This is the mail archive of the
libc-help@sourceware.org
mailing list for the glibc project.
Re: fast additive copy method
- From: "Carlos O'Donell" <carlos at systemhalted dot org>
- To: JoÃl KrÃhemann <weedlight at gmail dot com>
- Cc: "libc-help at sourceware dot org" <libc-help at sourceware dot org>
- Date: Sun, 10 Aug 2014 22:53:09 +0200
- Subject: Re: fast additive copy method
- Authentication-results: sourceware.org; auth=none
- References: <1407648757 dot 15843 dot 2 dot camel at localhost dot localdomain> <CAE2sS1hTvkvkhiUfJS521466W-n2p9MOL+2U-OtJNN=WkFNYxA at mail dot gmail dot com> <1407703436 dot 8772 dot 15 dot camel at localhost dot localdomain>
On Sun, Aug 10, 2014 at 10:43 PM, JoÃl KrÃhemann <weedlight@gmail.com> wrote:
> Hi, I'm doing a soft synth therefore in RAM is copied audio buffers in a
> repining way. The function ags_audio_signal_copy_buffer_to_buffer()
> should be optimized.
There is nothing in glibc that can really help you. It's a compiler
issue at this point. You need to optimize what you're doing to produce
good generated object code. You may be able to vectorize much of this
also, so look into compiler vectorization options and see if you can
get the compiler to vectorize any loops.
Cheers,
Carlos.