Hi Robin,
Robin Getz wrote:
On Wed 18 Apr 2007 02:03, Greg Ungerer pondered:
Sven Johnsson wrote:
I have executed a Dhrystone 2.1 benchmark on my uClinux system and get
an extremely low result, about 0.0259 DMIPS (I also used a stopwatch
to confirm it). The datasheet of the processor says 211 DMIPS!
It looks ok in the 2.6.20 code base, but you need to check it
in your older code base.
Greg:
What results did you get on 2.6.20? We posted some various tests (both with
flat and fdpic - if you are interested in the overhead of fdpic)
I haven't run the dhrystone code for a while, so I don't have
any specific numbers.
That comment above was referring to the cache enable code
in 2.6.20 (for the ColdFire's).
http://docs.blackfin.uclinux.org/doku.php?id=dhrystone#results_on_a_blackfin
When I last looked at this the big difference seemed to be that
hardware vendors (well, Freescale in my example case) where using
the fast internal RAM to run dhrystone. Running it from DRAM was
am immediate big lose.
Then on top of that was compiler.
Together that meant that numbers measured under uClinux where
significantly lower.
Most of the work I did was with fully relocated application
binaries - so no PIC to slow it down.
Where we measured around 328.8 with gcc under Linux - according to the folks
who don't work on Linux, the results are sub-optimal - the architecture is
capable of over ~450 with no OS and the proprietary compiler - and I was just
wondering how close gcc/Linux on your platforms is to the non-OS/proprietary
compilers.
-Robin
And yes - for those that are interested, we are going through the output of
all the compilers to see how to make gcc better.
A fine thing indeed :-)
Regards
Greg
--
------------------------------------------------------------------------
Greg Ungerer -- Chief Software Dude EMAIL: [EMAIL PROTECTED]
SnapGear -- a Secure Computing Company PHONE: +61 7 3435 2888
825 Stanley St, FAX: +61 7 3891 3630
Woolloongabba, QLD, 4102, Australia WEB: http://www.SnapGear.com
_______________________________________________
uClinux-dev mailing list
[email protected]
http://mailman.uclinux.org/mailman/listinfo/uclinux-dev
This message was resent by [email protected]
To unsubscribe see:
http://mailman.uclinux.org/mailman/options/uclinux-dev
