The company will demonstrate the breadth of its ecosystem and value of optical I/O in advancing AI infrastructure at Supercomputing 2024
Ayar Labs, the leader in optical interconnect solutions for large-scale AI workloads, will demonstrate a broad range of optical I/O implementations for AI scale-up fabrics at its Supercomputing 2024 (SC24) booth (#810). The company’s optical I/O solution eliminates the inefficiencies, high power consumption, and increasing costs of copper interconnects and pluggable optics, revolutionizing the performance and economics of AI infrastructure. Ayar Labs will feature its technology in various AI infrastructure concepts with Fujitsu Limited, Intel Foundry, Corning Inc, Altera, and others at the event.
“Copper interconnects and pluggable optics have already failed to support large-scale AI workloads,” said Mark Wade, CEO & Co-Founder of Ayar Labs. “Optical I/O overcomes these bottlenecks by enabling scale-up fabrics that connect more GPUs or accelerators per cluster across greater distances. This increases cluster performance without increasing power per rack, which paves the way for more efficient, cost-effective, and profitable AI infrastructure.”
Ayar Labs and Fujitsu will showcase the future of hardware and system architecture design in response to the growing demands of AI and HPC workloads. A conceptual model of Ayar Labs’ optical I/O solution integrated with the Fujitsu A64FX processors in a PRIMEHPC FX700 chassis will be on display in Ayar Labs’ booth representing up to 16 Tbps of bi-directional bandwidth with the integration of two TeraPHY™ optical I/O chiplets per CPU.
“Collaborating with Ayar Labs allows us to showcase a new era of AI and HPC system design,” said Naoki Shinjo, SVP, Head of Advanced Technology Development Unit at Fujitsu. “Our joint architectural concept at SC24 highlights our commitment to push the boundaries of innovation and deliver unparalleled solutions that meet tomorrow’s most demanding computational challenges.”
In addition to the model on display, Ayar Labs and Fujitsu will present a joint talk titled “New Optical-Based Scale-Up Fabrics to Meet the Performance and TCO Requirements of Next-Generation AI/HPC System Architectures” on Tuesday, November 19 at 11:30 a.m., room B206. Vladimir Stojanovic, Ayar Labs’ CTO & Co-Founder, and Miki Atsushi, a member of Fujitsu’s Advanced Technology Development Division, will discuss the key challenges in current architectures and the requirements for future systems, while Ayar Labs will explain how optical I/O-based scale-up fabrics enhance system-level performance and reduce total cost of ownership for these systems.
Other demonstrations and displays planned for SC24 include:
- Innovative AI System Architecture Tool: Developed by Ayar Labs, this new tool can predict the performance and economics of AI inference workloads, including future agentic models. It helps assess next-gen AI infrastructure by simulating various GPU and network configurations. Visitors to the booth can see the impact Ayar Labs’ optical I/O has on scaling large language model (LLM) inference, with profitability gains up to 20x and a 3-4x interactivity improvement in future GPT models.
- Advancing AI with Optical FPGAs: Ayar Labs, Altera, and Corning have partnered to pioneer a new optical field-programmable gate array (FPGA) solution. This proof of concept provides 4 Tbps of bi-directional I/O data transfer by integrating Ayar Labs’ TeraPHY™ optical I/O chiplets with Corning’s advanced glass waveguide modules to Altera’s FPGA fabric. This unique solution provides unprecedented bandwidth and latency for compute-intensive applications like generative AI, LLMs, and AI scale-up fabrics.
- 4 Tbps In-Package Optical I/O Solution: SC24 guests can experience a live demonstration of Ayar Labs’ 4 Tbps optical I/O solution powered by its SuperNova™ light source. Visitors can see first-hand ultra-efficient data transfer at extremely low latency without the need for forward error correction (FEC). Ayar Labs optical I/O provides a high level of energy efficiency, power density, and performance per watt that is ideally suited for AI models with trillions of parameters, advanced HPC designs, and more.
- Detachable Optical Connector Ecosystem: Ayar Labs will highlight the latest advancements in detachable optical connectors for optical I/O, including the latest Intel Foundry detachable photonic glass interconnect and the Teramount TeraVERSE® detachable connector. These connectors enable flexible, efficient, and cost-effective deployment and maintenance of Ayar Labs’ in-package optical I/O solutions for AI.
For a complete list of Ayar Labs’ SC24 activities, please visit: https://ayarlabs.com/supercomputing/
About Ayar Labs
Ayar Labs is the leader in optical interconnect solutions that move data at the speed of AI. Recognizing that the complexity and size of AI models are increasing at a rate that traditional interconnect technology cannot handle, the company has developed the industry’s first optical I/O solution that enables customers to maximize the compute efficiency and performance of growing AI infrastructure, while reducing costs, latency and power consumption. Based on open standards and optimized for both AI training and inference, Ayar Labs’ optical I/O solution is backed by a robust ecosystem that enables it to integrate smoothly into AI systems at scale. Ayar Labs was founded in 2015 and is funded by domestic and international venture capital firms, as well as strategic investors including GlobalFoundries, Hewlett Packard Pathfinder, Intel Capital, Lockheed Martin Ventures, and NVIDIA. For more information, visit www.ayarlabs.com