On Thursday May 14 2015 16:55:35 René J.V. Bertin wrote:
Audio being in essence 1D data (time series) it should be relatively easy to
deploy template libraries that provide array/vector types the use optimised
SIMD instructions internally. With those you should be able to do better than
with au
Thanks for all the insights so far.
I confess i’m a newbie regarding performance optimisation. I’m writing a
synthesiser. It’s computing audio on a real time basis and it’s already getting
heavy for 8 voices of polyphony. It’s making an iPad 2 work on the limit which
is not good, specially whe
On Thursday 14 May 2015 14:52:45 Allan Sandfeld Jensen wrote:
> Alternatively use vector intrinsics, but the generic intrinsics are not
> that powerful.
>
> To write in a way that the compiler can auto-vectorize, write the CPU
> intensive work in simple inner loops without function calls (or onl
On Thursday May 14 2015 14:52:45 Allan Sandfeld Jensen wrote:
> Alternatively use vector intrinsics, but the generic intrinsics are not that
> powerful.
To put that in perspective:
there's a yuv4xx conversion routine I once used, I think it's from FFmpeg,
which has a hand-optimised SSE2 versio
On Thursday 14 May 2015, Nuno Santos wrote:
> Hi,
>
> Sorry if the title is not the most appropriated.
>
> I’m developing an app that will be target for iOS/Android/x86/x86_64
>
> Since this is CPU intensive application I think that I will reach a point
> were assembly and vector instructions wi
On Thu, May 14, 2015 at 6:39 AM Nuno Santos
wrote:
> Hi,
>
> Sorry if the title is not the most appropriated.
>
> I’m developing an app that will be target for iOS/Android/x86/x86_64
>
> Since this is CPU intensive application I think that I will reach a point
> were assembly and vector instructi
Hi,
Sorry if the title is not the most appropriated.
I’m developing an app that will be target for iOS/Android/x86/x86_64
Since this is CPU intensive application I think that I will reach a point were
assembly and vector instructions will be needed for maximum performance.
Since ARM and x86 in
