Aria Networks, Inc.

Last chance to experience @AriaNetworks✨ at #OFC! It’s been an incredible week of conversations and connections. If you haven’t stopped by yet — or want one more look — this is your moment. Don’t miss us on the final day. Where you can find us: @Broadcom booth #4601 @amphenol booth #949 @commbroad Hyper Photonix booth #449

Finding us at #OFC26 this week: Not hard. 💪🏻 Three booths. One team. Zero shortage of things to talk about. Come see @AriaNetworks at Broadcom (booth #4601), Amphenol (booth #949), and Hyper Photonix (booth #449). Los Angeles. Next week. Say hi. 👋🏻 ofcconference.org

Today we celebrate International Women's Day and the women whose ideas, leadership, and innovation move our industry forward. At @AriaNetworks, we are proud to work alongside talented women who challenge assumptions, solve complex problems, and help shape the future of technology. Thank you for the impact you make every day!

Another day in the life at @AriaNetworks! Today’s install: bringing up our 1.6Tb/s system powered by @Broadcom's Tomahawk® 6 (TH6) chipset for a customer with our white-glove deployment service. From rack and stack to configuration and validation, our team ensures everything is running smoothly from day one. Nothing beats seeing cutting-edge infrastructure get into the hands of our customers.

The decades-old model of networking is colliding with the extreme requirements of AI. "Networks that Think" require more than just software; they require a specialized foundation of optimized hardware and fine-grained telemetry. We invite you to join us at @ofcconference in Los Angeles to experience the next generation of AI networking. Come experience our 1.6Tb/s systems powered by @Broadcom's Tomahawk® 6 (TH6) chipset. Where to find us: -@Broadcom booth 4601, West Hall (The 1.6T TH6 Showcase) -@commbroad Hyper Photonix booth 449, South Hall -@amphenol booth 949, South Hall See you there!

Day in the life at @AriaNetworks - shipping our TH6 switch to a customer! @mansourkaram @Broadcom

We’re proud that @AriaNetworks is now officially certified by @AMD to support the AMD Pensando Pollara 400 AI NIC. For organizations building AI infrastructure on AMD, this means Aria is a validated option for deploying Pollara 400 at scale. Our platform helps maximize GPU utilization while preserving the flexibility of an open, Ethernet-based architecture. This certification reflects rapid progress in our technology and execution. We are focused on delivering production-ready networking for demanding AI environments, not future promises. If you are building with AMD and evaluating how to scale AI workloads efficiently and credibly, Aria should be part of that conversation. docs.amd.com/r/en-US/xapp14…

AI is forcing a reset in data center networking. Scale, performance, and real-time visibility are no longer nice-to-haves, they are table stakes. As @DellOroGroup puts it: “The AI era is driving a fundamental shift in data center networking, with 1.6T Ethernet emerging as the new industry standard. As AI back-end networks demand unprecedented scale, performance, and real-time visibility, open and interoperable architectures are no longer optional. Aria Networks' portfolio directly addresses this industry inflection by pairing 102.4 Tbps standard Ethernet with advanced telemetry to deliver the scale, performance, and openness required for the next generation of AI infrastructure.” - @Samehbj This is exactly the inflection point Aria is building for. Our latest announcement expands the Aria portfolio with 1.6Tb/s systems powered by @Broadcom Tomahawk®, combining standard Ethernet, massive scale, and telemetry-first design. Read the full story on what this shift means for your next-generation AI clusters 👇 arianetworks.com

“With the launch of its 102.4Tbps portfolio, Aria is solving the AI connectivity bottleneck.” — @dylan522p, Founder of @SemiAnalysis_ By pairing standard Ethernet with the performance of Broadcom's Tomahawk® 6 and a telemetry-centric software architecture, we are laying the groundwork for the next generation of AI clusters. More detail here 👇 arianetworks.com

"Proprietary fabrics are a thing of the past. With its 1.6 Tbps launch, combined with a telemetry-centric software architecture, Aria Networks is proving that the highest-performance AI networks on the planet are being built on a foundation of open, scalable Ethernet such as Broadcom's Tomahawk 6 switch series." -Hasan Siraj, Vice President of Product Marketing, Core Switching Group, @Broadcom Read the full story by @mansourkaram here: arianetworks.com/blog/th6-annou…

Doesn't seem all that long ago that intent-based networking was all the rage. Today of course it's all about AI ... @AriaNetworks is targeting AI scale-out with a microsecond telemetry approach. networkworld.com/article/409522…

AI is pushing networking past its limits. Today, we’re raising the bar. We’re excited to announce that Aria Networks is expanding its hardware portfolio with 1.6Tb/s systems powered by @Broadcom's Tomahawk ® 6. This marks a major step forward in building Networks that Think™. Over the past year, the industry has shifted decisively from cost-optimized cloud networking to performance-optimized AI clusters. The requirements of large-scale AI are colliding with decades-old networking assumptions and the takeaway is clear: software alone isn’t enough. At Aria, we believe the future of AI networking is built on three pillars: • Standard, interoperable Ethernet not proprietary fabrics • Accelerator-agnostic design so infrastructure investments last • Modular systems at massive scale, optimized through telemetry-first software and domain-native AI With our Tomahawk 6–based 1.6Tb/s systems, we’re extending this architecture to support the next generation of AI clusters — from gearbox-free 800G deployments to liquid-cooled 200G SerDes at extreme density. This isn’t about chasing peak specs. It’s about delivering networking that scales reliably to tens of thousands of accelerators, performs in real production environments, and stays flexible as the AI ecosystem evolves. The journey to Networks that Think is accelerating — and today’s announcement is a meaningful step forward. Learn more on our website - arianetworks.com @mansourkaram

Beyond Intent—I explain why real-time network optimization for AI workloads demands a new architecture. See you at #Supercomputing25 @Broadcom Booth #935! @AriaNetworks #NetworksThatThink #SC25 #IntentBasedNetworking linkedin.com/pulse/beyond-i…