On 20/11/14 15:23, Daniel Hellstrom wrote:
On 11/20/2014 03:09 PM, Sebastian Huber wrote:
[...]
The image is a boxplot of all the MaxThreadDispatchDisabledTime samples.
I think this is a nice utility and you seem to be able to update the
results quickly too. Thanks. Since it is the test-sui
On 11/20/2014 03:09 PM, Sebastian Huber wrote:
On 20/11/14 12:36, Daniel Hellstrom wrote:
On 11/20/2014 12:08 PM, Sebastian Huber wrote:
On 20/11/14 10:22, Daniel Hellstrom wrote:
I will fix this. I missed it since it I never enabled RTEMS_PROFILING.
I did a test suite run on NGMP with pr
On 20/11/14 12:36, Daniel Hellstrom wrote:
On 11/20/2014 12:08 PM, Sebastian Huber wrote:
On 20/11/14 10:22, Daniel Hellstrom wrote:
I will fix this. I missed it since it I never enabled RTEMS_PROFILING.
I did a test suite run on NGMP with profiling enabled and your
patches with a local f
On 11/20/2014 12:08 PM, Sebastian Huber wrote:
On 20/11/14 10:22, Daniel Hellstrom wrote:
I will fix this. I missed it since it I never enabled RTEMS_PROFILING.
I did a test suite run on NGMP with profiling enabled and your patches with a local fix. So overall they don't make things worse a
On 20/11/14 10:22, Daniel Hellstrom wrote:
I will fix this. I missed it since it I never enabled RTEMS_PROFILING.
I did a test suite run on NGMP with profiling enabled and your patches
with a local fix. So overall they don't make things worse and the
median of all maximum thread dispatch d
Hi,
I will fix this. I missed it since it I never enabled RTEMS_PROFILING.
Thanks!
Daniel
On 11/20/2014 10:12 AM, Sebastian Huber wrote:
With your patches applied I get a link-time error:
gmake[6]: Entering directory
`/scratch/git-build/b-smp-ngmp/sparc-rtems4.11/c/ngmp/testsuites/samples/h
On 19/11/14 16:35, Daniel Hellstrom wrote:
+ta 9 ! syscall (disable interrupts)
Maybe these magic numbers should get a #define so that you can grep for
it in the sources.
--
Sebastian Huber, embedded brains GmbH
Address : Dornierstr. 4, D-82178 Pu
With your patches applied I get a link-time error:
gmake[6]: Entering directory
`/scratch/git-build/b-smp-ngmp/sparc-rtems4.11/c/ngmp/testsuites/samples/hello'
sparc-rtems4.11-gcc -B../../../../../ngmp/lib/ -specs bsp_specs -qrtems
-DHAVE_CONFIG_H -I.
-I/home/sh/rtems-4.11/c/src/../../testsuit
On 20/11/14 09:01, Daniel Hellstrom wrote:
Also, do these changes complicate the paravirtualization efforts done
with sparc32 for xtratum?
I don't know, I guess it will break. Can you point me to the xtratum
source code I will have a look. Of course I want xtratum to work with
RTEMS/LEON, how
Hi,
On 11/19/2014 08:19 PM, Gedare Bloom wrote:
This one needs a release note as it may impede some applications if
they assumed they could use these trap vectors.
I agree. Where should I update?
Also, do these changes complicate the paravirtualization efforts done
with sparc32 for xtratum?
This one needs a release note as it may impede some applications if
they assumed they could use these trap vectors.
Also, do these changes complicate the paravirtualization efforts done
with sparc32 for xtratum?
Otherwise, quick skim of the patch series looked good.
On Wed, Nov 19, 2014 at 10:35
* Coding style cleanups.
* Use OS reserved trap 0x89 for IRQ Disable
* Use OS reserved trap 0x8A for IRQ Enable
This will result in faster Disable/Enable code since the
system trap handler does not need to decode which function
the user wants. Besides the IRQ disable/enabled can now
be inline whic
12 matches
Mail list logo
