[This message was posted by Stefan Basiuk of Rapid Addition Limited 
<[email protected]> to the "Product Discussion" discussion forum 
at http://fixprotocol.org/discuss/24. You can reply to it on-line at 
http://fixprotocol.org/discuss/read/86e822e9 - PLEASE DO NOT REPLY BY MAIL.]

Rapid Addition today announced that it’s FIX engine has processed 70 million 
messaging with an average time of under 20 µs. The test was a sustained high 
volume FIX engine message parsing and transmission exercise. In the tests RA 
processed 99.9% of 70 million messages in under 30 us and had a mean and median 
message processing time of about 19 µs with a standard deviation of 3.1 µs.

 The tests were conducted on commodity hardware running .NET3.5 on Windows 2008.

 

Over 70 million New Order Single messages with a size of 197 byte were sent and 
received across 140 sessions running 2 threads over a 50 minute period 

An average 12,000 messages were processed per second with 190MB per minute sent 
and received on the network. 

Messages were fully validated.

Measurements were performed at the application and socket layers. 

Garbage collection had no discernable impact over the run period. 

No memory or thread leaks detected 

Rapid Addition is constantly at the leading edge of high performance low 
latency technology within the FIX and FAST space producing consistent high 
quality low latency performance. 

Toby Corballis, CEO of Rapid Addition said ‘We welcome the recent developments 
in the low latency space, where we are seeing a number of competitors and the 
market in general raising their game. At Rapid Addition we have always invested 
heavily in R & D and working with our partners at Intel and Microsoft , and 
thus being able to give our clients a truly competitive edge’.

Rapid Addition will shortly be publishing the technical performance testing 
data and would welcome other vendors doing the same.

‘What would also be welcome would be an industry accepted standard in 
performance measurement. We are seeing a conspicuous need in the market for 
greater transparency where technical performance testing data is concerned. We 
intend being at the forefront of the development of an industry initiative for 
such a standard. This is something that would allow customers to compare FIX 
engine performance on a proper, like-for-like basis for the benefit of the 
market and importantly customers.

[You can unsubscribe from this discussion group by sending a message to 
mailto:[email protected]]

--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"Financial Information eXchange" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to 
[email protected]
For more options, visit this group at 
http://groups.google.com/group/FIX-Protocol?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to