Scorpio Smart Fabric Switches

Fabric switches for the AI Era

Download Portfolio Brief

Purpose-built portfolio for deploying cloud-scale AI platforms at unprecedented pace and scale

Improve energy efficiency with maximum performance per watt fabric solutions
Increase GPU utilization with predictable, secure and high-performance data flows
Maximize server uptime with COSMOS delivering unprecedented data center observability
Reduce time to market with flexible software-defined architecture and seamless interoperability

Why Use Scorpio Smart Fabric Switches?

Maximize Utilization

High Performance Data Ingest

With PCIe 6 support and AI-optimized architecture, Scorpio P-Series delivers maximum predictable performance to increase GPU utilization
High Performance Scale-up

With a software-defined architecture, Scorpio X-Series delivers protocol and performance optimization for increased data transfer efficiency
Performance Monitoring

Real-time telemetry data provides valuable insights to optimize performance and improve utilization

Ease-of-Use

Purpose-built Board Design

Small package size with integrated power supply decoupling to enable easier routing
Future-proof

Mix current and next-generation devices on the same platform
Seamless Software Integration

Common COSMOS APIs enable Scorpio to integrate seamlessly into existing infrastructure management solutions that use the widely-deployed Aries Retimers

Increase Uptime

Fleet Management

COSMOS software with deep telemetry and diagnostics for link and device health monitoring enables unprecedented data center observability
Quick Debug

Built-in protocol analyzer with link state history and timestamps, full non-destructive eye scan for RX Lane margining, self-test features to minimize link downtime and accelerate fault isolation
Rigorous Interop Testing

System testing with diverse ecosystem of PCIe hosts and endpoints in our Cloud-Scale Interop Lab minimizes interoperation risk for improved reliability

P-Series and X-Series

Application-specific products built from the ground up for AI servers and AI clusters

Architected for mixed traffic AI head node connectivity (GPU-to-CPU/NIC/SSD)

Industry’s first PCIe 6 fabric switch
Predictable and high-performance GPU-to-CPU/NIC/SSD data flows
High bandwidth and low latency peer-to-peer for GPU data ingest
Interoperability with diverse ecosystem of PCIe hosts and endpoints

Architected to deliver highest back-end bandwidth for AI scale-up (GPU-to-GPU)

Software-defined architecture enables flexibility for diverse AI accelerators
Platform-specific customization for homogeneous GPU scale-up fabrics
Protocol and performance optimization for increased data transfer efficiency
Expanded reliability and telemetry features for maximum uptime

Use Cases

Resources

First Look Demo: Scorpio X-Series Fabric Switch

Scorpio X-Series Fabric Switches are architected to deliver the highest back-end bandwidth for AI scale-up.

Optimizing NVIDIA MGX Platforms with Scorpio

See Scorpio Smart Fabric Switches in action with a PCIe® 6-ready NVIDIA Blackwell-based MGX™ platform.

End-to-End PCIe 6 Interop with NVIDIA Blackwell

Industry-first end-to-end PCIe 6 interop demo with Scorpio Smart Fabric Switches, Aries Smart Retimers, and NVIDIA Blackwell.

Combating Noisy Neighbors with Scorpio P-Series Fabric Switches

How We Test – Scorpio

Scorpio Smart Fabric Switches undergo interoperability and stress testing with a wide range of PCIe 6.x hosts and endpoints.

Accelerating the PCIe 6.x Ecosystem: Industry-First PCIe 6.x Interop Demonstration at DesignCon

AI Demands Purpose-Built Solutions

Learn how Scorpio P-Series Fabric Switches maximize GPU utilization with unparalleled performance, reliability, and scale.

Accelerating the PCIe 6 Ecosystem

See the first public demo of end-to-end interoperability between Astera Labs’ Scorpio P-Series Switch and Micron’s PCIe 6 Data Center SSD for ecosystem…

End-to-End PCIe 6 Live Demo at OCP Summit 2024

See the industry’s first end-to-end PCIe 6 live demo at OCP Global Summit, featuring Scorpio Smart Fabric Switches.

Scorpio First Look Demo

See the first demonstration of Scorpio Smart Fabric Switches showcasing a real-world AI server configuration.

Scaling AI with Astera Labs’ Smart Fabric Switch Portfolio

Listen in as Jitendra Mohan and Thad Omura discuss with Moor Insights how Scorpio Smart Fabric Switches are changing the game for AI infrastructure.

Introduction to Scorpio Smart Fabric Switches

Astera Labs unveils its Scorpio Smart Fabric Switch portfolio built from the ground up for demanding AI workloads.

Overcome Next-Gen AI Infrastructure Challenges with Scorpio Smart Fabric Switches

Building the Case for UALink™: A Dedicated Scale-Up Memory Semantic Fabric

Astera Labs’ Vision for the AI Era

Astera Labs’ co-founders share how the company is expanding its market opportunities with Scorpio Smart Fabric Switches.

