On 2016-11-02 23:14:28 +0200, Martin Storsjö wrote:
> On Wed, 2 Nov 2016, Martin Storsjö wrote:
>
> I'll push the arm version tomorrow unless there's more comments on it.
patch ok. push when you want.
Janne
___
libav-devel mailing list
On Wed, 2 Nov 2016, Martin Storsjö wrote:
+@ Instantiate a horizontal filter function for the given size.
+@ This can work on 4, 8 or 16 pixels in parallel; for larger
+@ widths it will do 16 pixels at a time and loop horizontally.
+@ The actual width is passed in r5, the height in r4 and
+@
On Wed, 2 Nov 2016, Janne Grunau wrote:
On 2016-11-02 13:47:37 +0200, Martin Storsjö wrote:
diff --git a/libavcodec/arm/vp9mc_neon.S b/libavcodec/arm/vp9mc_neon.S
new file mode 100644
index 000..0651ec7
--- /dev/null
+++ b/libavcodec/arm/vp9mc_neon.S
@@ -0,0 +1,764 @@
+
+@ All public
On 2016-11-02 13:47:37 +0200, Martin Storsjö wrote:
...
> ---
> libavcodec/arm/Makefile | 2 +
> libavcodec/arm/vp9dsp_init_arm.c | 140 +++
> libavcodec/arm/vp9mc_neon.S | 764
> +++
> libavcodec/vp9.h | 4 +-
>
This work is sponsored by, and copyright, Google.
The filter coefficients are signed values, where the product of the
multiplication with one individual filter coefficient doesn't
overflow a 16 bit signed value (the largest filter coefficient is
127). But when the products are accumulated, the