https://trolmark.github.io/tags/matrix-multiplication/Recent content in Matrix-Multiplication on Andrii's NotesHugoen-usSun, 20 Sep 2026 00:00:00 +0000https://trolmark.github.io/posts/blog_gemm_syrk/Sun, 20 Sep 2026 00:00:00 +0000https://trolmark.github.io/posts/blog_gemm_syrk/<h2 id="the-task-pearson-correlation"> The task: Pearson correlation <a class="heading-link" href="#the-task-pearson-correlation"> <i class="fa-solid fa-link" aria-hidden="true" title="Link to heading"></i> <span class="sr-only">Link to heading</span> </a> </h2> <p>This is the story of a task I solved during a performance-programming course from Aalto University&rsquo;s <a href="https://ppc.cs.aalto.fi/" class="external-link" target="_blank" rel="noopener">Programming Parallel Computers</a>:</p> <p>given an <code>ny × nx</code> matrix, compute the lower triangle of its <code>ny × ny</code> Pearson correlation matrix as fast as possible on a CPU. <strong>Pearson correlation</strong> measures how similarly two rows vary after removing their means. A value near <code>1</code> means they move together, <code>-1</code> means they move in opposite directions, and <code>0</code> means no linear correlation.</p>