ANNOUNCEMENT: Live Wireshark University & Allegro Packets online APAC Wireshark Training Session
April 17th, 2024 | 14:30-16:00 SGT (UTC+8) | Online

Wireshark-dev: Re: [Wireshark-dev] Profiling results with optimized function ws_mempbrk_sse42()

From: Anders Broman <a.broman58@xxxxxxxxx>
Date: Thu, 5 Jun 2014 00:03:50 +0200


Den 4 jun 2014 23:29 skrev "Jakub Zawadzki" <darkjames-ws@xxxxxxxxxxxx>:
>
> Hi,
>
> On Wed, Jun 04, 2014 at 11:24:59AM +0000, Anders Broman wrote:
> > I did a test with
> > static inline const guint8*
> > guint8_pbrk(const guint8* haystack, size_t haystacklen _U_, const guint8 *needles, guchar *found_needle)
> > {
> >                 const guint8 *result = (const guint8 *)strpbrk(haystack, needles);
> >
> >                 if (result && found_needle)
> >                                 *found_needle = *result;
> >
> >                 return result;
> > }
> >
> > Which seems to give as good results on Ubuntu 13.10, it ends up using __strpbrk_sse42 (libc-2.17.so: strcspn-c.c, ...)
> > ==29458==
> > ==29458== Events    : Ir
> > ==29458== Collected : 21130728727
> > ==29458==
> > ==29458== I   refs:      21,130,728,727
> > Load time in WS 0:19.300
>
> Yep, ws_mempbrk_sse42() is based on __strpbrk_sse42(), and it should give similar results.
> Still we must have binary (string, length) search, and strpbrk() works correctly only for NUL terminated string.
> Our tvb's are not NUL terminated, and strpbrk() won't skip over NULs, so we need some modification.
>
> Cheers,
> Jakub.

Yeah,
I realised after writing The mail.
Anders
> ___________________________________________________________________________
> Sent via:    Wireshark-dev mailing list <wireshark-dev@xxxxxxxxxxxxx>
> Archives:    http://www.wireshark.org/lists/wireshark-dev
> Unsubscribe: https://wireshark.org/mailman/options/wireshark-dev
>              mailto:wireshark-dev-request@xxxxxxxxxxxxx?subject=unsubscribe