Scorpio Smart Fabric Switch

Scorpio™ X-Series 320 Lanes

Largest Open, Memory-Semantic Fabric Switch
for AI Scale-up

Download Family Brief

Scorpio™ P-Series

Broadest Family of PCIe 6 Fabric Switches
32 to 320 Lanes

Download Family Brief

Purpose-built AI fabric switches

  • Scorpio X-Series 320 Lane: Largest Open, Memory-Semantic Fabric Switch
  • Scorpio P-Series 32 to 320 Lane: Broadest Portfolio of PCIe 6 Fabric Switches

Benefits

  • Simplify large scale-up topologies and improve performance with single-hop latency
  • Maximize token economics with Hypercast™ and In-Network Compute engines
  • Improve efficiency with memory-semantic based open and platform-specific protocols
  • Optimize operational resilience and platform performance with COSMOS software
  • Scale compute capacity with diverse accelerator optionality and system topologies

Scorpio Highlights

Intelligent AI Fabric switches engineered to maximize token economics

Boost Collective Operations

With Hypercast™ and In-Network Compute engines

High-radix, Single-hop Scale-up

Many parallel switches maximize GPU bandwidth

Platform Performance Optimization

Software stack enhanced beyond fleet management

Why Use Scorpio Smart Fabric Switches?

Purpose-built for the demands of production AI at scale

Performance

  • Optimize Fabric Efficiency

    Memory-semantics enables accelerators to access resources through native load/store operations and eliminates software overhead

  • Maximize Tokens per Watt

    High-radix switch simplifies scale-up topologies, cutting hops and reducing end-to-end latency across the cluster with lower power

  • Improve Time to First Token

    Intelligent fabric with hardware-accelerated Hypercast™ and In-Network Compute engines accelerate collective operations by up to 2x

Scalability

  • Deploy Larger Clusters

    Largest open, memory-semantic fabric switch, Scorpio X-Series supports increased cluster sizes with up to 80 accelerators per switch

  • Increase Compute Capacity

    Broadest family of PCIe 6 fabric switches, spanning 32 to 320 lanes, Scorpio P-series enables flexibility to rapidly scale across diverse topologies

  • Enable Optionality

    Software-defined architecture designed for open and platform-specific protocols to support diverse accelerators and AI platforms

Resilience

  • Maximize Rack Uptime

    Comprehensive failure isolation, non-disruptive firmware updates, and integration into OpenBMC management

  • Accelerate Deployment

    In-depth signal, link, and packet diagnostics provide end-to-end protocol visibility to accelerate debug and improve serviceability

  • Deploy with Confidence

    Rigorous testing with diverse PCIe hosts and endpoints in Cloud-Scale Interop Lab minimizes deployment risk and accelerates time-to-market

Scorpio Smart Fabric Switch Family

Fabric Switches built from the ground up for AI clusters and servers

Scorpio X-Series 320 Lane: Largest open, memory-semantic fabric switch

  • Hardware-accelerated Hypercast™ and In-Network Compute engines
  • High-radix enables rack-scale, low latency, accelerator clusters
  • Platform-specific protocol, performance, and resilience customization

Scorpio P-Series 32 to 320 Lanes: Broadest Family of PCIe 6 fabric switches

  • Optimize AI connectivity with right-sized fabric switches
  • Predictable and high-performance GPU-to-CPU/NIC/SSD data flows
  • Interoperable with a diverse ecosystem of PCIe hosts and endpoints

Example Topologies

High Radix, Multi-level Switch Scale-up

Scorpio X-Series 320 Lane: Expand GPU scale-up with multi-level switching fabric

High Radix, Single-hop Switch Scale-up

Scorpio X-Series 320 Lane: Many parallel switches maximize GPU bandwidth with single-hop latency

16 GPU AI Server

Scorpio P-Series 320 Lane: Maximize performance with single hop latency to all 16 GPUs

8 GPU AI Server

Scorpio P-Series 320 Lane: All-to-all bandwidth across all 8 GPUs and devices with a single switch

8 GPU AI Server

Scorpio P-Series 160 Lane: High bandwidth GPU connectivity with optional switch-to-switch ports

8 GPU AI Server

Scorpio P-Series 64 Lane: High performance GPU to NIC scale-out with modular server design

KV Cache Storage Disaggregation

Scorpio P-Series 160/320 Lane: Increase inference performance with disaggregated KV Cache appliance

Scale-Out NIC/GPU Optionality

Scorpio P-Series 48/64 Lane: High performance GPU-to-NIC peer-to-peer for diverse applications

Front-end NIC Data Ingest

Scorpio P-Series 48/64 Lane: High performance data ingest and storage fanout

Resources

Ordering Information

SeriesPart #ProtocolLanesPackage Size [mm]
X-SeriesPlatform Specific up to 320 Lanes – Contact Sales
P-SeriesPF63201LPCIe 632062.5×62.5
P-SeriesPF61601LPCIe 616045×45
P-SeriesPF60641LPCIe 66429×29
P-SeriesPF60481LPCIe 64821×21
P-SeriesPF60321LPCIe 63221×21
P-SeriesPF50641LPCIe 56429×29

