Mailinglist Archive: radeonhd (427 mails)
| < Previous | Next > |
RE: [radeonhd] RS690 full-HD performance
- From: Christian König <deathsimple@xxxxxxxxxxx>
- Date: Wed, 13 May 2009 00:25:01 +0200
- Message-id: <1242167101.6762.8.camel@zweiundvierzig>
Am Dienstag, den 12.05.2009, 18:00 -0400 schrieb Bridgman, John:
successfully so far, but it should be quite simple. It's just an pixel
shader with some cosinus functions, nothing more. You don't even need to
do a FFT, because that's only needed in the encoder part, not at
decoding time.
@Matthias:
I will send you the RS690 HDMI patch tomorrow, don't know if it will
work in all cases, but it's at least a good start.
Bye,
Christian.
--
To unsubscribe, e-mail: radeonhd+unsubscribe@xxxxxxxxxxxx
For additional commands, e-mail: radeonhd+help@xxxxxxxxxxxx
An XvMC implementation would be a good way to get comfortable withI actually tried to implement a iDCT test inside r600demo. Haven't been
shader-processed video,
but the same approach could be used for both motion comp and in-loop
deblocking of H.264, you'd just need a different API.
successfully so far, but it should be quite simple. It's just an pixel
shader with some cosinus functions, nothing more. You don't even need to
do a FFT, because that's only needed in the encoder part, not at
decoding time.
@Matthias:
I will send you the RS690 HDMI patch tomorrow, don't know if it will
work in all cases, but it's at least a good start.
Bye,
Christian.
--
To unsubscribe, e-mail: radeonhd+unsubscribe@xxxxxxxxxxxx
For additional commands, e-mail: radeonhd+help@xxxxxxxxxxxx
| < Previous | Next > |