Could you please make sure to properly reply to mails in the future?
Otherwise this causes quite a mess to anyone who's viewing the ML in a
threaded view, which includes the list archives.
___
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
http://ffmpe
Hi Oliver,
Yes, for same quality I also noticed a bandwidth usage drop like 4-6%. This
is my case.
But as you know it depends on the samples you work.
For CBR, you are right, it should bring a higher quality. I compared decode
of PSNR for CBR 8 bits and 10 bits HD NVENC HEVC encodded content with
On Fri, Sep 02, 2016 at 15:40:54 +0300, Oliver Collyer wrote:
> In my test, my sample file went from 80mb encoded down to 69mb with
> the same global quality setting. (using -constq -global_quality 21)
I also wonder whether the 10-bit algorithms have the same visual result
as the 8-bit algorithms,
> Just one note; encoding from YUV420P to P010LE is still slow. It will be
> nice a similar patch is done for YUV420P 8bits to P010LE 10 bits
> convertion. (For reason:
> http://x264.nl/x264/10bit_02-ateme-why_does_10bit_save_bandwidth.pdf)
>
Ali
I’m curious as whether you have managed to save
>>>
>>> …or is that really old-school and a modern compiler does all that when
>>> optimising?
>>>
>>> Or is readability considered more important than marginal gains in
>>> performance?
>>>
>>> Oliver (time travelling from the 1980s)
>>
>> You would still have to add the remaining stride.
>> The
Hello Timo,
I tested your patch. It increases UHD HEVC 10 bits Main10 encoding
performance a lot while doing YUV420P10LE to P010LE (same level to Oliver's
original 10 bits HEVC encoding patch).
Your patch together with current FFmpeg git source, encoding performance
increase from 40-42 fps to 69-
> On 2 Sep 2016, at 12:12, Timo Rothenpieler wrote:
>
>> Just sticking my head above the parapet, but shouldn’t things like...
>>
>>> +for (x = 0; x < c->srcW / 2; x++) {
>>> +dstUV[x*2 ] = src[1][x] << 6;
>>> +dstUV[x*2+1] = src[2][x] << 6;
>>> +
> Just sticking my head above the parapet, but shouldn’t things like...
>
>> +for (x = 0; x < c->srcW / 2; x++) {
>> +dstUV[x*2 ] = src[1][x] << 6;
>> +dstUV[x*2+1] = src[2][x] << 6;
>> +}
>
> …be more efficiently written as...
>
> uint16_
Am 02.09.2016 um 11:02 schrieb Michael Niedermayer:
> On Fri, Sep 02, 2016 at 10:38:39AM +0200, Timo Rothenpieler wrote:
+uint16_t *src[] = {
+(uint16_t*)(src8[0] + srcStride[0] * srcSliceY),
+(uint16_t*)(src8[1] + srcStride[1] * srcSliceY),
+(uint16_
On Fri, Sep 02, 2016 at 10:38:39AM +0200, Timo Rothenpieler wrote:
> >> +uint16_t *src[] = {
> >> +(uint16_t*)(src8[0] + srcStride[0] * srcSliceY),
> >> +(uint16_t*)(src8[1] + srcStride[1] * srcSliceY),
> >> +(uint16_t*)(src8[2] + srcStride[2] * srcSliceY)
> >
> > this
>> +uint16_t *src[] = {
>> +(uint16_t*)(src8[0] + srcStride[0] * srcSliceY),
>> +(uint16_t*)(src8[1] + srcStride[1] * srcSliceY),
>> +(uint16_t*)(src8[2] + srcStride[2] * srcSliceY)
>
> this looks odd, why is this needed ?
>
Without it, every
dstY[x] = src[0][x] << 6
On Thu, Sep 01, 2016 at 07:49:38PM +0200, Timo Rothenpieler wrote:
> ---
> libswscale/swscale_unscaled.c | 42 ++
> 1 file changed, 42 insertions(+)
>
> diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
> index b231abe..f47e1f4 10064
Just sticking my head above the parapet, but shouldn’t things like...
> +for (x = 0; x < c->srcW / 2; x++) {
> +dstUV[x*2 ] = src[1][x] << 6;
> +dstUV[x*2+1] = src[2][x] << 6;
> +}
…be more efficiently written as...
uint16_t* tdstUV = dstU
On Thu, Sep 01, 2016 at 06:44:56PM +0200, Timo Rothenpieler wrote:
> On 9/1/2016 6:20 PM, Michael Niedermayer wrote:
> > On Thu, Sep 01, 2016 at 05:23:04PM +0200, Timo Rothenpieler wrote:
> >> ---
> >> libswscale/swscale_unscaled.c | 39 +++
> >> 1 file changed,
---
libswscale/swscale_unscaled.c | 42 ++
1 file changed, 42 insertions(+)
diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
index b231abe..f47e1f4 100644
--- a/libswscale/swscale_unscaled.c
+++ b/libswscale/swscale_unscaled.c
@@ -
On 9/1/2016 6:20 PM, Michael Niedermayer wrote:
> On Thu, Sep 01, 2016 at 05:23:04PM +0200, Timo Rothenpieler wrote:
>> ---
>> libswscale/swscale_unscaled.c | 39 +++
>> 1 file changed, 39 insertions(+)
>>
>> diff --git a/libswscale/swscale_unscaled.c b/libswsca
On Thu, Sep 01, 2016 at 05:23:04PM +0200, Timo Rothenpieler wrote:
> ---
> libswscale/swscale_unscaled.c | 39 +++
> 1 file changed, 39 insertions(+)
>
> diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
> index b231abe..51768fa 100644
---
libswscale/swscale_unscaled.c | 39 +++
1 file changed, 39 insertions(+)
diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
index b231abe..51768fa 100644
--- a/libswscale/swscale_unscaled.c
+++ b/libswscale/swscale_unscaled.c
@@ -197
18 matches
Mail list logo