[concurrency-interest] Tools for identifying cache misses

Nathan Reynolds nathan.reynolds at oracle.com
Fri Jun 15 14:26:09 EDT 2012


I have never seen any cachegrind reports with processor performance 
counters.  That doesn't mean it can't do it.

One might interpret this page in such a way that Oracle Studio Analyzer 
can capture x86 hardware counters on Linux.  But, it is hard to say. 
https://blogs.oracle.com/openomics/entry/cpu_hardware_counter_stats

You might consider using OProfile. 
http://oprofile.sourceforge.net/news/  It captures processor performance 
counters and is free.

Nathan Reynolds 
<http://psr.us.oracle.com/wiki/index.php/User:Nathan_Reynolds> | 
Consulting Member of Technical Staff | 602.333.9091
Oracle PSR Engineering <http://psr.us.oracle.com/> | Server Technology
On 6/14/2012 10:27 PM, Mohan Radhakrishnan wrote:
> Hi,
>        I am aware of some of the effects  of cache line sharing and 
> padding required to address  it. Are tools like cachegrind advocated 
> to identify these issues ? VTune is expensive and and I remember Sun 
> Studio analyzer wasn't specifically meant for x86 ?
> I am basically working on Capacity Planning by gathering metrics  like 
> this and finding their correlation coefficient for system modeling. 
> This  is  just the context and has  nothing to do with my main question.
> I ask  this because it is related to concurrency.
> Thanks,
> Mohan
>
>
> _______________________________________________
> Concurrency-interest mailing list
> Concurrency-interest at cs.oswego.edu
> http://cs.oswego.edu/mailman/listinfo/concurrency-interest


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.oswego.edu/pipermail/concurrency-interest/attachments/20120615/f8efd776/attachment.html>


More information about the Concurrency-interest mailing list