Hi,
I've tried pfmon-3.9/libpfmon-3.9 , but failed too.
[r...@localhost tests]# ldd /usr/local/bin/pfmon
linux-vdso.so.1 => (0x7fffa4bfe000)
libpthread.so.0 => /lib64/libpthread.so.0 (0x0034bbe0)
libm.so.6 => /lib64/libm.so.6 (0x0034bb60)
librt
Hi,
noploop is comliled like this.
[r...@localhost tests]# file noploop
noploop: ELF 64-bit LSB executable, AMD x86-64, version 1 (SYSV), for
GNU/Linux 2.6.9, dynamically linked (uses shared libs), for GNU/Linux
2.6.9, not stripped
On 07/12/2010 08:59 PM, stephane eranian wrote:
> Corey,
>
> Back from vacation.
>
> With what is currently in CVS do you pass the tests for Power?
Yes, there are no problems that I know of for Power in the code in CVS.
Thanks for asking.
- Corey
Hi,
I want to compare performance on POWER6 and Xeon X5355.
Basically I want to do the following with pfmon:
Over a long time periode I want to collect all available performance counter
for analysis.
Are performance counter grouped?
How can I do this for Xeon?
Hi,
I want to compare performance on POWER6 and Xeon X5355.
Basically I want to do the following with pfmon:
Over a long time periode I want to collect all available performance counter
for analysis system-wide.
Are performance counter grouped?
How can I do this for Xeon?
Any best-practices?
--
Hi,
I use pfmon3.9/libpfm3.9,
I want to collect the number of L2 misses every million instructions.
But I got two errors.
First, LAST_LEVEL_CACHE_MISSES was not counted at all !!! pfmon outputs zero
for the second counting event.
Secondly, when tasks was cloned , pfmon encounters lack of memory