Driving AI and Cloud Innovation: How Astera Labs is Expanding its Market Opportunity

Ordering Information

Series	Part #	PCIe	Lanes	Package Size [mm]	Status
P-Series	PF60641L	6.x	64	29×29	Pre-Production
P-Series	PF50641L	5.x	64	29×29	Pre-Production
P-Series	X6064-1M04	Xami MCIO-MCIO Evaluation Kitt				Pre-Production
X-Series	Customer Specific						Contact Us

How Your Hyperscale Data Center Can Overcome the Challenges of Next-Gen AI Infrastructure with Scorpio Smart Fabric Switches

Request the White Paper

Download

Breaking the 100 GB/s Barrier: Astera Labs and Micron Demonstrate Production-Ready PCIe 6 Storage Performance at FMS 2025

The future of AI infrastructure arrived at the Future of Memory and Storage (FMS) 2025 conference, where Astera Labs and Micron achieved a groundbreaking milestone: over 100 GB/s of sustained throughput using production-ready PCIe 6 technology. This industry-first demonstration represents a transformative advancement in AI storage performance, featuring four Micron 9650 PCIe Gen6 SSDs and…

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

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…

Astera Labs at OCP APAC Summit: Advancing Open AI Infrastructure 2.0 Through Rack-Scale Connectivity

As AI training clusters scale to 200,000+ GPUs, traditional server architectures require a fundamental paradigm shift to handle this unprecedented scale. Join Astera Labs at the OCP APAC Summit, August 5-6 in Taipei, as we put a spotlight on the transition to AI Infrastructure 2.0—where the rack is replacing the server as the new unit of compute.This transformation isn’t just evolutionary—it’s…

Astera Labs Announces Financial Results for the Second Quarter of Fiscal Year 2025

Record quarterly revenue of $191.9 million, up 20% QoQ and 150% YoY, and record operating cash flow generation of $135.4 millionIndustry leading PCIe 6 connectivity portfolio ramping in volume on customized rack-scale AI systemsScorpio Fabric Switch design wins expand across multiple new customers and applicationsSAN JOSE, CA, U.S. – August 5, 2025 – Astera Labs, Inc. (Nasdaq:…

Astera Labs Opens New Global Headquarters in San Jose to Accelerate AI Infrastructure Innovation

900-employee campus powers Astera Labs’ mission to usher in the rack-scale computing eraSAN JOSE, Calif.– July 18, 2025 – Astera Labs, Inc. (Nasdaq: ALAB), a provider of semiconductor connectivity solutions for AI and cloud infrastructure, today announced the opening of its new corporate headquarters in San Jose, California. Designed to accommodate up to 900 employees, the new…

Astera Labs Announces Conference Call to Review Second Quarter 2025 Financial Results

SAN JOSE, Calif., July 08, 2025 — Astera Labs, Inc. (Nasdaq: ALAB), a global leader in semiconductor-based connectivity solutions for AI and cloud infrastructure, today announced that it will release its financial results for the second quarter 2025 after the close of market on Tuesday, Aug. 5, 2025. Astera Labs will host a corresponding conference call at 1:30 p.m. Pacific Time, 4:30…

Astera Labs and Alchip Announce Strategic Partnership to Advance Silicon Ecosystem for AI Rack-Scale Connectivity

Hyperscalers benefit from seamless integration of purpose-built compute and connectivity solutions to rapidly deploy AI infrastructure at scale– SANTA CLARA, Calif. and TAIPEI, Taiwan – June 16, 2025 – Astera Labs, a leading provider of purpose-built connectivity solutions for AI and cloud infrastructure, and Alchip Technologies, the high-performance ASIC leader, today announced a…

Accelerate AI with Real-World CXL Platforms

We’ve collaborated with SMART Modular Technologies to showcase our Leo CXL Smart Memory Controller in a real-world setup that delivers up to 2TB of additional CXL memory using SMART Modular CXL cards.In the demo, we ran a series of Large Language Model inferencing tasks with FlexGen. Using CXL, the demo achieved 5.5x higher throughput and 90% GPU utilization. The demo also showcased COSMOS…

Boost AI with 100+ GB/s PCIe 6

Building on our successful DesignCon 2025 demonstration with Micron that achieved 54 GB/s with two SSDs, we’ve now scaled to four Micron 9650 PCIe Gen6 SSDs with three Scorpio P-Series Fabric Switches to achieve over 100 GB/s aggregate performance. This marks another step in expanding PCIe 6 adoption as Astera Labs continues to validate interoperability across an increasing range of endpoints,…

Demo: COSMOS Developer Kit Diagnostics Tools

Astera Labs’ COSMOS Developer Kit provides user-friendly test and debug capabilities that accelerate validation workflows. The Developer Kit supports device, discovery, configuration, security attestation, firmware updates, scripting, and automation, making it a versatile solution for system designers and integration.