• Use a binary transaction protocol to eliminate data conversions and complex parsing.

• Use Remote Direct Memory Access (RDMA) verbs and zero copy mechanisms to eliminate network protocol stack processing.

• Use preallocated data structures to completely eliminate all memory turnover and associated garbage collections.

• Tune the hardware and OS for low latency

Part of me says “duh” but part of me says that maybe this is not necessarily common application yet?

Another “worlds fastest matching engine” – here

Tibco FTL messaging – seems interesting…

Fixnetix Raises the Bar: World’s Fastest Nanosecond Trading – more FPGA trading…

Responses are currently closed, but you can trackback from your own site.