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

Cosmos Platform Logo – Astera Labs Developer Ecosystem for CXL Products

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

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

Supercharging Agentic AI: How Leo X-Series Smart Memory Controllers Accelerate Inference With KV Cache Offload

In the early days of chat-based LLMs, the memory wall was driven by linear context growth. For each individual inference workload, expanding context length pushed available memory demand beyond capacity.But we are now in the agentic era. Agentic workloads operate on dynamic loops: They generate reasoning tokens, call external tools and APIs, parse returned data, and append state updates… Read more

The Ecosystem of Optical Fiber-to-Chip Connectors: Building Blocks of NPO and CPO for Scale-Up AI

We’ve been framing the increasing adoption of optical connectivity for scale-up applications with a clear organizing principle: Copper where you can, optics where you must. At today’s per-lane signaling rates in rack-scale AI fabrics, “must” is moving inside the rack. The reach and loss budgets available to passive copper compress with every protocol generation, and a growing number of… Read more

Seven Years Later: 200G Ethernet Retimers vs. Redrivers

Seven years ago, I wrote about the eye-popping difference between retimers and redrivers. The central point was that a redriver boosts an impaired signal, while a retimer recovers the data, extracts the embedded clock, and retransmits a fresh copy of the data on a clean clock. That distinction is still accurate and directly influences design decisions; but it’s not the only factor!On… Read more

Astera Labs Bolsters Leo Smart Memory Controller Family for Agentic AI and General-Purpose Cloud Workloads

As high-value AI applications drive explosive memory-footprint growth amid tight supply, new connectivity architectures enhance optimal memory utilization and reuseHighlightsNew Leo X-Series optimizes token economics: Paired with Astera Labs’ Scorpio X-Series Fabric Switches, Leo X-Series enables fabric-attached memory for long-context, KV-cache-intensive workloads. Platform-specific… Read more

Astera Labs Reports Second Quarter 2026 Financial Results

Record quarterly revenue of $392.4 million, up 27% QoQ and up 104% year-over-yearQ2 revenue strength reflects diversified growth across AI fabrics and signal conditioningQ3 revenue inflection to be driven by Scorpio™ X-Series 320-lane fabric switch production ramp SAN JOSE, CA, U.S. – August 4, 2026 – Astera Labs, Inc. (Nasdaq: ALAB), a leader in semiconductor-based connectivity… Read more

Astera Labs Expands Taurus Family with Industry’s First OCP-Standard Footprint Compatible 3.2T Smart Retimers and Smart Redrivers

Unified COSMOS stack helps customers accelerate time to market with real-time link observability and advanced diagnostic featuresNews Highlights:Expanded Taurus family adds 3.2T Ethernet Smart Retimers and Smart Redrivers for scale-up and scale-out AI infrastructure.Sampling industry-first Smart Retimers and Smart Redrivers built on the OCP Signal Conditioner Standard Footprint…. Read more

Astera Labs Expands Taiwan Operations to Accelerate Global AI Infrastructure Buildout

Expanded Cloud-Scale Interop Lab and growing engineering presence to strengthen AI system integration with leading AI platform providers and Taiwan system manufacturersTAIPEI, Taiwan—June 3, 2026—Astera Labs, Inc. (Nasdaq: ALAB), a leader in semiconductor-based connectivity solutions for rack-scale AI infrastructure, today announced a significant expansion of its Taiwan operations… Read more

First Look: Expanded Leo Smart Memory Controller™ Family

See the new X-Series for fabric-attached KV cache offload and the Leo 2 E-Series and P-Series for CXL 3.2 expansion, pooling, and sharing. Read more

First Look: Taurus Smart Signal Conditioners

As AI scale-up networks move to 200G per lane, signal integrity and reach extension become critical design challenges. Astera Labs solves this challenge with the introduction of its fourth generation of Taurus Smart Signal Conditioners – our new 3.2T family of Retimers and  Redrivers for on-board Ethernet, UALink™, and ESUN scale-up connectivity.Taurus is the industry’s first signal… Read more

Accelerating the NVIDIA NVLink Fusion Ecosystem: How Astera Labs and NVIDIA are Bringing the Vision to Life

Join Thad Omura and Kishore Atreya for an engaging fireside chat on the NVIDIA NVLink Fusion ecosystem. Dive into how NVLink Fusion is redefining accelerator connectivity and discover how Astera Labs is enabling the ecosystem with purpose-built, high-performance solutions. This forward-looking conversation offers valuable insights for technology leaders, architects, and anyone building the… Read more