[j-nsp] Qfabric

Keegan Holley keegan.holley at sungard.com
Sun Feb 27 11:55:50 EST 2011


On Fri, Feb 25, 2011 at 8:42 AM, Saku Ytti <saku at ytti.fi> wrote:

> On (2011-02-24 17:15 -0800), Joel Jaeggli wrote:
>
> > that activity can be simple as front-running large orders (which take
> > longer to fill) with small ones, an elaborate algorithm is not
> > necessarily a requirement. I'm kind of down on the market utility of
> > such activity but it's not presently illegal.
>
> I suppose it still may be somewhat more complex task than my trading
> software, in terms of how many instructions it needs from CPU, and thus
> necessarily higher latency, as it is competing with other stuff, for
> example kernel house-keeping.
>
> Are these software being ran in regular PC, or has someone tapped this
> market and is producing FPGA based fixed delay trading solutions at
> nanoseconds jitter scale?
> I wonder how much jitter in normal PC could be reduced for running
> simplistic software, even with esoteric stabbing of the kernel, sub 1ms
> jitter on software solution seems unachievable.
>

An FPGA based trading solution would be interesting and probably very
profitable if it worked.  The bigest problem would probably be the cost of
the platform withmultiple multi-core proc's and FPGA's vs. how much you'd
really end up doing in silicon.  The FPGA would be great to do the same
trades over and over. However, if the software has to use other values to
figure out what action to take and then program the FPGA on the fly I would
assume everything but the network operation would be slower.  I suppose you
could separate the repetitive actions and use ASICS.  All in all it sounds
like a fun project though.


More information about the juniper-nsp mailing list