https://yuchaosu.com/tags/tenstorrent/TenstorrentHugo Blox Builder (https://hugoblox.com)en-usThu, 02 Oct 2025 00:00:00 +0000https://yuchaosu.com/media/icon_hu_982c5d63a71b2961.pnghttps://yuchaosu.com/tags/tenstorrent/https://yuchaosu.com/post/tenstorrent/Thu, 02 Oct 2025 00:00:00 +0000https://yuchaosu.com/post/tenstorrent/<p><strong>Official Documentation:</strong> </p> <p> </p> <!-- [Tenstorrent Metalium](https://docs.tenstorrent.com/tt-metal/latest/tt-metalium/index.html) --> <!-- [Tenstorrent Metalium Examples](https://docs.tenstorrent.com/tt-metal/latest/tt-metalium/tt_metal/examples/index.html) --> <h2 id="introduction-to-tenstorrent">Introduction to Tenstorrent</h2> <p>Tenstorrent is a Canadian AI hardware and software company that designs and manufactures high-performance processors for machine learning and artificial intelligence applications. Founded in 2016 by Ljubomir Perkovic, Tenstorrent aims to provide cutting-edge solutions for AI workloads, focusing on efficiency, scalability, and performance. Tenstorrent has multiple levels of software stack, including:</p> <ul> <li> : The low-level, open-source software development kit (SDK) that provides developers direct access to Tenstorrent hardware. It is a bare-metal programming environment designed for users who must write custom C++ kernels for machine learning or other high-performance computing workloads.</li> </ul> <p> <figure id="figure-tenstorrent-software-stack"> <div class="flex justify-center "> <div class="w-full" > <img alt="Tenstorrent Software Stack" srcset="https://yuchaosu.com/post/tenstorrent/Software_hu_978631f73d4d279.webp 320w, https://yuchaosu.com/post/tenstorrent/Software_hu_56ac139426d8d5a5.webp 480w, https://yuchaosu.com/post/tenstorrent/Software_hu_15a9d1f58a8ec066.webp 760w" sizes="(max-width: 480px) 100vw, (max-width: 768px) 90vw, (max-width: 1024px) 80vw, 760px" src="https://yuchaosu.com/post/tenstorrent/Software_hu_978631f73d4d279.webp" width="760" height="641" loading="lazy" data-zoomable /></div> </div><figcaption> Tenstorrent Software Stack </figcaption></figure> </p> <ul> <li> : Tenstorrent’s Multi-Level Intermediate Representation (MLIR)-based compiler. It bridges high-level machine learning frameworks with the Tenstorrent software stack.</li> <li> : A library of neural network operations that provides a user-friendly interface for running models on Tenstorrent hardware. It is designed to be intuitive for developers familiar with PyTorch.</li> <li> : Deprecated.</li> </ul> <h2 id="tenstorrent-hardware-overview">Tenstorrent Hardware Overview</h2> <p> <figure id="figure-tenstorrent-hardware-overview"> <div class="flex justify-center "> <div class="w-full" > <img alt="Tenstorrent Hardware Overview" srcset="https://yuchaosu.com/post/tenstorrent/Overview_hu_2847d3bfd50f4a8.webp 320w, https://yuchaosu.com/post/tenstorrent/Overview_hu_a9f36c0d9b2d1aca.webp 480w, https://yuchaosu.com/post/tenstorrent/Overview_hu_1d1067e0775e6e9c.webp 760w" sizes="(max-width: 480px) 100vw, (max-width: 768px) 90vw, (max-width: 1024px) 80vw, 760px" src="https://yuchaosu.com/post/tenstorrent/Overview_hu_2847d3bfd50f4a8.webp" width="760" height="531" loading="lazy" data-zoomable /></div> </div><figcaption> Tenstorrent Hardware Overview </figcaption></figure> </p> <h3 id="overview">Overview</h3> <h3 id="tensix-core">Tensix Core</h3> <h3 id="large-risc-v-core">Large RISC-V Core</h3> <h3 id="arc-core">ARC Core</h3> <h3 id="dram-core">DRAM Core</h3> <h3 id="ethernet-core">Ethernet Core</h3> <h3 id="pcie-core">PCIE Core</h3> <h2 id="tensix-core-1">Tensix Core</h2> <ul> <li>Baby RISC-V core</li> <li>Router</li> <li>Compute</li> <li>Buffer</li> </ul>