{"slug": "a-thread-register-decoupled-gpu-execution-model-for-efficient-tensor-computation", "title": "A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation", "summary": "Researchers proposed FIBER, a thread-register decoupled GPU execution model that extends the SIMT architecture to improve tensor computation efficiency, achieving a 2.25x end-to-end speedup on Ampere, 1.8x on Hopper, and 2.09x on Blackwell in mixed-precision LLM serving, with kernel-level gains up to 2.49x. The architecture decouples execution from private register ownership, enabling dynamic parallelism scaling and fine-grained register-level dataflow scheduling.", "body_md": "# Computer Science > Hardware Architecture\n\n[Submitted on 20 Aug 2026]\n\n# Title:A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation\n\n[View PDF](/pdf/2608.19628)\n\n[HTML (experimental)](https://arxiv.org/html/2608.19628v1)\n\nAbstract:Modern GPUs increasingly integrate Tensor Cores into the execution pipeline. Although aggregate tensor throughput continues to grow, aided by an operand supply that has evolved from register-based in Ampere to redundancy-free, memory-based in Hopper and Blackwell, efficiently orchestrating the complete tensor compute pipeline for the modern AI workloads remains challenging. We identify the fundamental bottlenecks as fixed parallelism and coarse-grained scheduling, both of which are exposed by modern AI workloads that interleave diverse non-GEMM operations with GEMM. To orchestrate tensor computation efficiently, we propose FIBER, a new architecture that extends the GPU SIMT (single instruction, multiple thread) model. Its basic execution instance, the \\emph{fiber}, is decoupled from private register ownership, carrying only minimal control state while accessing an SM's registers through a shared view. This enables dynamic parallelism scaling, fine-grained register-level dataflow scheduling, and offers a redundancy-free alternative for matrix operand supply. We extend the ISA, microarchitecture, and compiler to realize shared-register addressing, conflict-free operand delivery, and fiber-based program mapping. Under a typical mixed-precision LLM serving scenario, FIBER achieves a 2.25x end-to-end speedup on Ampere (1.15x for the original FP16 computation), with 1.8x and 2.09x on Hopper and Blackwell respectively, and kernel-level gains up to 2.49x.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/a-thread-register-decoupled-gpu-execution-model-for-efficient-tensor-computation", "canonical_source": "https://arxiv.org/abs/2608.19628", "published_at": "2026-08-26 19:08:58+00:00", "updated_at": "2026-08-26 20:21:30.269087+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-infrastructure", "ai-research"], "entities": ["FIBER", "Ampere", "Hopper", "Blackwell", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/a-thread-register-decoupled-gpu-execution-model-for-efficient-tensor-computation", "markdown": "https://wpnews.pro/news/a-thread-register-decoupled-gpu-execution-model-for-efficient-tensor-computation.md", "text": "https://wpnews.pro/news/a-thread-register-decoupled-gpu-execution-model-for-efficient-tensor-computation.txt", "jsonld": "https://wpnews.pro/news/a-thread-register-decoupled-gpu-execution-model-for-efficient-tensor-computation.jsonld"}}