On Tue, 2005-11-01 at 22:16 +0100, Mark Wielaard wrote:
> That seems like an significant improvement. Could you test with a larger
> dataset (or just run the test in a loop 10 times)? I still haven't tried
> with gcj. If someone could test, that would be super. I believe gcj has
> really slow monitor enter and exit support so the speedup should be
> significant there. But without testing...

In a 10 times loop (fastest of 3 runs):

w/o: 13.92user
w/:  10.14user

Interestingly i get 11 more minor page faults:

w/o: 0inputs+0outputs (0major+2477minor)pagefaults 0swaps
w/:  0inputs+0outputs (0major+2488minor)pagefaults 0swaps

But who cares, it's faster. :-)

TWISTI



_______________________________________________
Classpath-patches mailing list
[email protected]
http://lists.gnu.org/mailman/listinfo/classpath-patches

Reply via email to