[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Compilers flags
From: |
Jaroslav Hajek |
Subject: |
Re: Compilers flags |
Date: |
Fri, 14 Jan 2011 16:45:53 +0100 |
On Fri, Jan 14, 2011 at 4:18 PM, CdeMills <address@hidden> wrote:
>
> Hello,
>
> Web pages about High Performance Computing mention gcc flag -ftree-vectorize
> as a performance gain by vectorizing loops. I compiled a version from hg
> tip, configured as
>
> env CFLAGS="-O3 -ftree-vectorize" CXXFLAGS="-O3 -ftree-vectorize"
> FFLAGS="-O3 -ftree-vectorize" ../configure --prefix=$HOME/usr
> --enable-strict-warning-flags
>
> [In most architectures except Power, -ftree-vectorize is implicitelly
> available in -O3 ]
> The tests done on this version were all successfull. Are there some kind of
> benchmarks to quantify the speed gain ?
>
> Regards
>
> Pascal
>
Try the "benchmark" OctaveForge package.
- Compilers flags, CdeMills, 2011/01/14
- Re: Compilers flags,
Jaroslav Hajek <=