[1/4] h264/aarch64: sign extend int stride in loop filter asm
diff mbox series

Message ID 20190101225747.17143-1-janne-libav@jannau.net
State New
Headers show
Series
  • [1/4] h264/aarch64: sign extend int stride in loop filter asm
Related show

Commit Message

Janne Grunau Jan. 1, 2019, 10:57 p.m. 
---
 libavcodec/aarch64/h264dsp_neon.S | 3 +++
 1 file changed, 3 insertions(+)

Comments

Martin Storsjo Jan. 2, 2019, 8:04 p.m. | #1 
On Tue, 1 Jan 2019, Janne Grunau wrote:

> ---
> libavcodec/aarch64/h264dsp_neon.S | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/libavcodec/aarch64/h264dsp_neon.S b/libavcodec/aarch64/h264dsp_neon.S
> index 9b4610a4d4..60ffa24500 100644
> --- a/libavcodec/aarch64/h264dsp_neon.S
> +++ b/libavcodec/aarch64/h264dsp_neon.S
> @@ -130,6 +130,7 @@ endfunc
> 
> function ff_h264_h_loop_filter_luma_neon, export=1
>         h264_loop_filter_start
> +        sxtw            x1,  w1
>
>         sub             x0,  x0,  #4
>         ld1             {v6.8B},  [x0], x1
> @@ -210,6 +211,7 @@ endfunc
> 
> function ff_h264_v_loop_filter_chroma_neon, export=1
>         h264_loop_filter_start
> +        sxtw            x1,  w1
>
>         sub             x0,  x0,  x1, lsl #1
>         ld1             {v18.8B}, [x0], x1
> @@ -228,6 +230,7 @@ endfunc
> 
> function ff_h264_h_loop_filter_chroma_neon, export=1
>         h264_loop_filter_start
> +        sxtw            x1,  w1
>
>         sub             x0,  x0,  #2
>         ld1             {v18.S}[0], [x0], x1
> -- 
> 2.20.1

LGTM

// Martin

Patch
diff mbox series 

diff --git a/libavcodec/aarch64/h264dsp_neon.S b/libavcodec/aarch64/h264dsp_neon.S
index 9b4610a4d4..60ffa24500 100644
--- a/libavcodec/aarch64/h264dsp_neon.S
+++ b/libavcodec/aarch64/h264dsp_neon.S
@@ -130,6 +130,7 @@  endfunc
 
 function ff_h264_h_loop_filter_luma_neon, export=1
         h264_loop_filter_start
+        sxtw            x1,  w1
 
         sub             x0,  x0,  #4
         ld1             {v6.8B},  [x0], x1
@@ -210,6 +211,7 @@  endfunc
 
 function ff_h264_v_loop_filter_chroma_neon, export=1
         h264_loop_filter_start
+        sxtw            x1,  w1
 
         sub             x0,  x0,  x1, lsl #1
         ld1             {v18.8B}, [x0], x1
@@ -228,6 +230,7 @@  endfunc
 
 function ff_h264_h_loop_filter_chroma_neon, export=1
         h264_loop_filter_start
+        sxtw            x1,  w1
 
         sub             x0,  x0,  #2
         ld1             {v18.S}[0], [x0], x1