This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [RFC] [BZ15384] Enchance finite and isfinite.
- From: OndÅej BÃlka <neleai at seznam dot cz>
- To: David Miller <davem at davemloft dot net>
- Cc: marc dot glisse at inria dot fr, libc-alpha at sourceware dot org
- Date: Fri, 26 Apr 2013 10:43:23 +0200
- Subject: Re: [RFC] [BZ15384] Enchance finite and isfinite.
- References: <20130421145745 dot GA15025 at domone dot kolej dot mff dot cuni dot cz> <alpine dot DEB dot 2 dot 02 dot 1304212033480 dot 19747 at laptop-mg dot saclay dot inria dot fr> <20130426061732 dot GA6475 at domone dot kolej dot mff dot cuni dot cz> <20130426 dot 030300 dot 673818092125010772 dot davem at davemloft dot net>
On Fri, Apr 26, 2013 at 03:03:00AM -0400, David Miller wrote:
> From: OndÅej BÃlka <neleai@seznam.cz>
> Date: Fri, 26 Apr 2013 08:17:32 +0200
>
> > Following should generic version be tried on other archs. I could get
> > 20% speedup on sparc on this benchmark.
> >
> > run with
> > for i in `seq 0 7`; do echo finite$i; gcc finite_bench.c -O3 -Wall -W -fno-builtin-finite -Dfinite=finite$i; for j in `seq 1 8`; do /usr/bin/time -f "%U" ./a.out; done; done
>
> That'll only be faster on sparc 32-bit where floating point
> values are passed in integer registers.
>
> For 64-bit, where floating point values are passed in floating point
> registers, the assembler in glibc will always be faster because GCC
> isn't smart enough to avoid allocating a register window when a stack
> slot is needed to move values between float and integer registers.
My benchmark tries to measure speed of inlined version when used in
condition. As 99% of uses are in condition this looks reasonable. Idealy
gcc should simplify condition based on expansion and have it smaller
than function call.
> Also, the sparc 64-bit multiarch variants make use of the VIS3
> float-int move instructions when available.
Without testing I do not know how much this helps.