At Partisia we are pioneers in building, tailoring and offering high-security privacy preserving software by providing new standards for secure solutions to protect and compute on confidential and highly regulated data. In this session we will present how Europe is currently focused on using privacy preserving measures in the healthcare industry to encrypt, protect and enable collaboration between hospitals and organizations using Multiparty Computation. In extension of that we will also present the future of data ownership, where each citizen is at the center of their own personal data, and has the power to controllably share it in a transparent and secure way across industries.

Optalysys is developing cutting edge photonic technology to directly address the processing challenges of using FHE methods at speed. We recently launched our cloud platform Explore which allows users to engage with the hardware through integrations with the main FHE libraries. Dr New will provide an update on the platform and present the Optalysys vision for the future of secure computing. 

The rise of generative AI has increased the size of LLMs, escalating computing costs for services. While Datacenter LLM services use larger batch sizes to improve GPU efficiency, self-attention block processing is still suffering from low efficiency. SK hynix's AiM device, utilizing Processing in Memory technology, offers high bandwidth and high energy efficiency, reducing operational costs significantly compared to GPUs regardless of batch size. Additionally, applying AiM in on-device services enables high performance and low energy consumption, enhancing competitiveness. SK hynix has developed the AiMX accelerator prototype for Datacenters, showcasing single batch operations last year and planning multi-batch operations with larger models this year. The AiMX structure can be similarly applied to on-device AiM implementations. SK hynix's AiM/AiMX solutions address cost, performance, and power challenges in LLM services for both Datacenters and on-device AI applications.

Flexible and programmable solutions are the key to delivering high performance, high efficiency AI at the edge. As semiconductor technologies experience the biggest shift in decades in order to meet the requirements of the latest generation of AI models, software is set to be the true enabler of success. Optimised libraries and toolkits empower all stakeholders in the developer journey to follow the “functional to performant to optimal” workflow typical of today’s edge compute application development cycle.

This presentation will present a software-first approach to enabling AI at the edge, touching on the importance of community-wide initiatives such as The UXL Foundation, of which Imagination is a founding member. 

Imagination is a global leader in innovative edge technology, delivering landmark GPU, CPU and AI semiconductor solutions across automotive, mobile, consumer and desktop markets for over thirty years.