[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [microblaze-uclinux] OT?, Performance
Jivin emanuel stiebler lays it down ...
> jozsef imrek wrote:
> >On Wed, 12 May 2004, emanuel stiebler wrote:
> >>Anybody had some thoughts already, why there is such a BIG
> >>difference between the numbers on xilinx web, and the dhrystones
> >>we measure here ?
> >i guess those numbers are for fpga's with speed grade 6, while
> >for example i have an fpga with speed grade 4. that might be a difference.
> Between the "grades" there is a difference of few percent.
> I'm talking about a difference bewteen 600 KMIPS and 50 KMIPS ...
> >i want to try to 'overclock' my board. have any of you tried to do so?
> Don't see a reason to get few percent of performance, and
> loose the stability for it.
I can't comment on the xilinx specifically, but I can say that there
has always been a significant difference between the dhrystone numbers
motorola post for their Coldfire and the numbers we get from the
dhrystone application running under uClinux.
I think they run it from the internal SRAM (0 wait states) for a start,
and use a different compiler, but I don't think anyone has duplicated the
results they get.
Could be a case of very specific and careful benchmarking to get those
David McCullough, email@example.com Ph:+61 7 34352815 http://www.SnapGear.com
Custom Embedded Solutions + Security Fx:+61 7 38913630 http://www.uCdot.org
microblaze-uclinux mailing list
Project Home Page : http://www.itee.uq.edu.au/~jwilliams/mblaze-uclinux
Mailing List Archive : http://www.itee.uq.edu.au/~listarch/microblaze-uclinux/