Alphawave Semi CTO to Present Keynote on Connectivity for AI to Annual IEEE Hot Interconnects Symposium
Dr. Tony Chan Carusone addresses the transformational role played by chiplets in enabling the accelerated bandwidth demands of artificial intelligence
LONDON, United Kingdom, and TORONTO, Canada – August 21 2024 - Alphawave Semi (LSE: AWE), a global leader in high-speed connectivity and compute silicon for the world’s technology infrastructure, announces its CTO, Dr. Tony Chan Carusone, will deliver a keynote address on chiplets and connectivity for AI systems to the IEEE Hot Interconnects symposium.
Now in its 31st year, the symposium will focus on the explosion of AI and workloads related to machine and deep learning, with insight into interconnection networks that alleviate bottlenecks as AI models double in size every four months.
Taking place from August 21 - 23, the event will highlight that as AI models grow, back-end GPU networks must expand beyond the confines of the rack. Given this premise, the question becomes: How can optical interconnects be engineered to transmit over tens of meters and at speeds of 10Tb/s, with data transfer rates doubling every two years?
In his presentation entitled “Connectivity for AI Everywhere: The Role of Chiplets”, Dr. Tony Chan Carusone will examine how chiplet-based architectures are enabling companies to reduce costs and time-to-market to meet the accelerated demands of AI infrastructure, addressing inter-die communication and high-speed optical connectivity.
Dr. Tony Chan Carusone’s presentation will take place on August 21 and is one of three keynotes at the seminar, alongside Meta’s Principal Research Scientist and NeuralFabric’s CTO. Last year’s keynotes were delivered by AMD, Lightmatter and Nvidia.
“It is a very prestigious honor to deliver a keynote at this symposium, especially now evolutions in optical interconnects are among the most critical in enabling AI systems to continue their pace of acceleration,” said Dr. Tony Chan Carusone. “The shift from monolithic SoCs to chiplet-based architectures will prove essential in enabling this evolution. This brings several benefits, not just in terms of time-to-market, but power and cost too. But, the good news is that this move is backed by a strong ecosystem of vendors, open standards, tools, interconnect protocols and manufacturing partners.”
Dr. Tony Chan Carusone’s keynote, ‘Connectivity for AI Everywhere: The Role of Chiplets’, takes place August 21 ,1 p.m. PDST. For further information https://hoti.org/event/ai_everywhere.
For more information on Alphawave Semi visit https://awavesemi.com.
About Alphawave Semi
Alphawave Semi is a global leader in high-speed connectivity and compute silicon for the world's technology infrastructure. Faced with the exponential growth of data, Alphawave Semi's technology services a critical need: enabling data to travel faster, more reliably, and with higher performance at lower power. We are a vertically integrated semiconductor company, and our IP, custom silicon, and connectivity products are deployed by global tier-one customers in data centres, compute, networking, AI, 5G, autonomous vehicles, and storage. Founded in 2017 by an expert technical team with a proven track record in licensing semiconductor IP, our mission is to accelerate the critical data infrastructure at the heart of our digital world. To find out more about Alphawave Semi, visit: awavesemi.com.
Related Chiplet
- Optical Chiplet
- Reverse Gearbox Chiplet
- FlexGen Multi-Die Smart Network-on-Chip (NoC) IP
- Ncore Multi-Die Interconnect IP
- Integrated voltage regulator (IVR) chiplet
Related News
- Alphawave Semi ‘Redefines Connectivity’ in AI Hardware and Edge AI Summit 2024 Presentation on Chiplet Interconnects
- Alphawave Semi Tapes Out Industry-First, Multi-Protocol I/O Connectivity Chiplet for High-Performance Compute and AI Infrastructure
- Alphawave Semi Partners with PCISig, CXL Consortium, UCIe Consortium, Samtec and Lessengers to Showcase Advances in AI Connectivity at Supercomputing 2024
- Alphawave Semi Scales UCIe™ to 64 Gbps Enabling >20 Tbps/mm Bandwidth Density for Die-to-Die Chiplet Connectivity
Latest News
- Amkor Technology and NVIDIA Advance Strategic Partnership for AI Infrastructure
- Siemens expands agentic AI collaboration to tackle 3D IC power and thermal challenges with NVIDIA
- Photon Bridge Raises €10M to Tackle AI’s Emerging Laser Bottleneck
- Abacus Semiconductor and Aalto University Announce Research Cooperation on High-Speed Chiplet Interconnects
- UK Launches Semiconductor Catapult to Strengthen Sovereign Capabilities in AI Hardware and Defence