GPU-Acceleration for the Graal VM

This project aims at automatically accelerating applications running on top of the Graal VM, an Open source Java VM. To achieve this goal we first define a high-level API inspired by functional programming and data-flow programming concepts. At runtime, our system recognises the calls to our API and automatically generate OpenCL kernels. The runtime then manages the execution of this OpenCL kernel on multiple devices (e.g. GPU) which results in the application being transparently accelerated.

Supported by

Oracle Labs
Oracle Labs

Christophe Dubach
Christophe Dubach
Associate Professor
Canada CIFAR AI Chair, Mila

My research interests include data-prallel language design and implementation, high-level code generation and optimisation for parallel hardware (e.g. GPU, FPGAs), architecture design space exploration, and the use of machine-learning techniques applied to all these topics.

Michel Steuwer
Michel Steuwer
Postdoc 2015-2017 (Edinburgh University) Now Lecturer at Glasgow University
Juan Fumero
Juan Fumero
PhD student 2013-2017 (Edinburgh University)