{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/stream-k-work-centric-parallel-decomposition","title":"Stream-K: Work-centric Parallel Decomposition for Dense Matrix-Matrix Multiplication on the GPU","arxiv_id":"2301.03598","date":"2023-01-09","proceeding":null,"authors":["Muhammad Osama","Duane Merrill","Cris Cecka","Michael Garland","John D. Owens"],"abstract":"We introduce Stream-K, a work-centric parallelization of matrix multiplication (GEMM) and related computations in dense linear algebra. Whereas contemporary decompositions are primarily tile-based, our method operates by partitioning an even share of the aggregate inner loop iterations among physical processing elements. This provides a near-perfect utilization of computing resources, regardless of how efficiently the output tiling for any given problem quantizes across the underlying processing elements. On GPU processors, our Stream-K parallelization of GEMM produces a peak speedup of up to 14$\\times$ and 6.7$\\times$, and an average performance response that is both higher and more consistent across 32,824 GEMM problem geometries than state-of-the-art math libraries such as CUTLASS and cuBLAS. Furthermore, we achieve this performance from a single tile size configuration per floating-point precision, whereas today's math libraries employ complex kernel-selection heuristics to select from a large ensemble of kernel variants.","url_abs":"https://arxiv.org/abs/2301.03598v1","url_pdf":"https://arxiv.org/pdf/2301.03598v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"stream-k-work-centric-parallel-decomposition","repo_url":"https://github.com/NVIDIA/cutlass","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"stream-k-work-centric-parallel-decomposition","repo_url":"https://github.com/flashinfer-ai/flashinfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"stream-k-work-centric-parallel-decomposition","repo_url":"https://github.com/usyd-fsalab/fp6_llm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.03598","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}