Additional PCIe capacity
Connect more devices, slots or modular chassis when the host platform alone is insufficient.
Dolphin PCIe interconnect technology
PCIe Expansion & Interconnect
PCIe adapters, switches, chassis, modular interconnects and software for extending device capacity and building high-bandwidth data paths across hosts and chassis.
PCIe Gen3–Gen5
Transparent expansion
NTB networking
Peer-to-peer
PXIe / CPCI-S
SISCI / SmartIO
Technical context:
Dolphin Interconnect Solutions provides transparent and non-transparent PCIe adapters, switches, modular-system interfaces and eXpressWare software. Generation, lane width, connector, cable media, clock isolation, operating-system support and topology capability are model-specific. Several published Gen5 products—including MXS524, MXH54x optical adapters, MXP52x modules and eBox 4 Pro/MXB585—remain preliminary or availability-controlled and must be confirmed before design-in.
Hardware and software
Product Range
Select adapters, switches, modular interconnects, expansion chassis, link media and fabric software according to the required topology.
PCIe Host & Target Adapters
Connect a host to remote devices or another computer while choosing native transparent access or isolated NTB communication.
Gen3–Gen5
Transparent
NTB
View details
PCIe Switches & Fabrics
Scale port count, endpoint capacity and multi-host connectivity through MXS524 Gen5, MXS924 Gen4 and MXS824 Gen3 external switch platforms.
24 × x4
Gen3 / Gen4
Managed fabric
View details
PXIe & CompactPCI Serial
Expand modular systems, connect chassis to external compute and enable communication between independent controllers.
PXIe Gen4/5
CPCI Serial
Multi-chassis
View details
PCIe Expansion Chassis & Backplanes
Add full-size and high-power devices with dedicated slots, cooling and service access while retaining the host platform.
2U / 4U
Up to 9 cards
Up to 4800 W
View details
Copper & Optical PCIe Links
Place PCIe resources across racks or rooms while preserving high-bandwidth access and using an electrically separated optical data path where appropriate.
Copper / optical
SFF interfaces
Up to 200 m
View details
PCIe Fabric Software
Turn the hardware fabric into a usable application platform through shared memory, sockets, IP, device access and management.
SISCI
SuperSockets
SmartIO
View details
System architecture
System Capabilities
The available products support several system approaches, from transparent device expansion to independent-host communication and direct device data paths.
Native device access
Retain compatible PCIe drivers, endpoint behaviour and DMA where the selected topology supports them.
Independent-host communication
Use NTB hardware and fabric software to exchange data between separate computers without merging their root complexes.
Configurable data paths
Select shared memory, sockets, IP, multicast or peer-to-peer transfers according to the application and supported hardware.
Dolphin PCIe technology
PCIe interconnect hardware and eXpressWare software
Dolphin Interconnect Solutions combines PCIe adapters, switches, modular-system interfaces and software for transparent I/O expansion, NTB communication and managed PCIe fabrics.
One PCIe hierarchy across cable or backplane
Transparent host and target adapters extend a root complex to compatible remote endpoints. Driver, BAR allocation, reset, hot-plug and peer-to-peer behaviour must be validated through the complete topology.
Independent hosts with translated PCIe windows
Non-transparent bridging keeps root complexes independent while enabling translated memory windows, DMA and interrupts. Switches add fan-out, multi-host and modular-system topologies.
Shared memory, sockets, IP and device access
Supported software components include SISCI, SuperSockets, IPoPCIe, reflective memory and SmartIO or device lending. Availability depends on the hardware family, operating system and license.
Current product families span PCIe Gen3, Gen4 and Gen5 adapters, PXIe and CompactPCI Serial modules, external switches and expansion systems. Model-specific links use SFF-8614, SFF-8644, CDFP CopprLink or FireFly optical interfaces; supported cable reach ranges from short passive-copper links to optical configurations of up to 200 metres.
System design patterns
Reference Architectures
Deployable patterns that define root-complex ownership, data movement, software responsibility, timing boundaries and qualification criteria before individual components are selected.
Single-root I/O
Host
Remote I/O
Reference architecture
Transparent PCIe Expansion
Extend native PCIe endpoints beyond the host while keeping one PCIe hierarchy and the endpoint driver model.
Explore architecture →
Independent hosts
Host A
Host B
Host C
NTB fabric
Reference architecture
Low-Latency PCIe Networking
Connect separate computers through NTB and select SISCI, SuperSockets or IPoPCIe according to the application path and supported software release.
Explore architecture →
Replicated state
Source region
Node B
Node C
Node D
Reference architecture
PCIe Reflective Memory
Distribute application-defined state to multiple nodes through SISCI broadcast segments and supported PCIe multicast.
Explore architecture →
Direct device movement
DAQ
FPGA
GPU
NVMe
Reference architecture
Peer-to-Peer PCIe Data Paths
Route compatible acquisition, FPGA, GPU, NIC and NVMe transfers directly between local or remote endpoints to reduce host-memory staging.
Explore architecture →
Scalable instrumentation
Controller
PXIe 1
PXIe 2
PCIe data path
Reference architecture
PXIe Multi-Chassis Systems
Scale slots and processing across chassis while keeping PCIe control/data transport separate from PXI timing and triggers.
Explore architecture →
Managed resources
Host A
Host B
Host C
Device pool
Reference architecture
Shared PCIe Device Access
Pool compatible devices and expose them through Device Lending or SISCI SmartIO with explicit ownership and lifecycle control.
Explore architecture →
Application areas
Applications
PCIe interconnect is used where endpoint bandwidth, latency, native driver access or system scalability is a primary design constraint.
HPC & accelerated computing
Increase accelerator and storage capacity while reducing data movement between compute, FPGA, GPU and NVMe stages.
Test & measurement
Scale instruments and acquisition across chassis without replacing the complete controller and software environment.
Automotive & EV
Connect HIL, simulation, logging and accelerator platforms for high-rate validation workflows with defined latency and bandwidth.
Machine vision
Create direct camera, FPGA, GPU and storage pipelines that reduce host-copy overhead and processing delay.
Semiconductor test
Expand instrumentation and move device data efficiently into processing and storage for characterization and production test.
Aerospace & defence
Build modular multi-node processing and remote-I/O systems with controlled ownership, isolation and deterministic data paths.