[PATCH v3 5/7] x86: Optimize strcmp-avx2.S

[Noah Goldstein]

On Tue, Feb 15, 2022 at 7:32 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
>
> On Tue, Feb 15, 2022 at 7:09 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
> >
> > On Tue, Feb 15, 2022 at 6:58 AM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
> > >
> > > On Tue, Feb 15, 2022 at 6:55 AM Andreas Schwab <schwab@linux-m68k.org> wrote:
> > > >
> > > > #0  0x00007f4fd4a61df3 in __strncmp_avx2_w (a=0x55aaa1906ffa "tst-tlsmod%",
> > > >     b=0x55aaa1940fed "tst-tls-manydynamic73mod", c=10)
> > > >     at ../sysdeps/x86_64/multiarch/strncmp-avx2_w.c:11
> > > > 11        if (n1 != n2) asm("hlt");
> > >
> > > I'll check that input thanks!
> > >
> > > One thing, your check has some false positives as all that matters is
> > > n1 / n2 have
> > > same zero/non-zero status or same sign.
> >
> > Confirmed. Sorry for the bug, will ping back when fix is up.
>
> Found a bug (hopefully the bug) in strncmp. Did you see this at all
> in strcmp-avx2 or was it just the commit you were referencing?

Made bugzilla for the one I found at least:
https://sourceware.org/bugzilla/show_bug.cgi?id=28895
> > > >
> > > > --
> > > > Andreas Schwab, schwab@linux-m68k.org
> > > > GPG Key fingerprint = 7578 EB47 D4E5 4D69 2510  2552 DF73 E780 A9DA AEC1
> > > > "And now for something completely different."