Re: Execution Time of Whetstone on LEON3

[Joel Sherrill]

On Thu, May 4, 2017 at 12:34 AM, Sebastian Huber <
sebastian.hu...@embedded-brains.de> wrote:

> On 03/05/17 22:52, Joel Sherrill wrote:
>
>> Has anyone run the whetstone benchmark on real leon3 HW?
>> I'm almost at 20 minutes of simulated CPU time on tsim so
>> am suspicious something is wrong.
>>
>> Any ideas?
>>
>
> Maybe soft-float plus a low CPU frequency? Do you have a function
> profiling histogram of the execution?
>
>
It is the default leon3 build and the leon3 is simulated at 50Mhz.  I have
never used profiling on tsim. Any guidance?

The test  did finally finish and here is the output of tsim's perf command:

*** END OF TEST WHETSTONE ***

Program exited normally.
tsim> perf


 Cycles   : 7446273
 Instructions : 45632185502
 Overall CPI  :  1.63

 CPU performance (50.0 MHz)  : 30.64 MOPS (30.64 MIPS,  0.00 MFLOPS)
 Cache hit rate  : 98.0 % (inst: 97.9, data:99.7)
 AHB bandwidth utilisation   : 34.8 % (inst: 14.1, data: 20.8)
 Simulated time  : 1489.25 s
 Processor utilisation   : 100.00 %
 Real-time performance   : 122.02 %
 Simulator performance   :  37.39 MIPS
 Used time (sys + user)  : 1220.46 s

So it just took a LONG time.

--joel



> --
> Sebastian Huber, embedded brains GmbH
>
> Address : Dornierstr. 4, D-82178 Puchheim, Germany
> Phone   : +49 89 189 47 41-16
> Fax : +49 89 189 47 41-09
> E-Mail  : sebastian.hu...@embedded-brains.de
> PGP : Public key available on request.
>
> Diese Nachricht ist keine geschäftliche Mitteilung im Sinne des EHUG.
>
>
___
devel mailing list
devel@rtems.org
http://lists.rtems.org/mailman/listinfo/devel

Re: Execution Time of Whetstone on LEON3

[Jiri Gaisler]

On 05/04/2017 04:00 PM, Joel Sherrill wrote:



On Thu, May 4, 2017 at 12:34 AM, Sebastian Huber 
> wrote:


On 03/05/17 22:52, Joel Sherrill wrote:

Has anyone run the whetstone benchmark on real leon3 HW?
I'm almost at 20 minutes of simulated CPU time on tsim so
am suspicious something is wrong.

Any ideas?


Maybe soft-float plus a low CPU frequency? Do you have a function
profiling histogram of the execution?


It is the default leon3 build and the leon3 is simulated at 50Mhz.  I 
have

never used profiling on tsim. Any guidance?

The test  did finally finish and here is the output of tsim's perf 
command:


*** END OF TEST WHETSTONE ***

Program exited normally.
tsim> perf
 Cycles   : 7446273
 Instructions : 45632185502
 Overall CPI  :  1.63

 CPU performance (50.0 MHz)  : 30.64 MOPS (30.64 MIPS,  0.00 MFLOPS)
 Cache hit rate  : 98.0 % (inst: 97.9, data:99.7)
 AHB bandwidth utilisation   : 34.8 % (inst: 14.1, data: 20.8)
 Simulated time  : 1489.25 s
 Processor utilisation   : 100.00 %
 Real-time performance   : 122.02 %
 Simulator performance   :  37.39 MIPS
 Used time (sys + user)  : 1220.46 s

So it just took a LONG time.

--joel


Note that TSIM reports 0.0 MFLOPS. This means that soft-float was used 
to compile the benchmark. Using hard-float should give about 100x 
speed-up ...


Jiri.


___
devel mailing list
devel@rtems.org
http://lists.rtems.org/mailman/listinfo/devel

Re: Execution Time of Whetstone on LEON3

[Joel Sherrill]

On Thu, May 4, 2017 at 2:27 PM, Jiri Gaisler  wrote:

>
>
> On 05/04/2017 04:00 PM, Joel Sherrill wrote:
>
>
>
> On Thu, May 4, 2017 at 12:34 AM, Sebastian Huber <
> sebastian.hu...@embedded-brains.de> wrote:
>
>> On 03/05/17 22:52, Joel Sherrill wrote:
>>
>>> Has anyone run the whetstone benchmark on real leon3 HW?
>>> I'm almost at 20 minutes of simulated CPU time on tsim so
>>> am suspicious something is wrong.
>>>
>>> Any ideas?
>>>
>>
>> Maybe soft-float plus a low CPU frequency? Do you have a function
>> profiling histogram of the execution?
>>
>>
> It is the default leon3 build and the leon3 is simulated at 50Mhz.  I have
> never used profiling on tsim. Any guidance?
>
> The test  did finally finish and here is the output of tsim's perf command:
>
> *** END OF TEST WHETSTONE ***
>
> Program exited normally.
> tsim> perf
>
>
>  Cycles   : 7446273
>  Instructions : 45632185502
>  Overall CPI  :  1.63
>
>  CPU performance (50.0 MHz)  : 30.64 MOPS (30.64 MIPS,  0.00 MFLOPS)
>  Cache hit rate  : 98.0 % (inst: 97.9, data:99.7)
>  AHB bandwidth utilisation   : 34.8 % (inst: 14.1, data: 20.8)
>  Simulated time  : 1489.25 s
>  Processor utilisation   : 100.00 %
>  Real-time performance   : 122.02 %
>  Simulator performance   :  37.39 MIPS
>  Used time (sys + user)  : 1220.46 s
>
> So it just took a LONG time.
>
> --joel
>
>
> Note that TSIM reports 0.0 MFLOPS. This means that soft-float was used to
> compile the benchmark. Using hard-float should give about 100x speed-up ...
>
> Thanks. I wonder if we should have a leon3 variant with hardware FPU
enabled.

--joel


> Jiri.
>
>
>
___
devel mailing list
devel@rtems.org
http://lists.rtems.org/mailman/listinfo/devel