Messages in this thread | | | Subject | Re: [PATCH] speed up on find_first_bit for i386 (let compiler do the work) | From | Steven Rostedt <> | Date | Thu, 28 Jul 2005 12:57:28 -0400 |
| |
On Thu, 2005-07-28 at 17:34 +0100, Maciej W. Rozycki wrote:
> Since you're considering GCC-generated code for ffs(), ffz() and friends, > how about trying __builtin_ffs(), __builtin_clz() and __builtin_ctz() as > apropriate? Reasonably recent GCC may actually be good enough to use the > fastest code depending on the processor submodel selected.
I can change the find_first_bit to use __builtin_ffs, but how would you implement the ffz? The clz and ctz only count the number of leading or trailing zeros respectively, it doesn't find the first zero. Of course a __builtin_ctz(~x) would but this might take longer than what we already have. I'll go ahead and try it and see. But I still don't have a decent benchmark on this. I'll start looking into the kernel and see how it's used, and see if I can find a proper benchmark.
-- Steve
- 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/
| |