Re: [LTP] time problem with LTP

[Manu I. <man...@ya...>]

hi thanks for the reply,
i dont think FPU is the problem, here is the details i got
from the LTP itself about my system, it says the FPU
version is 5.0



Linux uclibc 2.6.11 #5 Sun Jan 29 16:46:46 IST 2006 mips
unknown
 
Gnu C                 
mount                  2.12
modutils               directory
e2fsprogs              1.37
Linux C Library        0.9.27
Linux C Library        0.9.27
Procps                 Command
Kbd                    66:
Sh-utils               --v
Modules Loaded         udm

free reports:
              total         used         free       shared 
    buffers
  Mem:       123356        11988       111368            0 
          0
 Swap:            0            0            0
Total:       123356        11988       111368

/proc/cpuinfo
system type		: ITE QED-4N-S01B
processor		: 0
cpu model		: RM7000 V5.3  FPU V5.0
BogoMIPS		: 0.00
wait instruction	: yes
microsecond timers	: yes
tlb_entries		: 64
extra interrupt vector	: no
hardware watchpoint	: no
VCED exceptions		: not available
VCEI exceptions		: not available

There is one more observation,
 I ran both the tests with out the -p & -l options and i
jst redirected the screen results to a file and found that
the uclibc test is taking only around 45 minutes. so is
logging could be a problem??
Thanks
Manu

--- Prashant Yendigeri <Pra...@ln...>
wrote:

> Hi,
> I think lot of time is being spent in float tests,threads
> tests  etc and 
> other mathematical related tests. Since the MIPS may not
> be having FPU and 
> cache ,it takes lots of time to execute simple function
> calls 
> (mathematical ) like pow,sin etc. 
> 
> Execute the script by commenting these tests and check
> out the time,It'll 
> reduce considerably.
> 
> Regards,
> Prashant 
> 
> 
> 
> Manu Ignatius <man...@ya...> 
> Sent by: ltp...@li...
> 03/13/2006 03:31 PM
> 
> To
> ltp...@li...
> cc
> 
> Subject
> [LTP] time problem with LTP
> 
> 
> 
> 
> 
> 
> hi all,
>  I conducted LTP (runalltests.sh) with the same options
> in
> both MIPS platform as well as x86 and the timings taken
> are
> 
> MIPS (RM7000 series)(with glibc based distribution) - 1Hr
> MIPS (with uClibc based distribution) - 3Hrs
> x86 (PIII 800Mhz)(uClibc based thinclient) - 8Hrs
> Can any one give me a hint, y is this huge difference in
> time is there. I repeated the tests 3 times and the
> results
> are the same. The results(PASS/FAIL) for x86 and
> MIPS-uClibc are same. Please help me. 
>  Manu
> 
> __________________________________________________
> Do You Yahoo!?
> Tired of spam?  Yahoo! Mail has the best spam protection
> around 
> http://mail.yahoo.com 
> 
> 
> -------------------------------------------------------
> This SF.Net email is sponsored by xPML, a groundbreaking
> scripting 
> language
> that extends applications into web and mobile media.
> Attend the live 
> webcast
> and join the prime developer group breaking into this new
> coding 
> territory!
>
http://sel.as-us.falkag.net/sel?cmd=lnk&kid=110944&bid=241720&dat=121642
> _______________________________________________
> Ltp-list mailing list
> Ltp...@li...
> https://lists.sourceforge.net/lists/listinfo/ltp-list
> 
>
______________________________________________________________________
> 
> 
> 
>
______________________________________________________________________


__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com