Open Ecosystem, Scalability, and Power Efficiency are Key to Equipping Partners with State-of-the-Art AI Technology
PALO ALTO, Calif., Oct. 08, 2024 (GLOBE NEWSWIRE) -- Broadcom Inc. ( AVGO) today announced that momentum continues to build in support of its vision of enabling AI infrastructure through a combination of open standards, scalability, and power efficient solutions. Broadcom will highlight advancements across the areas via a series of presentations, product demonstrations, and other forums at the 2024 Open Compute Project (OCP) Global Summit. The 2024 Summit takes place in San Jose, Calif. from Oct. 15-17. Highlights regarding Broadcom’s participation in this year’s Global Summit can be found here.
“AI is at an inflection point in our industry that will change our lives and the way we work,” said Charlie Kawwas, Ph. D., president, Semiconductor Solutions Group, Broadcom. “At Broadcom, we are on the front lines of this historic moment, pushing boundaries and pioneering breakthroughs in networking and connectivity to enable open, scalable and power efficient AI infrastructure. We are excited to showcase our products at the OCP Global Summit in collaboration with our partners who share our vision for enabling AI.”
As AI clusters expand to a million nodes, managing energy consumption becomes crucial, necessitating power-efficient and high-performance connectivity solutions. Further, open standards like Ethernet and PCIe play a vital role offering interoperable and time-to-market solutions for the rapidly growing AI infrastructure market.
At this year’s summit, Broadcom will showcase several innovations that power its comprehensive portfolio of Ethernet, Ethernet NIC Adapters, Co-Packaged Optics (CPO), PCIe switches and retimers, and Sian2 optical networking products. Broadcom’s AI architects and engineers will also deliver key talks and technical panels covering topics across our broad AI infrastructure solutions. The final agenda will be available here.
At the summit several cutting-edge AI solutions will be featured including:
- Ethernet networking switches like the Tomahawk 5 and Jericho3-AI designed to accelerate AI/ML workloads.
- The Trident4-X11 Ethernet switch engineered to create the front-end fabric that interfaces with the back-end AI fabric.
- Tomahawk 5 - Bailly, the world's leading 51.2 Tbps CPO Ethernet switch, which combines advanced silicon photonics CPO technology with Broadcom's Tomahawk 5 switch chip, setting a new benchmark for power efficiency and performance in AI infrastructure.
- High-performance, low-power 400G PCIe Gen 5.0 Ethernet adapters, developed as open, standards-based solutions to address connectivity challenges as XPU bandwidth increases and AI data center clusters expand.
- PCIe Gen 5.0 switches, which are the open, standards-based fabric of choice for AI connectivity; drawing half the power of alternatives, with industry leading SerDes, telemetry and diagnostics.
- The industry's first PCI Express Gen5/Gen6 retimers, offering ultra-low power solutions to enhance efficiency and scalability in AI infrastructure.
- Sian and Sian2 DSPs, supporting 200G/lane pluggable modules for connecting next-generation AI clusters.
Broadcom’s talks and panel events are designed to give the audience a peek into the technology behind our vision to enable AI infrastructure. Key talks and technical panel sessions at this year’s summit include:
- An Overview of Work Streams of Hardware Management Projects, Hemal Shah, distinguished engineer and architect, Broadcom and Jeff Autor, distinguished technologist, Hewlett Packard Enterprise, Weds, Oct. 16, 8:00am – 8:20am, Concourse Level - 210CG.
- Best Practices for Liquid & Air Cooling of a 51.2Tbps Switch for High-Density AI Clusters, Henry Wu, technical director, Broadcom, and Fangbo Zhu, senior thermal export, Alibaba, Weds, Oct. 16, 8:00am - 8:20am, Lower Level - LL20A.
- Standards Update: Reducing Optical Power Consumption, Karl Muth, hardware engineer, Broadcom and Nathan Tracy, member of the board, TE Connectivity, Weds, Oct. 16, 8:40am - 9:00am, Concourse Level 220 - C.
- Orchestration Needs with SONiC for AI Clusters, Kamini Santhanagopalan, product marketing engineer, Broadcom and Dan Hanson, director AI networking product management, Supermicro, Weds, Oct. 16, 10:40am -11:00am, Concourse Level - 220B.
- Introducing the SPDM Authorization Specification, Brett Henning, firmware engineer, Broadcom, Raghu Krishnamurthy, principal security architect, NVIDIA, and Scott Phuong, principal software engineer, Microsoft, Weds, Oct. 16, 1:30pm - 1:50pm, Concourse Level - 220C.
- OCP NIC 3.0: PCIe Gen 6 Support with Next Generation SI and Thermal Test Fixtures, Hemal Shah, distinguished engineer and architect, Broadcom, and Jason Rock, distinguished member of technical staff, and Jon Lewis, distinguished engineer, Dell, Weds, Oct. 16, 1:50pm - 2:10pm, Concourse Level - 210CG.
- Link Delay Measurement with P2P TC, Bhaskar Chinni, principal product line manager, and Amit Oren, distinguished engineer, architect and technology, Broadcom, Thurs, Oct. 17, 10:45am - 11:00am, Lower Level - LL20A.
About Broadcom
Broadcom Inc. ( AVGO) is a global technology leader that designs, develops, and supplies a broad range of semiconductor, enterprise software and security solutions. Broadcom's category-leading product portfolio serves critical markets including cloud, data center, networking, broadband, wireless, storage, industrial, and enterprise software. Our solutions include service provider and enterprise networking and storage, mobile device and broadband connectivity, mainframe, cybersecurity, and private and hybrid cloud infrastructure. Broadcom is a Delaware corporation headquartered in Palo Alto, CA. For more information, go to www.broadcom.com.
Broadcom, the pulse logo, and Connecting Everything are among the trademarks of Broadcom. The term "Broadcom" refers to Broadcom Inc., and/or its subsidiaries. Other trademarks are the property of their respective owners.
Press Contact:
Jon Piazza
Corporate Communications
[email protected]
Telephone: +1 310 498 5254
