Aries 7 PCIe Smart RedriversAries 7 PCIe Smart Redrivers

Aries PCIe® Smart Redrivers

Power-Optimized PCIe 7 Connectivity for AI Infrastructure

Purpose-Built for Fleet-Wide AI Deployment

  • PCIe/CXL® Smart Redriver optimized for low power and low latency topologies
  • Advanced telemetry with adaptive EQ and integrated eye monitoring
  • Pin-compatible with Aries Smart Retimers for design flexibility
  • COSMOS software suite for real-time monitoring and fleet management

Nothing Out of Reach

Enable Power-Optimized Topologies

Extending the Aries Family to Support Diverse Applications

Low Power

Power savings over retimers at 128 GT/s

Ultra-Low Latency

Built for latency-sensitive AI scale-up and CXL® applications

Enhanced Diagnostics

Cosmos Platform Logo – Astera Labs Developer Ecosystem for CXL Products

Enables adaptive equalization and integrated eye monitoring

Why Choose the Aries Smart Redriver?

Intelligent PCIe Connectivity for Next-Gen AI Infrastructure

Performance

  • Reach Extension

    18+ dB reach extension at 128 GT/s for AI server boards, backplanes, and active cable deployments

  • Ultra-Low Latency

    <50ps latency minimizes timing overhead, running AI workloads at full speed

  • Power Efficiency

    >50% power savings compared to retimer for efficient signal conditioning that keeps rack power budgets in check at scale

Ease of Use

  • Plug and Play

    Seamless interop and transparency to PCIe link training with support for any link bifurcation

  • Smart Swap

    Pin-compatible Aries 7 Smart Redriver and Retimer give designers maximum flexibility as channel requirements evolve

  • Compact Form Factor

    Small package footprint enables PCIe reach extension in space-constrained AI and cloud infrastructure

Diagnostics and Management

  • On-Die Signal Monitoring

    Dedicated monitoring path delivers real-time link health, integrated eye monitoring, and loss of signal detection to accelerate deployment

  • COSMOS Link Intelligence

    COSMOS software suite enables unified fleet management, link telemetry, and in-field upgrades for secure, optimized link performance

  • Dynamic Tuning

    Adaptive equalization, integrated eye monitoring, and temperature-compensating EQ optimize signal quality across all operating conditions

Use Cases

Read more

AI Server Head Node

Deliver high-performance, robust PCIe link connectivity with optimized thermal efficiency for CPU root complex server boards that connect to GPU baseboards…
Read more

Modular Infrastructure

Accelerate general purpose server deployments with high performance, robust PCIe connectivity solutions in modular infrastructure based on industry standard…

Resources

Evaluation Kits

Evaluation KitImageDocumentsDescriptionMax PCIe GenPCIe LanesPack QuantityOrderingProduction Status
ECLIPSE7-REVAECLIPSE7-REVA-675x550Product BriefAries 7 Smart Redriver MCIO Test BoardPCIe 7.xx161Contact UsPre-Production
EQUINOX7-REVBEQUINOX7-REVB-675x550Product BriefAries 7 Smart Redriver CEM Add-In CardPCIe CEM 7.xx161Contact UsPre-Production

Ordering Information

Part NumberPCIe GenConfigPackage SizeStatusCompatibility
PD7080LPCIe 7.0 8-Ch, Unidirectional7.5 x 10.5 mm SamplingSeamless hardware and software upgradability utilizing industry standard footprints and COSMOS
PD7162LPCIe 7.016-L, Bidirectional22 x 22 mmSamplingSeamless hardware and software upgradability utilizing industry standard footprints and COSMOS

Buy the Rack Once, Pick the Accelerator Later: How Orion and Hyve Aim to Speed Up AI Inference Capacity

Inference capacity is one of the most sought-after resources in the data center, yet supply chain constraints make it difficult for neoclouds and enterprises to secure accelerators in time. The challenge is sequencing. Operators commit to power and floor space long before they know which accelerator and rack architecture they will use. Tie that early investment to a single platform, and the… Read more

AllReduce Speedup With In-Network Compute: How INC Accelerates AI Collective Operations

At a glance:INC reduces the transfer time component of latency for collective operations.The tensor parallelism that drives modern inference means INC is most impactful at small message sizes.AllReduce is an increasing percentage of inference time as cluster sizes grow.The inflection point facing AI today as inference workloads overtake training workloads in volume1 has… Read more

Inference is Everywhere…Even the Fabric Switch: Why AI Needs In-Network Compute Today

At a glance:In-Network Compute (INC) is the execution of collective operations at network switches.INC is most impactful for inference workloads, where performance, latency, and efficiency directly shape user experience and deployment cost.Scale-up is the best INC use case because the most demanding inference systems depend on tightly coupled, high-bandwidth, low-latency communication… Read more

Hyve Solutions and Astera Labs Collaborate to Bring AI Inference Capacity to Customers Faster

Hyve Solutions Apex™ platform with Astera Labs’ Orion lineup designed to let customers deploy the rack once and choose accelerators as workloads evolveNews HighlightsExpanded Orion portfolio: Hyve Solutions to integrate and deploy the Orion Compute Board (Orion-CB), Fabric Tray (Orion-FT), and Link Board (Orion-LB), validated building blocks for open, rack-scale AI inference.More… Read more

Astera Labs Reports Third Quarter 2026 Financial Results

Record quarterly revenue of $584.9 million, up 49% QoQ and up 154% year-over-yearScorpio™ fabric switches became the company’s largest product family, led by volume production of the Scorpio X-Series 320-lane fabric switchPortfolio expanded across memory, optical and copper signal conditioning, and rack-scale AI platforms with Leo 2 and Leo X-Series, Aries 7 and OrionSAN JOSE,… 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

Podcast: SixFive Media With Sanjay Gajendra and Hyve’s Dimitris Ziakas

At OCP 2026, Astera Labs President and COO Sanjay Gajendra sat down with Hyve Solutions CTO Dimitris Ziakas on SixFive Media’s On the Road podcast to introduce the Orion Rack-Scale Reference Architecture.They discussed the AI inference demand driving the need for an open scale-up architecture, the proven Astera Labs components that deliver performance across Orion’s six modular… Read more

Podcast: TechArena With Ahmad Danesh and Intel’s Anil Nanduri

At OCP Global Summit in San Jose, TechArena’s Allison Klein talked with Intel Vice President, Product Management, GTM & Customer Success for AI Accelerators Anil Nanduri and Astera Labs AVP of Product Management Ahmad Dinesh about how open standards like PCIe® and CXL® are shaping AI infrastructure.They covered Intel’s Crescent Island inference GPU, Astera Labs’ Orion… 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