JavaConference45min
TornadoVM: Supercharge your Java applications with GPU acceleration
This talk introduces TornadoVM, an open-source framework enabling seamless GPU acceleration for Java applications, including AI and LLM inference. Used by the ESA GAIA mission, TornadoVM simplifies GPU programming and boosts performance, offering a rich ecosystem for development and integration with Java AI libraries and frameworks.
Christos KotselidisThe University of Manchester/Nimble Innovation
Mary XekalakiUniversity of Manchester
talkDetail.whenAndWhere
Tuesday, February 10, 09:25-10:10
Globe
talks.roomOccupancytalks.noOccupancyInfo
In this talk we will present TornadoVM (www.tornadovm.org); a state-of-the-art programming framework that enables native GPU acceleration of Java programs. TornadoVM allows developers to program GPUs from within Java while the system handles compilation, execution, and optimization completely transparently.
TornadoVM is an open-source project (https://github.com/beehive-lab/TornadoVM) and it is being used by the European Space Agency GAIA mission to accelerate its data processing pipelines resulting in significant reduction of execution times. In addition, it offers a rich toolset ecosystem to help developers throughout their journey (coding, debugging, performance optimizations) and it recently added to its ecosystem GPULlama3.java (https://github.com/beehive-lab/GPULlama3.java); the first GPU-accelerated native Java implementation for AI inference on a plethora of LLM models which has been integrated with Lanchain4J and Quarkus.
The target audience is developers who wish to make a first transition into the GPU programming world, or just practitioners who wish to use the high performance Java AI libraries that TornadoVM provides.
The key takeaways are:
1) Java is AI ready since we can harness GPU power natively for LLM inference
2) Programming GPUs from within Java is easier with the mature ecosystem that TornadoVM provides
3) Having a native Java platfrom for AI and general purpose GPU acceleration enhances both productivity and integration
TornadoVM is an open-source project (https://github.com/beehive-lab/TornadoVM) and it is being used by the European Space Agency GAIA mission to accelerate its data processing pipelines resulting in significant reduction of execution times. In addition, it offers a rich toolset ecosystem to help developers throughout their journey (coding, debugging, performance optimizations) and it recently added to its ecosystem GPULlama3.java (https://github.com/beehive-lab/GPULlama3.java); the first GPU-accelerated native Java implementation for AI inference on a plethora of LLM models which has been integrated with Lanchain4J and Quarkus.
The target audience is developers who wish to make a first transition into the GPU programming world, or just practitioners who wish to use the high performance Java AI libraries that TornadoVM provides.
The key takeaways are:
1) Java is AI ready since we can harness GPU power natively for LLM inference
2) Programming GPUs from within Java is easier with the mature ecosystem that TornadoVM provides
3) Having a native Java platfrom for AI and general purpose GPU acceleration enhances both productivity and integration
Christos Kotselidis
I am an Associate Professor (Reader) at The University of Manchester and a Chief Engineer at Nimble Innovation. I currently lead the TornadoVM project which bring native GPU acceleration of AI applications in Java. In addition, I am the technical coordinator of the Horizon Europe/UKRI AERO project and the PI of the EU Horizon Europe/UKRI P2CODE, TANGO, and ENCRYPT projects. My work focuses on both hardware and software. In particular, I am interested in embedded systems, micro-architecture, hw/sw co-designed CPUs and VMs, Heterogeneous Acceleration, Compilers, Virtual Machines and Garbage Collection.
talkDetail.shareFeedback
talkDetail.feedbackNotYetAvailable
talkDetail.feedbackAvailableAfterStart
talkDetail.signInRequired
talkDetail.signInToFeedbackDescription
occupancy.title
occupancy.votingNotYetAvailable
occupancy.votingAvailableBeforeStart
talkDetail.signInRequired
occupancy.signInToVoteDescription
comments.speakerNotEnabledComments