Aries PCIe® Smart Gearbox

Industry’s First Purpose-Built PCIe Gearbox

Download Portfolio Brief

Industry’s first PCIe 6 Gearbox Portfolio

Intelligently bridges the performance gap between cutting-edge PCIe 6 and established PCIe 5 ecosystems for maximum data throughput

  • Solves bandwidth bottlenecks that arise when integrating the latest PCIe 6 with existing PCIe 5 infrastructure
  • Optimizes PCIe lane utilization and reach-extension for demanding AI workloads and cloud-scale deployments
  • Ensures a reliable, scalable, and customizable interconnect solution for diverse cloud environments, maximizing I/O bandwidth
  • Comprehensive solution, complete with COSMOS software suite for advanced Link, Fleet & RAS telemetry & diagnostics

Nothing Out of Reach

Nothing out of reach aries smart gearbox highlighted

Aries Smart PCIe Gearbox Highlights

Bridging a Multi-Generational PCIe Ecosystem

Increase effective CPU or GPU lanes by

When attaching PCIe 6 devices with PCIe 5 devices, reducing TCO

Robust Signal
Integrity

64GT/s PAM4 SerDes and DSP customized for demanding AI server channels

Enhanced Diagnostics
& Telemetry

Cosmos Platform Logo – Astera Labs Developer Ecosystem for CXL Products

Extended capabilities through
in-band and out-of-band management

Why Use Aries Gearbox

Enhanced portfolio with years of learnings from cloud-scale deployments

Maximize Throughput

  • Flexible Protocol

    Supports a comprehensive range of PCIe rates (64 GT/s to 2.5 GT/s) ensuring full utilization of all available PCIe lanes in mixed-generation setups

  • Seamless Protocol Translation

    Enables efficient 1-to-1 communication between the latest PCIe 6 (Flit-Mode) and older PCIe 5 (Non-Flit-Mode) devices, ensuring maximum data transfer rates are maintained across the interconnected ecosystem

  • Extended Reach

    Advanced long-reach SerDes maintains signal integrity and performance across high-loss channels, maximizing bandwidth over extended distances

Quick Deploy

  • Purpose-built Design

    Small package footprint with flexible clocking modes simplify routing and reduce solution size

  • 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

  • SW-defined Architecture 

    COSMOS with Aries software-defined architecture adjusts protocol and state transitions to support open and diverse PCIe ecosystem

Increase Uptime

  • Deep Diagnostics

    Advanced Error Reporting (AER) and FW driven link health monitoring to alert system of any possible link performance issues

  • Robust Error Handling

    Integrates Host and Downstream Port Containment (DPC) and hardware interrupt generation for uncorrectable errors, ensuring link stability and data integrity

  • In-field Upgrade

    COSMOS software upgrades enable seamless deployment of new features into existing infrastructure in the field

Use Cases

Resources

Ordering Information

Orderable Part NumberDocumentsFrom (Lanes @PCIe Gen)To (Lanes @PCIe Gen)Total LanesOrderingStatus
PG60161LRPortfolio Brief8L @ PCIe 6 8L @ PCIe 5 8L @ PCIe 416L @ PCIe 5
16L @ PCIe 4
16L @ PCIe 3		24Contact UsProduction
PG60321LRPortfolio Brief8+8L @ PCIe 6
8+8L @ PCIe 5
8+8L @ PCIe 4		16+16L @ PCIe 5
16+16L @ PCIe 4
16+16L @ PCIe 3		48Contact UsProduction

Accelerating AI Design and Deployment: Modularity Is How Inference Capacity Gets Built

Inference demand is growing faster than the industry can build for it. Modularity at every level, from chip to grid, is how capacity gets built fast enough.This theme ran through the 2026 OCP Global Summit. AMD CEO Dr. Lisa Su called 2026 “the year of inference,” with agentic traffic up 14x this year. Dr. Dimitrios Ziakas, CTO of Hyve Solutions, pointed to a 7x year-over-year jump in… Read more

Lighting the Way: Demonstrated Progress on Our Optical Roadmap to NPO and CPO

Earlier this year, Astera Labs outlined how we’re responding to the demand for low-power, ultra-low-latency, high-density, high-speed links as AI outgrows the rack. We demonstrated our progress toward this goal with a high-radix linear pluggable optics (LPO) demonstration at Computex 2026.Our flagship event of the year, the OCP Global Summit, has now wrapped up, and it’s the right… Read more

One High-Radix Switch, 89% More Tokens/s: Scorpio X-Series Outperforms Conventional Switches in 8-GPU Clusters

AI infrastructure has entered the era of the “AI factory.” Inference workloads dominate AI compute and hyperscalers are increasingly focused on profitable tokens/s generation. Inference accounts for roughly two-thirds of all AI compute in 2026, up from about a third in 2023, and the trend line only points up.1The AI fabric has a real impact on tokens per second, and the switch that connects… Read more

Astera Labs Unveils Orion: A Compute-Agnostic Rack-Scale Architecture for Token-Efficient AI Factories

Modular, production-grade, reference designs for neoclouds and enterprises to quickly scale AI inference capacity up and across with up to 160 accelerators per podNews Highlights:Bring Your Own GPU/CPU: Modular Orion reference architecture is designed to give customers the flexibility to choose accelerators and CPUs based on availability, lead time, cost, target applications, or… Read more

Astera Labs Announces Aries 7: Industry’s First PCIe 7 Signal Conditioning Portfolio Across Copper and Optical Interconnects 

Purpose-built retimers, redrivers, cable modules, optical drivers, and optical transimpedance amplifiers (TIAs) to support diverse PCIe 7 connectivity in AI systemsNews highlights:Most comprehensive PCIe signal conditioning portfolio: Building on Aries’ field-tested deployments, Aries Smart Signal Conditioning family is now the industry’s first PCIe 7 portfolio to span copper… 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

To the Stars: The Astera Labs Growth Journey

Watch COO Sanjay Gajendra recount the astronomic origins of the Astera Labs name and trace our growth from start-up to scale across our expanding product families.From a single PCIe Smart Retimer to a full stack of standard and custom connectivity products, we’re just getting started on the journey to deliver AI Your Way. Read more

Delivering AI Your Way

Today, there is no single blueprint for AI. AI infrastructure is evolving rapidly with technologies optimized for different workloads, performance requirements, and deployment models.Watch the leaders of Astera Labs’ Compute Connectivity Group and Signal Connectivity Group outline how our interconnect technology helps organizations build AI architecture for any protocol, any CPU, any GPU,… Read more

First Look: Orion Rack-Scale Reference Architecture

As AI inference scales rapidly, neoclouds and enterprises need infrastructure that delivers predictable performance and can quickly adapt to the evolving market. They must secure and deploy sufficient compute capacity while navigating increasingly complex infrastructure and supply-chain challenges.AVP, Product Marketing and Strategy for Platform Solutions Mike Hendricks reveals our solution:… Read more