Messages in this thread | | | Date | Tue, 29 Mar 2011 08:27:06 +0200 | From | Ingo Molnar <> | Subject | Re: [PATCH 0/6] x86-64: Micro-optimize vclock_gettime |
| |
* Andy Lutomirski <luto@mit.edu> wrote:
> This series speeds up vclock_gettime(CLOCK_MONOTONIC) on by almost 30% > (tested on Sandy Bridge). They're ordered in roughly decreasing order > of improvement. > > These are meant for 2.6.40, but if anyone wants to take some of them > for 2.6.39 I won't object. > > The changes and timings (fastest of 20 trials of 100M iters on Sandy > Bridge) are: > > Unpatched: > > CLOCK_MONOTONIC: 22.09ns > CLOCK_REALTIME_COARSE: 4.23ns > CLOCK_MONOTONIC_COARSE: 5.65ns
[ Patched: ]
> CLOCK_MONOTONIC: 15.66ns > CLOCK_REALTIME_COARSE: 3.44ns > CLOCK_MONOTONIC_COARSE: 4.23ns
That looks like a nice speedup, and speedups are definitely welcome. Many of your speedup patches were framed in an unclean or hard to maintain fashion though - so those have to be improved for this series to become palatable.
Thanks,
Ingo
| |