https://arshadhs.github.io/tags/latency/Recent content in Latency on Arshad SiddiquiHugoen-ushttps://arshadhs.github.io/docs/ai/038-ml-system-optimisation/010-ml-and-dl-system-performance/Mon, 01 Jan 0001 00:00:00 +0000https://arshadhs.github.io/docs/ai/038-ml-system-optimisation/010-ml-and-dl-system-performance/<h1 id="ml-and-dl-system-performance"> ML and DL System Performance <a class="anchor" href="#ml-and-dl-system-performance">#</a> </h1> <p>Machine learning system optimisation begins with measurement. Before changing an algorithm, adding processors, or moving work to a GPU, we need to understand <strong>what is slow</strong>, <strong>which resource is limiting performance</strong>, and <strong>how performance changes as the workload grows</strong>.</p> <p>This page covers:</p> <ul> <li>time and space complexity</li> <li>throughput and latency</li> <li>the relationship between workload, throughput, and latency</li> <li>the main measurements used to describe system performance</li> </ul> <h2 id="learning-objectives"> Learning Objectives <a class="anchor" href="#learning-objectives">#</a> </h2> <p>By the end of this page, you should be able to:</p>