Re: MVME3100 FPU Support on RTEMS 4.10.2

[Joel Sherrill <joel@rtems.org>]

On Thu, Jun 7, 2018 at 8:26 AM, Gedare Bloom <gedare@rtems.org> wrote:

On Wed, Jun 6, 2018 at 10:35 PM, Heinz Junkes <junkes@fhi-berlin.mpg.de> wrote:
> There is RTEMS 5 support for the MVME2500 made by Sebastian Huber.
> Unfortunately, I have not been able to test it properly with EPICS7.
> I will try it after the Epics meeting and will report.
>

The BSP support for mvme2500 is in the qoriq family of powerpc BSPs. I
have no clue how difficult it would be to use with 4.10. The APU route
suggested by Till is probably ideal unless you need 'double' types...

If you want to use that BSP, I recommend upgrading RTEMS. There are

a lot of differences between 4.10 and the master including SMP, BSP

infrastructure improvement, and even qoriq support itself. 

I think it would be much less work to update RTEMS than to backport 

the BSP.

--joel

 

Gedare

> Heinz
>
>> On 6. Jun 2018, at 23:24, Matt Rippa <mrippa@gemini.edu> wrote:
>>
>> Thanks for the fast reply. Of all the mvme boards you listed,
>> the 3100 hits a nice price point and we're attempting to find
>> suitable replacement stock (quantity 30+) for the 2700 which are no longer
>> manufactured.
>>
>> Are the 6100 boards on beatnik bsp the only remaining option for RTEMS?
>> They cost nearly twice as much and have shown thermal regulation issues.
>>
>> -Matt
>>
>> On Wed, Jun 6, 2018 at 11:10 AM, Michael Davidsaver <mdavidsaver@ospreydcs.com> wrote:
>> Hi Matt,
>>
>> The MVME3100 is based on the MPC8540 processor.  This chip doesn't have an FPU.
>> Other boards do (eg. mvme270x, mvme6100, or mvme2500) and RTEMS supports this.
>>
>> I can certainly confirm that lack of an FPU really hurts performance, even
>> something as (apparently) simple as integer to float.
>>
>> Michael
>>
>>
>> On 06/06/2018 02:03 PM, Matt Rippa wrote:
>> > It appears we've compiled our mvme3100 bsp without FPU support.
>> > We're on the mvme3100 running EPICS 3.14.12.7 and RTEMS 4.10.2.
>> >
>> > We're attempting to commission our astrometric kernel control system
>> > and we've run into trouble meeting some of our thread deadlines. What
>> > we've found is a transform routine that takes our mvme2700 ~200 us,
>> > takes the mvme3100 ~8 ms.  So not a surprise to see this with only "-msoft-float"?
>> >
>> > ...
>> > 2018-05-31-tcs.log:May 31 11:41:15  E) PORT: tcs_vme, MSG: Welcome to rtems-4.10.2(PowerPC/Generic (*no FPU*)/mvme3100)
>> >
>> > Is FPU support possible with RTEMS 4.10.2? If so, what would we need to do?
>> > It looks like there's a multilib on 4.11.2 https://docs.rtems.org/releases/rtems-docs-4.11.2/cpu-supplement/powerpc.html#multilibs(*Eg., see #13* )
>> >
>> > Here's our bsp specs:
>> >
>> > beatnik:
>> > -specs bsp_specs -qrtems -fasm -c -mcpu=7400 -D__ppc_generic -DUNIX -O2 -g -g -Wall
>> > (mvme2700) mvme-2307:
>> > -specs bsp_specs -qrtems -fasm -c -mcpu=604 -mmultiple -mstring -mstrict-align -meabi -DUNIX -O2 -g -g -Wall
>> > mvme-3100
>> > -specs bsp_specs -qrtems -fasm -c -mcpu=powerpc *-msoft-float* -D__ppc_generic -DUNIX -O2 -g -g -Wall
>> >
>> > Thank you!
>> > -Matt
>> >
>>
>>
>>
>> --
>>
>> ----------------------------------------------------------------------
>> Das FHI verarbeitet, speichert und loescht Daten im Rahmen seiner
>> Geschaeftstaetigkeit gemaess der Datenschutz-Grundverordnung (DSGVO)
>> [General Data Protection Regulation (GDPR)] der Europaeischen Union.
>>
>
>
> ----------------------------------------------------------------------
> Das FHI verarbeitet, speichert und loescht Daten im Rahmen seiner
> Geschaeftstaetigkeit gemaess der Datenschutz-Grundverordnung (DSGVO)
> [General Data Protection Regulation (GDPR)] der Europaeischen Union.
>
>

> _______________________________________________
> users mailing list
> users@rtems.org
> http://lists.rtems.org/mailman/listinfo/users
_______________________________________________
users mailing list
users@rtems.org
http://lists.rtems.org/mailman/listinfo/users