A GPU is better suited to some kinds of massively parallel tasks, like video encoding. After all, you're applying various matrix transforms to an image, with a bunch of funky floating point math to whittle all that transformed data down to its most significant/perceptible bits. GPUs are supposed to be really really good at this sort of thing.
And there's your problem.
An h.264 encoder takes a frame of video and splits it up into 16x16 pixel macroblocks. Each macroblock is heavily dependent on those surrounding it (spatially and temporally). For an intra block, a prediction of the content of the current block is made using the decoded content of the top and left blocks. For inter blocks, a previous frame is used as a reference. The decoder has no idea what the original source file looked like, so any predictions made in the encoding process must be from the decoded frames. This leads to massive data dependencies in the encoder which cause a cascade of blocks that need to be encoded before the current block can be.
Many, many, people have come onto #x264dev and tried implementing GPU accelerated encoding, some of them with impressive backgrounds. All of them left once they realised how difficult this problem is.
The raspberry pi is meant to introduce programming concepts to school-level children.
My question is: How are you planning on doing this from a UI perspective? The BBC micro (as far as I can tell, a little before my time) simply dropped the user into a BASIC prompt and left the rest to their imagination. This seems like a pretty fundamental design question for the raspberry pi, but I haven't been able to find a clear answer yet.
What about something like an android phone, they come with GPS. Then you also have a pretty cool phone to go along with it. I have no idea what apps there are for mapping but I would hope there would be something good by now.
If we have to choose between spending a trillion dollars now and spending a trillion fifty years from now, which should we do?
I think you've got the wrong idea.
The Stern Review came to the conclusion that the benefits of strong, early action on climate change considerably outweigh the costs. Waiting fifty years might be the worst thing we could do.
Biased, I know, but here's what an x264 developer had to say in response.
Quote:
They apparently used the worst possible x264 settings (yes, subme 0 and so forth) in order to make Theora look better--if Theora didn't win such a test I would be shocked indeed! Instead, they just proved the fact that they're a bunch of liars who are no better than the worst of the proprietary companies they claim to compete against.
I have a lot more respect for the BBC after checking out their high definition service. As high definition is just kicking off in the UK they have had the opportunity to use the very latest h264 standards. They show programmes in 1080p at around 16Mb/s which looks great on a decent tv.
Looking at providers in the US it seems they're stuck with outdated mpeg2 standards which really doesn't do anything for the picture at low bitrates.
The only trouble is that hardly anything is filmed in HD in the UK. NOTE TO BBC: I want to see Jeremy Clarkson being eaten by dogs in full 1080p glory!
The only reason I bought a Zune was because I thought it would have linux on it a few months after launch. I thought to myself "Ipod fans have had Rockbox and ipodlinux for ages so why not Zune?". Big mistake.
Microsoft have gone out of their way to prevent third party firmware being loaded on by only accepting Microsoft signed firmware. Its such a shame. Think about what could be done: wireless syncing, actually sharing songs between other Zune users (not that 3 songs in 3 days crap), gapless playback, proper video format support (not just wmv) etc. It could have been good...
Slashdot Mirror
A GPU is better suited to some kinds of massively parallel tasks, like video encoding. After all, you're applying various matrix transforms to an image, with a bunch of funky floating point math to whittle all that transformed data down to its most significant/perceptible bits. GPUs are supposed to be really really good at this sort of thing.
And there's your problem.
An h.264 encoder takes a frame of video and splits it up into 16x16 pixel macroblocks. Each macroblock is heavily dependent on those surrounding it (spatially and temporally). For an intra block, a prediction of the content of the current block is made using the decoded content of the top and left blocks. For inter blocks, a previous frame is used as a reference. The decoder has no idea what the original source file looked like, so any predictions made in the encoding process must be from the decoded frames. This leads to massive data dependencies in the encoder which cause a cascade of blocks that need to be encoded before the current block can be.
Many, many, people have come onto #x264dev and tried implementing GPU accelerated encoding, some of them with impressive backgrounds. All of them left once they realised how difficult this problem is.
The raspberry pi is meant to introduce programming concepts to school-level children.
My question is: How are you planning on doing this from a UI perspective? The BBC micro (as far as I can tell, a little before my time) simply dropped the user into a BASIC prompt and left the rest to their imagination. This seems like a pretty fundamental design question for the raspberry pi, but I haven't been able to find a clear answer yet.
How upgrading the cameras before worrying about higher resolution displays? BBC still shoot in 720p for some things.
What about something like an android phone, they come with GPS. Then you also have a pretty cool phone to go along with it. I have no idea what apps there are for mapping but I would hope there would be something good by now.
I think you've got the wrong idea.
The Stern Review came to the conclusion that the benefits of strong, early action on climate change considerably outweigh the costs.
Waiting fifty years might be the worst thing we could do.
Biased, I know, but here's what an x264 developer had to say in response.
Quote: They apparently used the worst possible x264 settings (yes, subme 0 and so forth) in order to make Theora look better--if Theora didn't win such a test I would be shocked indeed! Instead, they just proved the fact that they're a bunch of liars who are no better than the worst of the proprietary companies they claim to compete against.
I have a lot more respect for the BBC after checking out their high definition service. As high definition is just kicking off in the UK they have had the opportunity to use the very latest h264 standards. They show programmes in 1080p at around 16Mb/s which looks great on a decent tv.
Looking at providers in the US it seems they're stuck with outdated mpeg2 standards which really doesn't do anything for the picture at low bitrates.
The only trouble is that hardly anything is filmed in HD in the UK. NOTE TO BBC: I want to see Jeremy Clarkson being eaten by dogs in full 1080p glory!
Although, when they said May I didn't think they would release it with only an hour to spare..
The only reason I bought a Zune was because I thought it would have linux on it a few months after launch. I thought to myself "Ipod fans have had Rockbox and ipodlinux for ages so why not Zune?". Big mistake. Microsoft have gone out of their way to prevent third party firmware being loaded on by only accepting Microsoft signed firmware. Its such a shame. Think about what could be done: wireless syncing, actually sharing songs between other Zune users (not that 3 songs in 3 days crap), gapless playback, proper video format support (not just wmv) etc. It could have been good...
This game is coded by one person, a few volentary artists. Look for yourself at what has been achieved so far: http://fl-tw.com/