https://ramet.github.io/tags/solvers/ Solvers HugoBlox Kit (https://hugoblox.com)en-usThu, 01 Jan 2026 00:00:00 +0000 https://ramet.github.io/media/icon_hu_731727514bcb35a2.png https://ramet.github.io/tags/solvers/ https://ramet.github.io/projects/solverstack/ Thu, 01 Jan 2026 00:00:00 +0000 https://ramet.github.io/projects/solverstack/ <h1 id="solverstackinria-bordeaux">SolverStack@Inria Bordeaux</h1> <p><strong>SolverStack</strong> aims at providing a coherent, high-performance (HPC) linear algebra solver stack. It provides a comprehensive collection of numerical solvers, partitioning tools, and runtime systems designed for modern supercomputers operating on dense and sparse matrices.</p> <p>The ecosystem includes direct, iterative (Krylov), and hybrid direct/iterative methods, with advanced preconditioners and low-rank compression techniques, ensuring <em>portability of performance</em> from multicore laptops to petascale and exascale supercomputers.</p> <p>👉 <strong>Official Website:</strong> </p> <h2 id="software-ecosystem">Software Ecosystem</h2> <ul> <li><strong>Sparse Direct Methods:</strong> , </li> <li><strong>Dense Direct Methods:</strong> </li> <li><strong>Sparse Matrix Package:</strong> </li> <li><strong>Iterative &amp; Krylov Methods:</strong> </li> <li><strong>Hybrid Direct/Iterative Solvers:</strong> </li> <li><strong>Randomized &amp; Low-Rank Decompositions:</strong> </li> <li><strong>Task-Based Runtime Systems:</strong> </li> <li><strong>Communication Libraries:</strong> </li> <li><strong>Partitioning &amp; Ordering:</strong> </li> </ul> <h2 id="packaging--distribution">Packaging &amp; Distribution</h2> <p>SolverStack software components are systematically packaged and maintained for high-performance computing environments:</p> <ul> <li><strong>Guix-HPC:</strong> <code>guix install &lt;package&gt;</code> ( )</li> <li><strong>Spack:</strong> <code>spack install &lt;package&gt;</code> ( )</li> <li><strong>Homebrew:</strong> <code>brew install &lt;package&gt;</code> ( )</li> </ul> <h2 id="partner-teams--institutions">Partner Teams &amp; Institutions</h2> <p>SolverStack software is developed by researchers and engineers in joint project-teams at <strong>Inria Bordeaux Sud-Ouest</strong>, <strong>Bordeaux University</strong>, <strong>CNRS</strong> ( ), and <strong>Bordeaux INP</strong>:</p> <ul> <li> </li> <li> </li> <li> </li> <li> </li> </ul> <p><strong>Contact:</strong> </p>