Reflective Memory Networking Solutions:

Determinism, Simplicity and Sheer Performance.

Reflective Memory networks are real-time Local Area Networks (LANs) in which each computer always has a local, up-to-date copy of the network's shared memory set.

Reflective Memory ImageReflective MemoryReflective Memory networks are designed to provide the highly deterministic, tightly timed performance necessary for a variety of distributed simulation and industrial control applications. They have benefited from advances in general-purpose data networks, but they remain an entirely independent technology, driven by different requirements and catering to applications where determinism, implementation simplicity, integration of a number of dissimilar hardware platforms running different operating systems, and a lack of software overhead are key factors.

Using Reflective Memory systems, designers are able to eliminate most communication latency and realize drastic improvements in resource utilization over traditional LAN technologies. The benefit of a low-software, high-speed, hardware driven network like Reflective Memory is extremely low data latency, both overall and between individual network nodes. This low latency performance is of paramount importance when building real-time systems such as simulators, PLC controller system, test stands, or High-Availability system.

Reflective Memory offers unique benefits to the network designer:

Blue ArrowPerformance

  • High speed, low latency data delivery
  • Deterministic data transfers for demanding real-time communications

Blue ArrowSimplicity

It is just memory – Read it and Write it

  • Each networked node has its own local copy of the data
  • Write operations are first performed in local RAM, then automatically broadcast to all other nodes on the network
  • Read operations access the local copy of the data, which always mirrors other local copies on the network

Using a Reflective Memory network requires only a few simple steps.

  1. Plug Reflective Memory into any available backplane slot or bus via VME, PCI, PCIe, or PMC, or connect it to any single board computer or carrier (VME, CompactPCI etc.) with a PMC site and connect cabling.
  2. Install the driver.
  3. Write to memory (Reflective Memory’s global memory appears to the computer as standard RAM).
  4. Read memory (from Reflective Memory boards on the network).

Blue ArrowFlexibility

  • Drastically reduced software development time and cost (time-to-market)
  • Connections to dissimilar computers and bus structures including standard and custom platforms.
  • Easy-to-use software, low overhead
  • Small to large separation distance between network nodes
  • Data can be shared regardless of processor type or operating system

 

Our Reflective Memory Products are designed to fit into your existing environment.

Our node interface cards can be installed in a variety of computer backplanes and buses including VME, PMC, PCI and PCI Express. We support a wide variety of operating systems such as Linux®, VxWorks®, Microsoft® Windows® XP/ Vista®/2003 and Solaris®. You also have the choice of multi-mode for short fiber runs or single-mode for spanning long distances between nodes for the fiber optic cable interconnect. Plus, our newly refreshed software tools are designed to ease migration from older Reflective Memory products to newer, fuller-featured and higher performance Reflective Memory products.

 

Choose the network topology that matches your needs.

Star Topology

With a fiber-optic hub, the Reflective Memory network will continue to operate even if a node has been turned off. The hub automatically bypasses any network node that ceases operation to ensure data continues to the next node in the network maintaining the integrity of the ring. Hubs can be cascaded, permitting a managed hub array with up to 256 nodes. Each port regenerates the serial optical signal, eliminating problems with insertion losses and cable attenuation. Signal regeneration also reduces jitter.

Star Topology
 

Ring Topology

The Reflective Memory ring architecture is capable of data transfer rates of 170 MB/s over fiber-optic media. It is not a collision-based bus arbitration system as most Ethernet systems are, so it avoids the complexities of queuing and checking data packets. This topology also ensures proper connectivity and does not impose additional loading restrictions or termination.

 

Ring Topology

 

Reflective Memory networks provide the highly deterministic, tightly-timed performance needed for a variety of distributed simulation and industrial applications.

Image AL

 

Aluminum Rolling Mill

On a 3,500 ft/min rolling mill, a standard PLC Control loop had a response time that allowed 2 to 3 feet of aluminum to pass through before actuators could respond. These actuators were applying and releasing pressure on the aluminum to vary the thickness. Using Reflective Memory, the response time was reduced to 4 inches, resulting in tremendous waste reduction and quality improvement in the final product.

 

 

Low-software, high-speed, hardware

Nuclear Image  

Nuclear Power Plant Simulation

One benefit of a low-software, high-speed, hardware driven network like Reflective Memory is extremely low data latency, both overall and between individual network nodes. This low latency is of paramount importance when building real-time systems such as the KSG nuclear power plant simulator with hundreds of real-time I/O points.

 

Data gathered from hundreds of real-time I/O points can be sent over a single link to the main computer in a central, remote control room.

Rocket Image

 

Rocket Engine Testing

A rocket engine test stand uses hundreds of transducers to measure various parameters. Operators need a lag-free connection to the testing, but for safety reasons, the instrumentation/viewing center may be located 3,000 meters away. With Reflective Memory, a single link can send data to the main computer in the control room, eliminating hundreds of discrete wires spanning the 3,000 meters. Operators can observe and react to changes as they occur, with minimal delays imposed by the connection, minimize risks to personnel and equipment with no degradation of test performance.

 

 

Fast, full system synchronization ensures continuous, efficient operations.

High availability Image

 

High Availability

For operations such as continuous processing, power and energy and certain telecommunications applications, high availability is essential. Unplanned downtime can have serious impact on productivity, profitability and performance. With Reflective Memory each networked computer always has a local, up-to-date copy of the network’s shared memory set. In a High-Availability application data can be synchronized between an active CPU and backup CPUs. If the active node fails, a backup node can seamlessly pick up the process using a memory that is identical to the failed system.

 

 

Migrate from legacy RFM1 100Mb/s Reflective Memory hardware to 2Gb/s RFM2 hardware.

Diagram Image

 

Porting API Library

The Porting API Library is a software tool that provides a migration path for legacy RFM1 Reflective Memory users to move to new RFM2 hardware that offers more features and higher performance. RFM1/RMNet-to-RFM2g porting enables RFM1 users to use the higher performance and feature-enhanced RFM2 devices with minimal change.

The Porting API is an interface layer that can be easily installed over RFM2g drivers and enables users to run application code developed for RFM1 products on new RFM2 Reflective Memory products with little or no modification.

The porting layer resides above the RFM2g API, providing a familiar RFM1/RMNet API to the application and aids in translating between the two APIs.

Porting API Libraries are available for downloading from RFM1/RMNet No Longer Recommended and Discontinued product pages.

 

 

Additional Resources:



News:

Novotek Combines GE’s Electronic Work Instructions with Google Glass™ Read more
GE’s Mark VIeS Safety Management System Receives exida 2014 Safety Award Read more
GE Delivers Real-time, Actionable Business Intelligence Capabilities with New Industrial Internet... Read more