TornadoVM Deep Dive: Empowering Java Developers with GPU Acceleration by Thanos Stratikopoulos, Ch скачать в хорошем качестве

TornadoVM Deep Dive: Empowering Java Developers with GPU Acceleration by Thanos Stratikopoulos, Ch

TornadoVM is an open-source technology that enables Java developers to tap into the power of GPUs and other hardware accelerators - without needing deep expertise in GPU programming. Designed for seamless integration, TornadoVM works with most major JDK distributions, including Amazon Corretto, GraalVM, OpenJDK, Red Hat Mandrel, Microsoft JDK, and Azul Zulu. Under the hood, it extends the Graal compiler with GPU code generation and introduces powerful runtime features, such as dynamic reconfiguration and multi-device execution.This deep dive session will guide the audience through the TornadoVM ecosystem, showing how it complements and enhances the Java tooling landscape:Crash Intro to GPU Programming - A quick overview of the GPU programming model and data parallelism.TornadoVM API Overview – Learn how to annotate and structure Java code to express parallelism and enable transparent offloading to accelerators.Tool Ecosystem – Discover the TornadoInsight IntelliJ plugin for profiling and debugging, and explore the TornadoVM Bytecode Visualizer to understand how Java code is transformed for heterogeneous targets.Live Demo: LLM Optimization – Integration with a separate Java project that will explain various optimizations applied at a large language model (LLM) pipeline, showcasing real-world GPU acceleration and performance insights. At this point we will see various attributes that can affect performance including data movements and code generation.