SC23 Recap: Liqid

SC23 Recap: Liqid

The News: Liqid announced a new UltraStack L40S reference architecture at SC23 that combines Dell PowerEdge servers with NVIDIA graphic processor units (GPUs) to help organizations quickly meet high-density GPU demand. Read more about the announcement on the Liqid website.

SC23 Recap: Liqid

Analyst Take: Futurum Group analysts talked often about GPUs with IT organizations at SC23―everyone wants them, and a whole lot of them. With its composable infrastructure technology, Liqid has been helping organizations maximize the efficiency of their GPU deployments for a long time. With this latest announcement, a solution they unveiled at SC23, Liqid is now helping customers with challenges around GPU density.

The challenge for many customers is keeping up with demand for GPU power through deploying a dense GPU based solution. Liqid’s response is a new reference architecture called UltraStack L40S, which features Dell PowerEdge R760xa servers with 8 or 16 NVIDIA L40S GPUs, NVIDIA ConnectX-7 NICs, NVIDIA BlueField DPUs, and Liqid NVMe IO Accelerator cards.

This comprehensive solution helps organizations get up and running quickly with a large amount of GPU compute power. Liqid claims that the UltraStack L40S solution can deliver “35 percent higher performance, while ensuring cost savings with a 35 percent reduction in power consumption and a 75 percent reduction in software licensing costs when compared to lower GPU capacity servers.”

The reference architecture announced by Liqid solves a clear problem for customers focusing on AI, high performance computing (HPC), or other GPU-driven workloads. These customers need a way to deploy a large amount of GPU power, and in many cases are looking for a way to do so as quickly as possible. The new UltraStack solution provides a simple, efficient way to deploy a GPU-dense solution to power these workloads.

Disclosure: The Futurum Group is a research and advisory firm that engages or has engaged in research, analysis, and advisory services with many technology companies, including those mentioned in this article. The author does not hold any equity positions with any company mentioned in this article.

Analysis and opinions expressed herein are specific to the analyst individually and data and other information that might have been provided for validation, not those of The Futurum Group as a whole.

Other Insights from The Futurum Group:

SC23 Recap: Quantum

SC23 Recap: IBM

SC23 Recap: Nyriad

Author Information

Mitch comes to The Futurum Group through the acquisition of the Evaluator Group and is focused on the fast-paced and rapidly evolving areas of cloud computing and data storage. Mitch joined Evaluator Group in 2019 as a Research Associate covering numerous storage technologies and emerging IT trends.

With a passion for all things tech, Mitch brings deep technical knowledge and insight to The Futurum Group’s research by highlighting the latest in data center and information management solutions. Mitch’s coverage has spanned topics including primary and secondary storage, private and public clouds, networking fabrics, and more. With ever changing data technologies and rapidly emerging trends in today’s digital world, Mitch provides valuable insights into the IT landscape for enterprises, IT professionals, and technology enthusiasts alike.

Related Insights
Embeddable Contact
April 20, 2026

Twilio Flex as an Embeddable Contact Center: Will Platform Integration Redefine CX Sourcing for the Enterprise?

Twilio Flex's embeddable contact center capability intensifies CCaaS competition, offering enterprises deeper integration and AI-driven customization while challenging legacy providers....
Unlock Faster AI
April 20, 2026

Can Eridu’s AI Networking Break the Data Center Bottleneck—or Just Move It?

With 78% of organizations boosting AI budgets, Eridu emerges from stealth with $200M+ in funding, claiming to break the data center bottleneck—but whether new architectures solve the problem or just...
Cadence and NVIDIA
April 20, 2026

Cadence and NVIDIA Double Down on AI-Driven Engineering—Accelerated Computing Bridges Simulation and Verification

Cadence and NVIDIA have announced an expanded partnership embedding agentic AI and GPU acceleration into simulation and verification platforms, reshaping engineering productivity across RTL design, analog, and 3D IC workflows....
Hybrid Data
April 20, 2026

Can Cloudera’s Stability Bet Win the Hybrid Data War?

Cloudera's platform enhancements enable hybrid data environments with stability, elastic scaling, and Apache Iceberg interoperability, positioning the company to serve enterprises balancing cloud and on-premises infrastructure....
Meta’s MTIA Partnership With Broadcom Solidifies the Future of XPUs in Inference Optimization
April 20, 2026

Meta’s MTIA Partnership With Broadcom Solidifies the Future of XPUs in Inference Optimization

Brendan Burke, Research Director at Futurum, examines how the Meta Broadcom MTIA partnership expands custom AI silicon and tests whether multi-gigawatt infrastructure can scale efficiently....
Can Claude Opus 4.7 and Ensemble AI Models Finally Make Code Review Reliable?
April 18, 2026

Can Claude Opus 4.7 and Ensemble AI Models Finally Make Code Review Reliable?

CodeRabbit's ensemble AI code review system using Claude Opus 4.7 catches subtle bugs and race conditions that single-model systems miss, signaling a major shift in software quality assurance....

Book a Demo

Newsletter Sign-up Form

Get important insights straight to your inbox, receive first looks at eBooks, exclusive event invitations, custom content, and more. We promise not to spam you or sell your name to anyone. You can always unsubscribe at any time.

All fields are required






Thank you, we received your request, a member of our team will be in contact with you.