I committed some code that should fix the timer problems on SPARC
linux. Can you either svn up and try again (or, if you are using
nightly builds) try tomorrow's tarball and see if it works? The test
tests/util/opal_timer.c should give an indication as to whether
everything is working ok or not.
Thanks!
Brian
On Sep 12, 2005, at 2:04 PM, Ferris McCormick wrote:
On Mon, 2005-09-12 at 13:34 -0500, Brian Barrett wrote:
Ok, I see what's happening, although I'm not sure the two problems
are actually related. The first is that the component to provide
high resolution timer support on Linux is disabling itself because:
1) it doesn't know how to figure out the clock rate of the CPU
2) there's no assembly for reading a CPU counter on SPARC chips
The only reliable way to get CPU frequency is reading /proc/cpuinfo,
and for Linux, each architecture seems to have a different format.
So that part's covered with the information provided below. Now I
just need to figure out how to get cycle counts out of a SPARC. So
much easier on Solaris ;).
Brian
Some information that might help:
The SB1000 is a (2x900MHz) Ultrasparc III, the second system is a
(2x400MHz) Ultrasparc II. The SB1000 is well over twice as fast as
the
U2.
Here is a (2x450MHz) Ultrasparc II (U60 system):
====================================================
fmccor@antaresia openmpi-1.0a1r7305 [33]% cat /proc/cpuinfo
cpu : TI UltraSparc II (BlackBird)
fpu : UltraSparc II integrated FPU
promlib : Version 3 Revision 29
prom : 3.29.0
type : sun4u
ncpus probed : 2
ncpus active : 2
Cpu0Bogo : 897.84
Cpu0ClkTck : 000000001ad2f5d5
Cpu2Bogo : 897.84
Cpu2ClkTck : 000000001ad2f5d5
MMU Type : Spitfire
State:
CPU0: online
CPU2: online
========================================================
I think what you need to look at is the 'Cpu?ClkTck' values, if
900 --> 0000000035a4e900
450 --> 000000001ad2f5d5
400 --> 0000000017d746a8
is useful.
If you need more, you can try joining #gentoo-sparc on IRC freenode
and
explaining exactly what you need; there are people there who probably
can help. At this point, though, I am giving you more than I know,
which can always be misleading.
Here's /proc/cpuinfo from the SB1000:
=====================================
fmccor@polylepis AGT [93]% cat /proc/cpuinfo
cpu : TI UltraSparc III (Cheetah)
fpu : UltraSparc III integrated FPU
promlib : Version 3 Revision 13
prom : 4.13.0
type : sun4u
ncpus probed : 2
ncpus active : 2
Cpu0Bogo : 598.01
Cpu0ClkTck : 0000000035a4e900
Cpu1Bogo : 598.01
Cpu1ClkTck : 0000000035a4e900
MMU Type : Cheetah
State:
CPU0: online
CPU1: online
========================================
====================================
Other failing system:
fmccor@lacewing openmpi-1.0a1r7305 [96]% cat /proc/cpuinfo
cpu : TI UltraSparc II (BlackBird)
fpu : UltraSparc II integrated FPU
promlib : Version 3 Revision 19
prom : 3.19.0
type : sun4u
ncpus probed : 2
ncpus active : 2
Cpu0Bogo : 799.53
Cpu0ClkTck : 0000000017d746a8
Cpu1Bogo : 799.53
Cpu1ClkTck : 0000000017d746a8
MMU Type : Spitfire
State:
CPU0: online
CPU1: online
===========================
Regards,
--
Ferris McCormick (P44646, MI) <fmc...@gentoo.org>
Developer, Gentoo Linux (Sparc, Devrel)
_______________________________________________
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel
