Скачать или смотреть TornadoVM: Transparent Hardware Acceleration of Managed Languages - Athanasios Stratikopoulos

This poster was presented at the virtual Arm Research Summit, September 9-11, 2020. This year's event explored global technology challenges across sustainability, security, and society, and attracted delegates from around the world for three days of innovative content.

In this poster presentation, Athanasios presents his work towards achieving transparent hardware acceleration of managed programming languages in the Arm ecosystem. In detail, he describes TornadoVM and its extended support for Arm GPUs and Xilinx FPGAs.

TornadoVM is a plug-in to OpenJDK and GraalVM that allows programmers to automatically run Java programs on heterogeneous hardware. TornadoVM currently targets OpenCL-compatible devices and it runs on multi-core CPUs (Intel, Arm), GPUs (NVIDIA and AMD), Intel integrated GPUs, and FPGAs (Intel and Xilinx). TornadoVM consists of three components: 1) a simple API for composing pipelines of existing Java methods, 2) an optimizing JIT compiler that extends the Graal compiler with hardware-aware optimizations that generate OpenCL C code, and 3) a runtime system that executes TornadoVM specific bytecodes, performs memory management, and schedules the code for execution on GPUs, multicore CPUs, and FPGAs. Essentially, TornadoVM is a “VM-in-a-VM” that can adapt execution completely dynamically and transparently to the user, always finding the highest-performing combination of hardware accelerators through dynamic reconfiguration.

Since version 0.6, TornadoVM can be executed on AArch64 architectures and accelerate high-level managed applications on Mali GPUs and Xilinx FPGAs completely transparently to the users. A number of examples and initial performance results will be showcased.

To view Athanasios' full poster in detail, click here: https://bit.ly/2GKInE1