraph partitioners?\",\"answer\":\"HySpecPro uses a single-level approach that performs end-to-end optimization directly in a spectral embedding space. It constructs embeddings from a bipartite Laplacian and applies efficient projection-based search, implemented fully on the GPU.\"}]",1784175766,18,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"hyspecpro-scalable-hypergraph-partitioning-via-spectral-projection-optimization","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/hyspecpro-scalable-hypergraph-partitioning-via-spectral-projection-optimization/81740/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is scalable hypergraph partitioning important for modern VLSI designs?","Question",{"text":75,"@type":76},"Modern VLSI netlists are extremely large, so full-chip optimization becomes computationally prohibitive. Partitioning enables parallel or hierarchical optimization by decomposing circuits into smaller sub-blocks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What problem in multilevel partitioning limits scalability in certain hypergraphs?",{"text":80,"@type":76},"The coarsening stage can distort structural information, particularly for hypergraphs with many high-degree hyperedges. This forces the refinement stage to spend excessive time performing local search to recover solution quality.",{"name":82,"@type":73,"acceptedAnswer":83},"How does HySpecPro differ from traditional multilevel hypergraph partitioners?",{"text":84,"@type":76},"HySpecPro uses a single-level approach that performs end-to-end optimization directly in a spectral embedding space. It constructs embeddings from a bipartite Laplacian and applies efficient projection-based search, implemented fully on the GPU.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]