Astera Labs at FMS 2025: Accelerating Storage and Memory Innovation in the AI Infrastructure 2.0 Era

Paroma Sen, VP, Corporate Marketing

As AI models push computational boundaries with breakthrough reasoning capabilities, storage and memory must also evolve to optimize AI Infrastructure 2.0. From training massive models to enabling real-time inference, every part of the AI workflow relies on seamless connectivity between diverse storage and memory technologies.

Join Astera Labs at the Future of Memory and Storage Summit (FMS), taking place August 5-7 at the Santa Clara Convention Center, where we’re advancing next-generation connectivity architectures through breakthrough demonstrations and technical sessions that define how interconnects such as CXL®, PCIe®, UALink™, and Ethernet  enable AI workflows from training to inference. This is where the industry comes together to solve the convergence challenges of connecting diverse storage and memory technologies into unified AI systems—and we’re driving that transformation through hands-on demonstrations, insight-driven panels and presentations, and expert networking sessions that define the path forward.

Advancing the State-of-the-Art Through Industry-First Demonstrations

  • Advancing End-to-end PCIe 6 Leadership with Enhanced Storage Performance with Micron
    • Experience the next transformative advancement in AI storage performance and see how we’re setting a new bar for AI platform performance – following our industry-first end-to-end PCIe 6 demo at DesignCon where Astera Labs Scorpio P-Series Fabric Switch and Micron’s PCIe 6 SSD delivered an unparalleled sequential read speed of 27GB/s.  
    • Micron Booth 107
  • Delivering NVMe over PCIe 6 with Teledyne Lecroy
    • See how we’re working with Teledyne LeCroy to lay the foundation for the PCIe 6 ecosystem. This demonstration featuring our Aries 6 Retimer and Scorpio P-Series Fabric Switch and Teledyne LeCroy’s M64 PCIe 6 analyzer verifies next-gen storage with live traffic and analysis.
    • Teledyne LeCroy Booth 625
  • Boosting AI Inferencing Performance with CXL Memory with SMART Modular Technologies
    • Learn how Astera Labs’ Leo CXL Smart Memory Controller and SMART Modular Technologies’ CXL Add-in Card expand memory capacity and improve I/O efficiency, boosting AI inferencing performance.
    • CXL Consortium Booth 725
  • Delivering CXL Memory Expansion and Composability with Liqid
    • Check out how Liqid is enabling CXL memory expansion with Samsung and Cisco. Featuring Astera Labs’ Leo CXL Smart Memory Controllers and Aries PCIe/CXL Smart DSP Retimers , the Liqid platform delivers memory composability via low-latency, high-bandwidth interconnects, meeting the demands of memory-bound AI workloads and in-memory databases
    • Samsung Booth 407
  • Bridging PCIe 6 and 5 Storage with Kioxia
    • See our showcase of Equinox 6 Aries Smart DSP Retimer CEM Add-in Card and Sargas Scorpio Smart Fabric Switch CEM Add-In Card. Our PCIe 6 solutions deliver line-rate performance with PCIe 5 SSDs from Kioxia.
    • Kioxia Booth 307
  • Leading the Scale-up AI Infrastructure Transformation with UALink
    • Meet with our experts at the UALink Consortium kiosk and learn how Astera Labs plans to support a full portfolio of UALink devices.
    • UALink Consortium Booth 725

Hear from Our Connectivity Experts

  • PCIe Technology in AI/ML: Maintaining High-Speed Connectivity
    • Panelist: Casey Morrison, Chief Product Officer
    • Tuesday, August 5, 9:45am-10:50am, Ballroom D, Floor 1
    • Join this panel moderated by PCI-SIG Board Chair Al Yanes and panelists from Astera Labs, Amphenol and Synopsys to learn about the key features of the new PCIe 7 specification and how PCI-SIG’s continued doubling of the data rate allows AI chipset vendors and AI accelerator developers to maintain a clear path for growth today and into the future
  • How CXL Transforms Server Memory Infrastructure
    • Speaker:Sandeep Dattaprasad, Director, Product Management/Technologist
    • Wednesday, August 6, 9:45am-10:50am, Ballroom D, Floor 1
    • Explore the benefits of CXL memory pooling and sharing and gain valuable insights into how the technology is being deployed to accelerate performance in AI workloads, In-Memory Databases, and Big Data Analytics.
  • Chat with the Experts: Focus on UALink and CXL
    • UALink Expert: Thad Omura, Chief Business Officer
    • CXL Expert: Sandeep Dattaprasad, Director, Product Management/Technologist
    • Wednesday, August 7, 7:15pm-9:00pm, Ballroom A-D, Floor 1
    • Meet one-on-one with our connectivity experts to get your questions on UALink and CXL technologies answered.
  • Accelerating AI with Real-World CXL Platforms
    • Speakers: Sandeep Dattaprasad, Director, Product Management/Technologist and Andy Mills, VP, Advanced Product Development, SMART Modular Technologies
    • Thursday, August 7, 12:10pm-1:15pm, Ballroom B, Floor 1
    • Learn how deploying CXL-based memory controllers and add-in cards alleviate data center bottlenecks and gain insights into CXL’s critical role in advancing AI infrastructure.
  • Why Now? UALink Emerges as a Leading Standard for Scale-Up Architectures
    • Speaker: Mike Hendricks, AVP, Solutions and Ecosystems
    • Thursday, August 7, 1:25pm-2:30pm, Ballroom C, Floor 1
    • Learn about UALink technology while we debunk the myth of memory semantics vs. network semantics.

The transformation to AI Infrastructure 2.0 requires bringing together diverse storage and memory technologies into unified systems that serve the complete AI workflow. At FMS 2025, we’re driving this convergence through purpose-built connectivity solutions and open standards that enable breakthrough AI performance.

Email to schedule a meeting with our connectivity experts at the show. We look forward to seeing you at FMS 2025!