SFM6126 Network Switch Board

6U OpenVPX wideband PCIe gen 3 network switch board

  • slide

Efficient, Low-latency PCIe Switching

The EnsembleSeries SFM6126 is a 6U OpenVPX PCIe Gen3 and Ethernet network switch board with I/O mezzanine sites and system management.

SFM6126 OpenVPX™ PCIe gen 3 switch with innovative capabilities for creating your truly composable data center edge processing architecture for aerospace and defense applications.


  • Full Gen3 PCIe high-bandwidth switching
  • 16 ports of 10 Gigabit Ethernet control plane switching
  • I/O distribution for PCIe data plane or expansion/sensor plane
  • Transparent or non-transparent port-by-port bridging
  • Dual XMC I/O mezzanine sites
  • VITA 46.11 system management
  • Optional MOTS+ rugged packaging for extreme environmental protection
  • Designed, built, coded and supported from trusted DMEA facilities

 MOTS.png    mae2020award-silver-resized.png


Extreme Embedded Switch Fabric Performance

SFM6126 modules switch the control and expansion planes with an efficient PCIe architecture that delivers a performance boost to OpenVPX subsystems. With the versatility of a XMC site for mounting mezzanines, including the EnsembleSeries IOM-400 that distribute wideband I/O transparently and holistically to any other PCIe-connected device – including CPUs, GPUs, FPGAs and storage arrays. This ability to mirror a composable data center architecture is critical for remote deployment of today’s most contemporary AI and other big processing algorithms.


High Performance Embedded Edge Computing (HPEEC) 

SFM6126 are critical scaling components for your truly composable high performance embedded edge computing (HPEEC) solution. When integrated with other EnsembleSeries OpenVPX compute building blocks, including the latest data center Intel Xeon Scalable blades, powerful GPU co-processing engines, the power of the data center is put into your application. These big data processing solutions are tailorable to your platform and can deployed in the harshest and most SWaP constrained environments.

The Anatomy of a Rugged OpenVPX Module

  • Optional MOTS+ packaging for proven extreme environmental protection
  • Next generation liquid and air cooling for reliable, deterministic processing
  • Miniaturization for processing density
  • Unrestricted OpenVPX signal channel for big processing tasks
  • Soldered down processors and components for resilience

Affordable, Interoperable and Upgradable

Place the best technology into the hands of service men and women faster by building your next HPEEC processing solution with EnsembleSeries compute modules that are made with open architectures for interoperability, scalability and re-use. Further drive affordability, performance and lower your program risk by using the architecture that evolves at the speed of technology, follows industry technology roadmaps and leverages data center hardware, software and IP.

Gain a Competitive Edge

Deploy next generation automatous platforms, cognitive EW systems, compute-intensive EO/IR, AI and radar processing, and sensor fusion applications that require data center-class capabilities closer to the source of data origin – at the edge. Efficiently process streaming data over a distributed heterogeneous PCIe-enabled architecture from the cloud to the edge with a seamless and common compute architecture that integrates the latest commercial capabilities for affordability and low program risk.


Use AI to Make Better Decisions

Turn your sea of sensor data into actionable intel quickly. Miniaturizing data center capability into a compact, OpenVPX high-performance embedded edge compute (HPEEC) architecture allows AI processing to be placed next to sensors on edge platforms



Mitigate Deployment Risk with Proven Experience

We employ cutting-edge commercial technologies and unique processes borne from a wealth of in-house expertise, garnered on over 300 programs, to develop and manufacture solutions to meet your application's demanding conditions. 



Utilize the Latest Silicon Valley Tech

We partner with industry leaders like Intel® and NVIDIA® to incorporate the most advanced AI-enabled data center and multi-core edge processors into the rugged, trusted and secure solutions that power your most ambitious on-platform processing applications.

Other HPEEC Building Blocks

GSC6204 6U OpenVPX, SOSA-aligned, GPGPU Coprocessing Board

GSC6204 6U OpenVPX, SOSA-aligned, GPGPU Coprocessing Board

Dual NVIDIA Quadro Turing GPU, 6144-cores, 32 GB total GDDR6, 896 GB /s, 4x DisplayPort, 2x VGA, PCIe, NVlink, 170W, MOTS+, OpenCL, CUDA


HDS6605 6U OpenVPX Multiprocessing Board

HDS6605 6U OpenVPX Multiprocessing Board

Intel Xeon Scalable 22-core server-class CPU, 192 GB DDR4, 100 GbE, PCIe Gen3, MOTS+ protection


SCM6010 and CAN6000 Plug-in Storage

SCM6010 and CAN6000 Plug-in Storage

6U OpenVPX SSD plug-in storage with PCIe switching and removable canister



Tech Brief: MOTS+ Environmental Protections for Operation at the Tactical Edge

Learn how Mercury's modular open systems architecture (MOSA) approach to subsystems design provides...


Case Study: EO/IR Airborne ISR Processing

Learn how rapid tech insertion enables real-time aircraft sensor processing in an actively deployed...


Webinar: Enhance Multi-Domain Operation with GPU-Enabled Solutions

Take advantage of GPU data processing and AI/ML capabilities at the tactical edge by managing the...


Blog: Durability begins with preparation

Welcome to fall! Just a few short hops from here to winter, and up here in the Northeast, we never...


White Paper: Durability Advantages of Mercury’s Modified Off-The-Shelf (MOTS) Product Approach

Learn how Mercury builds products with varying degrees of enhanced durability to operate under...


White Paper: Enabling big data processing and AI-powered everything, everywhere

Learn how Mercury and Intel collaborate to scale and deploy composable data center capabilities...


Infographic: Embedded Processing Subsystems

Mercury subsystems solve big data processing problems for platforms operating at the tactical edge....


Blog: Innovating past the need for compromise for your embedded computing

What do you think of when you hear the word ‘compromise’? Possibly an agreement made between...