Hi Philippe,
We have performed some test with the patch and everything is OK.
We got the same latencies than before; we're now investigating what is
the cause of some occasional peaks to 40-50 us.
Daniel
Message d'origine
De: Philippe Gerum [mailto:[EMAIL PROTECTED]
Date: lun
This adds powerpc version of fptest.h. It just stores and loads the raw
integer into/from FPU registers without converting to proper IEEE form.
Converting would have added unneccessary complexity. As a side note, the
ppc barfs on the test with "1000 != 10". :I
-- hl
diff -Nru xenomai.orig/incl
Hi,
I guess this is more like what check-in #1185 wanted to achieve:
--- src/skins/vrtx/task.c (Revision 1186)
+++ src/skins/vrtx/task.c (Arbeitskopie)
@@ -247,5 +247,6 @@ void sc_unlock (void)
void sc_delay (long timeout)
{
XENOMAI_SKINCALL1(__vrtx_muxid,
-
Heikki Lindholm wrote:
> This adds powerpc version of fptest.h. It just stores and loads the raw
> integer into/from FPU registers without converting to proper IEEE form.
> Converting would have added unneccessary complexity. As a side note, the
> ppc barfs on the test with "1000 != 10". :I
Hi Philippe
Your change seems to be broken (at least on PPC). In
http://ngiger.dyndns.org/buildbot/hcu3/builds/71/step-mk_xeno/0
you will notice near the end
gcc -DHAVE_CONFIG_H -I. -I../../../../../build/xenomai/src/skins/vrtx
-I../../../src/include -O2 -D_GNU_SOURCE -D_REENTRANT -D__XENO__ -
Gilles Chanteperdrix kirjoitti:
Heikki Lindholm wrote:
> This adds powerpc version of fptest.h. It just stores and loads the raw
> integer into/from FPU registers without converting to proper IEEE form.
> Converting would have added unneccessary complexity. As a side note, the
> ppc barfs
Niklaus Giger wrote:
Hi Philippe
Your change seems to be broken (at least on PPC). In
http://ngiger.dyndns.org/buildbot/hcu3/builds/71/step-mk_xeno/0
you will notice near the end
gcc -DHAVE_CONFIG_H -I. -I../../../../../build/xenomai/src/skins/vrtx -I../../../src/include -O2 -D_GNU_SOURCE -D
Jan Kiszka wrote:
Hi,
I guess this is more like what check-in #1185 wanted to achieve:
--- src/skins/vrtx/task.c (Revision 1186)
+++ src/skins/vrtx/task.c (Arbeitskopie)
@@ -247,5 +247,6 @@ void sc_unlock (void)
void sc_delay (long timeout)
{
XENOMAI_SKINCALL1(__vrtx_muxid,
-
Philippe Gerum wrote:
> Jan Kiszka wrote:
>> Philippe Gerum wrote:
>>
>>> Hi Jan,
>>>
>>> Based on your previous work, here is a set of patches coupling KGDB and
>>> the I-pipe. Basically, I've attempted to shrink the extra patches needed
>>> against the original KGDB + I-pipe ones to the bare mini