AMD Networking

Official Twitter handle for AMD networking solutions.

[AMD Networking @AMDNetworking]

Scaling AI is not just about adding GPUs.

AMD Pensando Pollara 400 AI NICs give Crusoe's AMD Instinct MI355X GPU instances the high-bandwidth networking needed to support demanding multi-node AI workloads.

Read more ⬇️

[Crusoe @CrusoeAI]

We were one of the first cloud providers to virtualize @AMD Instinct™ MI355X GPUs. Here's what it actually took:

❌ RCCL routing through the wrong interface
❌ GPU memory reg failing (ib_peermem is gone in kernel 6.8+)
❌ PCIe topology flattened by Cloud Hypervisor

✅ 368 GB/s all-reduce. Zero errors. Nice work @shubh_chakrawar and Andrew Carp.

Full debug walkthrough: https://t.co/pPXhldGoIa

#GPUCompute #CloudInfrastructure #AMD #ROCm

[AMD Networking @AMDNetworking]

As AI scales across hundreds of GPUs, communication becomes critical to performance. Enter AI networking.

In our new blog “What is AI Networking?”, we break down how it enables efficient, scalable AI infrastructure.

Learn more: https://t.co/5eDGLnZqAC

[AMD Networking @AMDNetworking]

As AI clusters scale, network congestion and tail latency limit efficiency.

Learn how the AMD Pensando Pollara 400 AI NIC overcomes these limitations with higher cluster uptime and better RCCL performance.

Read the product guide now: https://t.co/MhjZ25X0Wr

[AMD Networking @AMDNetworking]

Networking is the backbone of scalable AI.

@Dell + AMD Pensando Pollara 400 AI NIC deliver a programmable Ethernet solution that accelerates AI workloads and adapts to evolving standards.

Explore the full ecosystem: https://t.co/jX9Yb72H1Z

[AMD Networking @AMDNetworking]

In the modern data center, CPUs and GPUs have been getting all the attention. Discover how Data Processing Units (DPUs) are reshaping modern infrastructure in our blog: https://t.co/Yv0ED2WDqM

[AMD Networking @AMDNetworking]

“Together, AMD and @Cisco can drive superior performance across frontend and backend environments—proving the power of an open Ethernet for AI.”

Cisco + AMD Pensando Pollara 400 AI NIC deliver intelligent, programmable solutions for complex AI tasks: https://t.co/jL3mb3YOUu

[AMD Networking @AMDNetworking]

NICs, such as the AMD Pensando Pollara 400 AI NIC, empower efficient scale-out fabrics with intelligent load balancing and congestion management.

Explore more on the role of NICs in AI infrastructure in @esg_global’s newest analyst paper: https://t.co/vixtdd2gbW

[AMD Networking @AMDNetworking]

For 10+ years, AMD Solarflare™ solutions have set the standard for ultra-low latency networking.

The AMD Solarflare™ X4 Series pushes performance for HFT and beyond — when every sub micro-second matters: https://t.co/kQQ583eFNW

[AMD Networking @AMDNetworking]

AI workloads are massive and traditional Ethernet can’t keep up.

AI NICs enable faster, more reliable GPU-to-GPU communication, reducing latency and improving scalability for generative AI and LLM training. https://t.co/jOl4B6mPQX

[AMD Networking @AMDNetworking]

Introducing AMD Pensando Pollara 400 AI NIC–Ready Server Platforms, built with leading OEM/ODM partners.

Together, we’re enabling high-performance AI networking for training & inference at scale. Learn more: https://t.co/TUSdF2YqmU

[AMD Networking @AMDNetworking]

The AMD Pensando Pollara 400 AI NIC keeps data flowing efficiently by intelligently retransmitting only lost or corrupted packets to save time, help reduce bandwidth usage, and speed up job completion.

It is built for demanding AI and ML workloads: https://t.co/gLD80KPnR9

[AMD Networking @AMDNetworking]

The AMD Pensando Pollara 400 AI NIC uses UEC-ready RDMA to intelligently manage out-of-order packet arrivals. Data hits the GPU in sequence, keeping throughput high and tail latency low, all without taxing the CPU/GPU.

Learn more: https://t.co/gLD80KPnR9

[AMD Networking @AMDNetworking]

The AMD Pensando Pollara 400 AI NIC is now available in a standard Open Compute Project (OCP) 3.0 compliant form factor. Enabling scaling out with OCP-based AI infrastructure.

See how AMD is bringing Ethernet designed for AI to OCP Data Centers: https://t.co/3l84clCEyy

[AMD Networking @AMDNetworking]

Introducing the AMD Solarflare X4 Ethernet Adapter — purpose-built for high-performance electronic trading. Engineered for ultra-low latency and real-time telemetry.

Explore how it’s changing the game: https://t.co/ortFrux2pN

[AMD Networking @AMDNetworking]

Reliability, performance, and security top the list when choosing networking protocols for generative AI clusters, per ESG’s latest report.

See how the AMD Pensando™ Pollara 400 AI NIC meets these demands. https://t.co/ZJmYqunC9n

[AMD Networking @AMDNetworking]

The AMD Pensando™ Pollara 400 AI NIC brings adaptive packet spraying to AI workloads, helping cut latency, boosting bandwidth, and eliminating the need for lossless networks. Simplified ops, powerful performance. https://t.co/N0W4nFB4t9

[AMD Networking @AMDNetworking]

With nearly 90% of organizations leveraging or planning to deploy Ethernet for their AI clusters, Ethernet-first NICs are critical. The AMD AI NIC™ is UEC-ready and designed to meet the demands of the future. Read more in a new analyst paper here: https://t.co/ZJmYquo9YWith nearly 90% of organizations leveraging or planning to deploy Ethernet for their AI clusters, Ethernet-first NICs are critical. The AMD AI NIC™ is UEC-ready and designed to meet the demands of the future. Read more in a new analyst paper here: https://t.co/ZJmYquo9YWith nearly 90% of organizations leveraging or planning to deploy Ethernet for their AI clusters, Ethernet-first NICs are critical. The AMD AI NIC™ is UEC-ready and designed to meet the demands of the future. Read more in a new analyst paper here: https://t.co/ZJmYquo9YWith nearly 90% of organizations leveraging or planning to deploy Ethernet for their AI clusters, Ethernet-first NICs are critical. The AMD AI NIC™ is UEC-ready and designed to meet the demands of the future. Read more in a new analyst paper here: https://t.co/ZJmYquo9YV

[AMD Networking @AMDNetworking]

Discover the intelligent capabilities of the AMD Pensando™ Pollara 400 AI NIC and how intelligent packet spray, selective retransmission, and congestion control can help reduce latency in large networks: https://t.co/LvOGocgc0G

[AMD Networking @AMDNetworking]

Microsoft Azure VTAP are now powered by AMD Pensando™ DPU technology for more secure, high-speed traffic mirroring and analysis. Learn more: https://t.co/5D0mupiV87

[StorageReview.com @storagereview]

AMD has launched the Pensando Pollara 400, the first fully programmable AI NIC. With 400Gbps throughput, PCIe Gen5, and support for UEC standards, it’s built to eliminate AI networking bottlenecks.
https://t.co/otaI9enRBC
#AI #Networking #AMD #GPU #DataCenter @AMDServer