On 08/02/14 16:34, Janne Grunau wrote:
> it's not a full code duplication, the version in hpeldsp assumes that
> src stride == dst stride and uses just one stride argument. A function
> call with one argument less might be a worthwhile optimization if the
> function which is hte case for put_pixels
On 2014-02-08 16:12:43 +0100, Diego Biurrun wrote:
> On Sat, Feb 08, 2014 at 02:38:53PM +, Janne Grunau wrote:
> > On 2014-02-06 12:05:16 +0100, Diego Biurrun wrote:
> > > On Thu, Feb 06, 2014 at 08:28:44AM +0100, Anton Khirnov wrote:
> > > > On Wed, 5 Feb 2014 15:32:59 +0100, Diego Biurrun
>
On Sat, Feb 08, 2014 at 02:38:53PM +, Janne Grunau wrote:
> On 2014-02-06 12:05:16 +0100, Diego Biurrun wrote:
> > On Thu, Feb 06, 2014 at 08:28:44AM +0100, Anton Khirnov wrote:
> > > On Wed, 5 Feb 2014 15:32:59 +0100, Diego Biurrun wrote:
> > > > On Wed, Feb 05, 2014 at 09:59:45AM +0100, Anto
On 2014-02-06 12:05:16 +0100, Diego Biurrun wrote:
> On Thu, Feb 06, 2014 at 08:28:44AM +0100, Anton Khirnov wrote:
> > On Wed, 5 Feb 2014 15:32:59 +0100, Diego Biurrun wrote:
> > > On Wed, Feb 05, 2014 at 09:59:45AM +0100, Anton Khirnov wrote:
> > > > --- a/libavcodec/ppc/vp8dsp_altivec.c
> > > >
On 2014-02-06 12:36:03 +0100, Luca Barbato wrote:
> On 06/02/14 12:21, Martin Storsjö wrote:
> > Can we push the plain C half of this commit first without waiting for
> > refactoring the PPC stuff?
>
> Fine for me.
pushed the libavcodec//vp8dsp.c part
Janne
__
On 06/02/14 12:21, Martin Storsjö wrote:
> Can we push the plain C half of this commit first without waiting for
> refactoring the PPC stuff?
Fine for me.
___
libav-devel mailing list
libav-devel@libav.org
https://lists.libav.org/mailman/listinfo/libav-d
On Thu, 6 Feb 2014, Diego Biurrun wrote:
On Thu, Feb 06, 2014 at 08:28:44AM +0100, Anton Khirnov wrote:
On Wed, 5 Feb 2014 15:32:59 +0100, Diego Biurrun wrote:
On Wed, Feb 05, 2014 at 09:59:45AM +0100, Anton Khirnov wrote:
--- a/libavcodec/ppc/vp8dsp_altivec.c
+++ b/libavcodec/ppc/vp8dsp_alt
On Thu, Feb 06, 2014 at 08:28:44AM +0100, Anton Khirnov wrote:
> On Wed, 5 Feb 2014 15:32:59 +0100, Diego Biurrun wrote:
> > On Wed, Feb 05, 2014 at 09:59:45AM +0100, Anton Khirnov wrote:
> > > --- a/libavcodec/ppc/vp8dsp_altivec.c
> > > +++ b/libavcodec/ppc/vp8dsp_altivec.c
> > > @@ -269,9 +269,4
On Wed, 5 Feb 2014 15:32:59 +0100, Diego Biurrun wrote:
> On Wed, Feb 05, 2014 at 09:59:45AM +0100, Anton Khirnov wrote:
> > --- a/libavcodec/ppc/vp8dsp_altivec.c
> > +++ b/libavcodec/ppc/vp8dsp_altivec.c
> > @@ -269,9 +269,44 @@ EPEL_HV(4, 4,6)
> >
> > +static void put_vp8_pixels16_altivec(ui
On Wed, Feb 05, 2014 at 09:59:45AM +0100, Anton Khirnov wrote:
> --- a/libavcodec/ppc/vp8dsp_altivec.c
> +++ b/libavcodec/ppc/vp8dsp_altivec.c
> @@ -269,9 +269,44 @@ EPEL_HV(4, 4,6)
>
> +static void put_vp8_pixels16_altivec(uint8_t *dst, ptrdiff_t dstride,
> uint8_t *src, ptrdiff_t sstride, int
On 05/02/14 09:59, Anton Khirnov wrote:
> +// hand-unrolling the loop by 4 gains about 15%
> +// mininum execution time goes from 74 to 60 cycles
> +// it's faster than -funroll-loops, but using
> +// -funroll-loops w/ this is bad - 74 cycles again.
> +// all this is on a 7450, tuning for the 7450
On Wed, 5 Feb 2014, Anton Khirnov wrote:
From: "Ronald S. Bultje"
Signed-off-by: Anton Khirnov
---
libavcodec/ppc/vp8dsp_altivec.c | 49 +--
libavcodec/vp8dsp.c | 20
2 files changed, 52 insertions(+), 17 deletions(-)
Patch
On Wed, 5 Feb 2014, Anton Khirnov wrote:
From: "Ronald S. Bultje"
Signed-off-by: Anton Khirnov
---
libavcodec/ppc/vp8dsp_altivec.c | 49 +--
libavcodec/vp8dsp.c | 20
2 files changed, 52 insertions(+), 17 deletions(-)
This f
From: "Ronald S. Bultje"
Signed-off-by: Anton Khirnov
---
libavcodec/ppc/vp8dsp_altivec.c | 49 +--
libavcodec/vp8dsp.c | 20
2 files changed, 52 insertions(+), 17 deletions(-)
diff --git a/libavcodec/ppc/vp8dsp_altivec.c b/l
14 matches
Mail list logo