Message102508
| Author |
pitrou |
| Recipients |
beazley, dabeaz, flox, kristjan.jonsson, loewis, pitrou, torsten |
| Date |
2010年04月07日.00:11:55 |
| SpamBayes Score |
5.062128e-06 |
| Marked as misclassified |
No |
| Message-id |
<1270599234.3518.65.camel@localhost> |
| In-reply-to |
<1270597990.96.0.191599968356.issue8299@psf.upfronthosting.co.za> |
| Content |
> The counter is "stall cycles".
> During the 10 second run on my 2.4Ghz cpu, we had instruction cache
> miss stalls for 2 billion cycles (2000 samples of 1000000 cycles per
> sample). That does account for around 10% of the availible cpu.
Ok, thanks.
> 2) The poor performance of competing CPU threads on multicore machines
> is due to the instruction cache behaviour of non-overlapping thread
> execution on different cores.
Have you tried your measurement approach with ccbench?
> We can fix 1) easily, even with a much less invasive patch than the
> ones I have put in here. I'm a bit surprised at the apparent
> disinterest in such an obvious bug / fix.
As already said, it's too late for 2.7. And the fix in 3.2 is most
probably better. |
|