ATI GPU transcoding app?

Why would i have to dig through 5 page document if they could state that right next to the AVIVO download link? But i guess thats too hard in these days where >4GB is something compeltelly usual and where users with 64bit systems aren't some outlaws...
 
Why would you ever use something without reading the documentation first? But I guess that's too hard in these days where using common sense is something completely unusual.
 
Why would you ever use something without reading the documentation first? But I guess that's too hard in these days where using common sense is something completely unusual.

Well, at least here in finland the common way is "do first, after the blue smoke is gone, check manual for what went wrong" ;)
 
It's not something AMD invented. They all do like this. You visit their webpage and it states:
2K/XP/Vista. But when you install it it fails from unknown reason. And when you start yelling at tech support they finally give you the precious info that even though Vista is supported, they don't support x64. Yey. Like we're in freakin 1998 where 64bit OS is a science fiction.
I found FormatFactory transcoder anyway now. It's slightly slower but at least it transcode things right unlike AMD's transcoder that simply decides to shrink the image from 1280 pixels wide to 320 while maintaining the height. Pheh... And i can encode high quality H.264 for a change.
 
Anandtech said:

"AMD shows up to this gun fight with a knife, as Avivo’s image quality isn’t acceptable. While the Avivo video converter is free, it’s not useful."

" we are very disappointed with AMD's Avivo video converter as a vehicle to show off ATI Stream. It is a poor application that provides little to no value in exchange for the immense frustration end users will have when trying to transcode video. It is not worth the time to it takes to download or the space it takes up on your hard drive."

...
 
That's bad. I know it wasn't going to be good, but that's just a waste of time. I hope Cyberlink will do a better job. Anyone have any inside info on when the patch for PowerDirector will be out ?
 
are AMD trying to suicide themselves making such crap available for download?
If it don't work don't make it available or at least call it alpha version.
 
Well, it's free after all. ;)

I have a feeling, that this transcoder will never make it beyond the proof-of-concept phase. Wait for something commercial or an open source project, hopefully on OpenCL, already.
 
It's a bullet point on the 4000 series. You sort of pay for it when you bought the card. So it's not free like x264. Proof of concept can be limited in features, but should at least work.
 
221mr5.png


Look ma'! It's written in the newspaper, so it has to be true. :p
 
Will more of the encode stages be put into GPU or will it be only the motion estimation stages for the foreseeable future ?

I think when they allowed us to increase the levels we will see the advantage of GPU encoding, but I wonder if the CPU will be too much of bottleneck to see the gain.
 
I've been having trouble with this 64-Bit-Issue also. It was not mentioned in the Early-Preview-Readme, but then was added to the final readme. According to my mail correspondence with AMD, not even all of their own guys were aware of the 64-Bit-issue.

After the initial report on the AVC (Avivo Video Converter), I've tried some encodings under XP (32 Bit of course this time) and was getting strange results again.

Under XP, the GPU was used (albeit not very much), got warmer and the transcoding speed scaled with core clock on a given card (4670, 4850). But surprisingly the same settings proved to be faster on a non-supported card like 3870 or even X850 - with the app obviously running off the CPU (which was dualcore, mind you!) only. At first, I thought this was due to my ub0r-anti-leet mobo with the PCIe connected only via 4 lanes from the southbridge (asrock 4core dual sata2) and thus more or less my fault but then the same proved to be repeatable on a more modern setup with an X48-Board. Plus, the ALU-count didn't seems to matter as much as their freq, because a 4670 with fixed clock at 750 was faster than the 4850 at a fixed 625-MHz-tick.

Maybe the AVC uses only one SIMD (or no SIMD at all but other portions of the GPU?) at the moment - dunno. This point seems to be true for Badaboom also, since it fails to scale according to even GFLOPS, let alone the architectural differences between G96/G92 and GT200. I think right now AVC is more a proof-of-concept than even a techdemo (which i would consider Badaboom), sadly.
 
Makes me wonder how AMD could get any third party developer interested in using Stream when what they have to show is so terrible.

Jawed
 
It's a face saver for AMD, IMO, so that they too can say that they are also doing something in the GPGPU space.
 
Makes me wonder how AMD could get any third party developer interested in using Stream when what they have to show is so terrible.

Jawed

There's potential in those new GPUs, no doubt about it, but maybe AMD has rushed the release of their first "serious" Stream-App for the consumer a bit to much to not leave Cuda uncontested for 2008?
 
Back
Top