Why Your Mixture-of-Experts Model Is Only as Good as Your Fabric

Introducing Hypercast™ for Improved Intelligence Benchmarks and Tokens-Per-Watt Performance

 

 

Read the Blog

Why Your Mixture-of-Experts Model Is Only as Good as Your Fabric

Introducing Hypercast™ for Improved Intelligence Benchmarks and Tokens-Per-Watt PerformanceThe more capable you make a frontier AI model, the harder it becomes to run. More parameters, more experts, more sophisticated routing: every architectural improvement that lifts benchmark scores also lifts the communication demands on the hardware connecting compute accelerators such as GPUs…. Read more

Bridge the PCIe 6 Transition Without Requalifying Your NIC Fleet

How Aries 6 PCIe Smart Gearbox enables hyperscalers to scale I/O for AI workloads while preserving qualified PCIe 5 frontend NIC infrastructureAI Infrastructure Is Outgrowing Yesterday’s I/O ArchitectureAI training and inference workloads don’t just demand faster GPUs—they demand faster systems. As model sizes and datasets explode, every critical path matters: moving data into… Read more

What NVIDIA GTC 2026 Said About the Future of AI Connectivity

NVIDIA GTC has always been a window into where the AI Infrastructure industry is heading. This year, what that window revealed was a compute layer fragmenting, deliberately and by design. Jensen Huang’s keynote introduced not one new architecture but several: Vera Rubin for high-throughput GPU compute, the Groq LPU integrated as a decode accelerator for latency-sensitive inference, and a… Read more

Astera Labs Extends Leadership in Open, AI Scale-Up Networking with New 320 Lane Scorpio X-Series Smart Fabric Switch

Now Shipping to Leading Hyperscalers, Scorpio Smart Fabric Switch Family Delivers Breakthrough Accelerator Utilization Through Memory-Semantic Based Open and Platform-Specific ProtocolsNews Highlights:Largest open, memory-semantic fabric switch: The Scorpio™ X-Series 320 Lane AI fabric switch, shipping today, supports increased scale-up cluster sizes with low latencyIntelligent… Read more

Astera Labs Reports First Quarter 2026 Financial Results

Record quarterly revenue of $308.4 million, up 14% QoQ and up 93% year-over-yearMarket-leading PCIe 6 AI fabric and signal conditioning portfolio delivered strong growth during Q1Now shipping newly announced Scorpio™ X-Series 320-lane AI Fabric switch and expanded Scorpio P-Series PCIe 6 switch family supporting 32 to 320 lanesSAN JOSE, CA, U.S. – May 5, 2026 – Astera Labs,… Read more

Astera Labs Announces Conference Call to Review First Quarter 2026 Financial Results

SAN JOSE, CA, U.S. – April 2, 2026 – Astera Labs, Inc. (Nasdaq: ALAB), a leader in semiconductor-based connectivity solutions for rack-scale AI infrastructure, today announced that it will release its financial results for the first quarter 2026 after the close of market on Tuesday, May 5, 2026. Astera Labs will host a corresponding conference call at 1:30 p.m. Pacific Time, 4:30… Read more

Astera Labs Reports Fourth Quarter and Full Year 2025 Financial Results

Record quarterly revenue of $270.6 million, up 17% QoQ, and record full-year revenue of $852.5 million, up 115% year-over-yearBroadening Scorpio X-Series smart fabric roadmap to address expanding scale-up market opportunities supporting multiple customers, starting production ramp for lead platformAppointed Desmond Lynch as Chief Financial Officer with Mike Tate transitioning to the… Read more

Scorpio X-Series 320 Lane: Largest Open, Memory-Semantic Fabric Switch

Get your first look at the new Scorpio™ X-Series 320-Lane AI Fabric Switch! The frontier models driving today’s most demanding AI applications require connectivity infrastructure that keeps pace with the accelerators powering them.High-radix AI fabric switch replaces multiple legacy switches to enable larger scale-up cluster sizes in a single hop and reduce overall latencyHardware-accelerated… Read more

Scorpio P-Series 32 to 320 Lane: Broadest Family of PCIe 6 Fabric Switches

As GPU clusters scale for frontier AI, the fabric matters. Performance, scalability, and resilience all depend on how CPUs, GPUs, NICs, storage, and memory connect—and that connection is PCIe. This is exactly what Scorpio™ P-Series Fabric Switches are built for. Introducing the expanded Scorpio P-Series PCIe fabric switch family—now spanning 32 to 320 lane configurations—designed… Read more

Extending Reach of Scale-out Networks for AI Clusters

See our latest demo where our Scorpio P-Series Fabric Switches connect NVIDIA H200 GPUs and ConnectX-8 NICs – running real NCCL-based training workloads at max data rates. Our Taurus Ethernet-enabled AECs then extend reach up to 7m with full interoperability with NVIDIA Spectrum-X for switch-to-switch and ConnectX-8 for switch-to-NIC connectivity at 800G per linkLearn how this demo delivers:✅… Read more