Messages in this thread | | | Date | Sun, 17 Apr 2011 10:15:40 +0200 | From | Robert Richter <> | Subject | Re: [PATCH 4/4] perf, x86: Fix event scheduler to solve complex scheduling problems |
| |
On 16.04.11 04:51:17, Peter Zijlstra wrote: > Argh, crap. That's because AMD is now the first with overlapping > constraints. Be sure to let your hardware guys know that they went from > top to bottom om my appreciation list. AMD used to have no constraints > and now they have the absolute worst.
Yes, the overlapping constraints are the problem.
> I'd really prefer not to do this for .39, and I'll have to sit down and > actually read this code. It looks like we went from O(n^2) to O(n!) or > somesuch, also not much of an improvement. I'll have to analyze the > solver to see what it does for 'simple' constraints set to see if it > will indeed be more expensive than the O(n^2) solver we had.
It wont be more expensive, if there is a solution. But if there is no one we walk all possible ways now which is something like O(n!).
Yes, we can shift this general solution after .39. Will try to find a solution that handles the special case for family 15h as a fix for .39.
> Also, I think this code could do with a tiny bit of comments ;-)
Will comment on the code inline in the patch.
-Robert
-- Advanced Micro Devices, Inc. Operating System Research Center
| |