<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Juan Fumero on foojay.io - Friends Of OpenJDK</title><link>https://foojay.io/today/author/juan-fumero/</link><description>Articles written by Juan Fumero on foojay.io - Friends Of OpenJDK</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 19 Sep 2024 07:50:28 +0000</lastBuildDate><atom:link href="https://foojay.io/today/author/juan-fumero/index.xml" rel="self" type="application/rss+xml"/><item><title>TornadoVM for RISC-V Accelerators</title><link>https://foojay.io/today/tornadovm-for-risc-v-accelerators/</link><pubDate>Thu, 19 Sep 2024 07:50:28 +0000</pubDate><guid>https://foojay.io/today/tornadovm-for-risc-v-accelerators/</guid><description>&lt;h2 id="takeaways"&gt;Takeaways&lt;/h2&gt;&#10;&lt;ul&gt;&#10;&lt;li&gt;RISC-V is an open standard instruction set architecture that anyone can use to build new processors and accelerators, for example, for AI.&lt;/li&gt;&#10;&lt;li&gt;oneAPI Construction Kit (OCK) is a new framework that allows software developers and system designers to bridge the gap between hardware accelerators and open standards, by enabling a programming system to implement domain specific instructions for modern hardware such as RISC-V accelerators and custom processors.&lt;/li&gt;&#10;&lt;li&gt;TornadoVM, a parallel programming framework for Java, can take advantage of OCK to offload and accelerate Java workloads on RISC-V chips. This post shows how to run on RISC-V CPUs with vector extensions.&lt;/li&gt;&#10;&lt;/ul&gt;&#10;&lt;h2 id="introduction"&gt;Introduction&lt;/h2&gt;&#10;&lt;p&gt;&lt;a href="https://riscv.org/" title="RISC-V" target="_blank" rel="noopener noreferrer"&gt;RISC-V&lt;/a&gt; is an open standard instruction set architecture (ISA) based on the principles of reduced instruction sets (RISC). RISC-V is freely available under open licences, allowing anyone to design, modify and implement RISC-V processors.&lt;/p&gt;</description></item><item><title>The TornadoVM Programming Model Explained</title><link>https://foojay.io/today/the-tornadovm-programming-model-explained/</link><pubDate>Tue, 28 May 2024 11:01:14 +0000</pubDate><guid>https://foojay.io/today/the-tornadovm-programming-model-explained/</guid><description>&lt;h2 id="key-takeaways"&gt;Key Takeaways&lt;/h2&gt;&#10;&lt;p&gt;&lt;img src="https://foojay.io/today/the-tornadovm-programming-model-explained/back-c8acc920.jpg" alt="" width="1600" height="914" loading="lazy" decoding="async"&gt;&lt;/p&gt;&#10;&lt;ul&gt;&#10;&lt;li&gt;&lt;a href="https://github.com/beehive-lab/TornadoVM/" target="_blank" rel="noopener noreferrer"&gt;TornadoVM&lt;/a&gt; offers an API for parallel programming on modern hardware that tackles data parallel, task parallel and pipeline parallel applications.&lt;/li&gt;&#10;&lt;li&gt;TornadoVM offers different abstractions to developers to be able to express parallel applications in Java, identify the methods to offload, and dispatch the application on the corresponding accelerators.&lt;/li&gt;&#10;&lt;li&gt;Task-Graphs and Execution Plans are the main building blocks of TornadoVM applications, allowing developers to compose complex graphs of computations and interact with the TornadoVM runtime to enable/disable profiling, enable debugging, or enable dynamic reconfiguration to select the best possible accelerators for the compute graphs.&lt;/li&gt;&#10;&lt;/ul&gt;&#10;&lt;p&gt;In this blog post, I will explain how developers can start programming with TornadoVM and interact with the TornadoVM runtime.&lt;/p&gt;</description></item></channel></rss>