Messages in this thread | | | Date | Fri, 2 May 2003 02:10:50 +0200 | From | Willy Tarreau <> | Subject | Re: [RFC][PATCH] Faster generic_fls |
| |
On Fri, May 02, 2003 at 01:27:16AM +0200, Thomas Schlichter wrote:
> So for me the table version seems to be the slowest one. The BSRL instruction > on the K6-III seems to be very slow, too. The tree and my shift version are > faster than the original version here... > > That someone else can test my fls_shift version I'll provide it here again:
That's interesting Thomasr. I get 18.4 s on the Athlon here vs 32.3 for Daniel's (I have broken my function at the moment so I cannot re-bench it right now, but it should be near Daniel's). At first, I thought you had coded an FFS instead of an FLS. But I realized it's valid, and is fast because one half of the numbers tested will not even take one iteration.
Regards, Willy
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |