A Proposed Framework for Advanced (Multi)Linear Infrastructure in Engineering and Science (FAMLIES)
2026-04-08 • Mathematical Software
Mathematical Software
AI summaryⓘ
The authors build on their previous successful software projects to create a new framework that connects tools for working with both regular matrices and multi-dimensional arrays (tensors). Their goal is to make these computations fast and flexible on different types of computers, from single processors to large parallel systems using CPUs and GPUs. They use their experience from earlier research and software to implement important linear algebra and tensor operations. This new framework aims to support scientific and machine learning applications by being adaptable and efficient.
linear algebratensor computationsBLASGPUsparallel computingsoftware frameworkmulti-core processorsalgorithm derivationmachine learningscientific computing
Authors
Devin A. Matthews, Tze Meng Low, Margaret E. Myers, Devangi N. Parikh, Robert A. van de Geijn
Abstract
We leverage highly successful prior projects sponsored by multiple NSF grants and gifts from industry: the BLAS-like Library Instantiation Software (BLIS) and the libflame efforts to lay the foundation for a new flexible framework by vertically integrating the dense linear and multi-linear (tensor) software stacks that are important to modern computing. This vertical integration will enable high-performance computations from node-level to massively-parallel, and across both CPU and GPU architectures. The effort builds on decades of experience by the research team turning fundamental research on the systematic derivation of algorithms (the NSF-sponsored FLAME project) into practical software for this domain, targeting single and multi-core (BLIS, TBLIS, and libflame), GPU-accelerated (SuperMatrix), and massively parallel (PLAPACK, Elemental, and ROTE) compute environments. This project will implement key linear algebra and tensor operations which highlight the flexibility and effectiveness of the new framework, and set the stage for further work in broadening functionality and integration into diverse scientific and machine learning software.