Celoxica Accelerator for Market Data Capture

Low-latency, high-capacity market data capture

Celoxica's Accelerator for Market Data Capture is the first product on the Acceleratormarket to offer ultra-low-latency access to market feed data. With average latency figures below 2 microseconds, Celoxica is redefining the term “low latency”.

Celoxica leverages hardware acceleration to provide an innovative new architecture for access to market data feeds. This architecture gives high reliability during spikes in message volume. Integrated into standard, tier 1 OEM servers, the Celoxica Accelerator for Market Data Capture offers the ultimate combination of performance and ease-of-use.

Key benefits

Lowest-latency access to market data feeds

High reliability during message spikes

Minimal impact on heat and power consumption

Plug-in improvement in performance of standard servers

Low-latency access to market data feeds

A co-processor directly connected to the network port means that the Accelerator can provide which is independent of the data volume. The HyperTransport link to the host CPU provides the lowest latency bus transfers available in standard servers.

Hardware protocol stack (TCP, UDP, IP) - no overhead typically associated with software protocol stack

Hardware FAST decoder

Hardware conversion from ASCII messages to binary representation

Automatic, hardware recovery via secondary feed and TCP link

During network benchmarks, the Accelerator gives a constant latency of 1.5 microseconds from the end of a packet arriving on the network to it being available in user memory

High reliability during message spikes

The innovative architecture of the Accelerator means that it can deal with fluctuating, high message volumes.

Each Accelerator can process 2 saturated 1 Gbps Ethernet links with constant, low latency

The Accelerator provides consistent latency and reliability during message volume spikes

Minimal impact on heat and power consumption

The low-power co-processor architecture means that even when processing two fully-saturated 1 Gbps network links, the total power consumption of the server is barely affected.

Consumes ~10 watts processing fully-saturated links

Plug-in improvement in performance of standard servers

Simple integration into existing applications on standard servers, with the ability to customise the message interface.

Qualified and supported by industry standard servers from HP, IBM and Appro

Supported in standard, readily-available slot form factor

Simple C/C++ API for integration into existing applications

NIC emulation for diagnostics and integration into IT infrastructure

An innovative architecture

Hardware co-processors have been discussed for a while in high-performance computing circles as a method for Architecture diagram 1dramatically increasing system performance and offloading computation from CPUs. Celoxica's Accelerator is the first market data handler to directly connect a network interface to a co-processor, eliminating one of the major contributors to latency in a hardware/software co-processing system: the peripheral bus transactions between the co-processor and the network device.

Once in the co-processor, the network data is processed in a highly-parallel processing pipeline at line-speed. The TCP/UDP/IP protocol stack, FAST decoder, recovery system and ASCII-to-binary conversion engine are all implemented in dedicated hardware, with the lowest-possible latency.

The co-processor board fits into a standard HyperTransport slot, which is the lowest latency server communications bus available today. Once converted to a binary representation, the network data is transferred via the HyperTransport Co-procssor diagrambus directly to the CPU's memory. A C/C++ API is then available for you to integrate this system with your own application, getting feed updates before the competition.

Supported market feeds

For each market, the Accelerator is configured with efficient co-processing logic tailored to that market feed.

ASCII and FAST-compacted market data feeds over UDP are supported

Recovery via redundant UDP feeds or TCP interfaces, where available, are both supported in low-latency logic

ISE Depth of Market Feed

OPRA, NASDAQ ITCH, NYSE Arca, CBOE, BOX, Philly, Amex coming soon

Easily customisable

Celoxica recognises the importance of fitting in to your organisation's needs, so we give a high-degree of control over the behaviour of the Accelerator.

Define filters on the market data to get just what you need minimising the load on your server

Filter on variables including symbol, price, quantity and expiration date

Customise the binary output format to suit your application

Deployment

The Accelerator Card fits into the slot of an industry standard 1U rack-mount server. With an Accelerator, each server can process the full data rate of one market feed. Multiple Accelerators and servers can be deployed to process different markets.

Deployment

Each Accelerator can process the full data rate of one market feed

The Accelerator is usually deployed in a pair of servers with one Accelerator per server

The second server acts as a live-backup, taking over in the unlikely event of failure in the first

A third Accelerator is advisable for testing and backup purposes

Compatibility

Red Hat 5.0, Red Hat 4.0 Update 4/5 (32 or 64 Bit)

2 x 1000BaseT Copper RJ45 connectors

HyperTransport slot

Verified on HP DL145 and IBM x3455 1U rack-mount servers with standard production BIOS

Contact Celoxica for information on compatibility with other operating systems or servers

Support, maintenance and professional services

Front-line support provided by server manufacturer or their reseller through partnerships with Celoxica.

Second-line support provided by Celoxica

A maintenance contract with Celoxica ensures timely access to the latest improvements and updates to the Accelerator

Professional services to implement user-specific customisations

©Celoxica 2008. T: +44 (0)1235 863656
Contact us "" Privacy policy "" Legal notice "" Site map "" Home ""