Our Experience with UVD and R600
It's easy to point to the presentations and say, "look, this is slightly misleading." This doesn't get across the even more convincing interactions we had with AMD personnel over the course of reviewing the HD 2900 XT. Hopefully this will help to illuminate the issue further. I'll have to put a disclaimer on this and say that I don't have a photographic memory and I forgot to bring my diary to the press briefing. This isn't normally the kind of stuff I take notes on for product launches.
At the AMD press event in Tunis, Tunisia (we still can't figure out why we went to Africa to talk about a graphics card), myself and a couple other reviewers had the good fortune of being able to see HD Decode first hand. We watched a side by side comparison of an R6xx based part and a G8x based part with interesting results that mostly pointed out the long way Intervideo and CyberLink have to go in refining their player software. We were under the impression that this was R600, though clarification was not provided.
We talked about UVD and PureVideo, and we were asked if a video decode comparison would be made against NVIDIA hardware for our HD 2900 XT launch article. Upon replying in the affirmative, we got the impression that we should expect the R600 to outperform its competition (the 8800 GTS) in video decode tests. This doesn't seem as certain without UVD, but our marketing speak filters failed to pick up on anything out of the ordinary.
Moving on, we were initially told to expect a driver to enable video decode acceleration shortly before launch. AMD also provided us with a copy of PowerDVD which was said to support AVIVO HD. We did get a newer driver near launch, but in testing it we saw very bad video decode performance. It turns out that we couldn't test video decode at all, as hardware acceleration was not enabled in our press driver. This indicates to us that, even though we saw decode acceleration working in Tunis, AMD was having more trouble than expected in the QA department.
We would expect QA issue with new UVD hardware. If we've got the same video decode hardware as a previous generation part, it seems a little odd to think that we wouldn't have a driver or software to enable the feature.
In going back through our slides for this piece, we noticed that it is explicitly stated that UVD is included on the Radeon Mobility HD 2300. This is an R5xx based part retrofitted with UVD. Of all the parts not to have this new feature, the DX9 class Mobility HD 2300 would have been the one we thought of first. Surely if this part has the new feature, the HD 2900 XT should also include it. The argument for not is, again, that higher end GPUs tend to be paired with CPUs that can handle the workload.
The reason we offer time and again for the fact that G86 and G84 include full video decode while G80 does not is that the slower parts had 6 months more development time. In NVIDIA's case, it makes complete sense that G80 would lack the more refined video decode hardware. For AMD to launch a top to bottom product line and leave a feature like this out of their highest end part is very strange.
So strange, in fact, that combined with all the other experiences we've had with this rather surreal product launch we still just can't help but doubt what we're hearing. To us, the most sensible explanation for all this is that the hardware must be there but is somehow broken - perhaps broken to the point that it will never be fixed on current silicon (i.e. via drivers) and a new spin would be required to address the problems.
In spite of what makes sense to us, AMD has indicated that UVD hardware is not at all present on R600. Their "official" statement has yet to appear, but we'll update this article when/if we get it.
It's easy to point to the presentations and say, "look, this is slightly misleading." This doesn't get across the even more convincing interactions we had with AMD personnel over the course of reviewing the HD 2900 XT. Hopefully this will help to illuminate the issue further. I'll have to put a disclaimer on this and say that I don't have a photographic memory and I forgot to bring my diary to the press briefing. This isn't normally the kind of stuff I take notes on for product launches.
At the AMD press event in Tunis, Tunisia (we still can't figure out why we went to Africa to talk about a graphics card), myself and a couple other reviewers had the good fortune of being able to see HD Decode first hand. We watched a side by side comparison of an R6xx based part and a G8x based part with interesting results that mostly pointed out the long way Intervideo and CyberLink have to go in refining their player software. We were under the impression that this was R600, though clarification was not provided.
We talked about UVD and PureVideo, and we were asked if a video decode comparison would be made against NVIDIA hardware for our HD 2900 XT launch article. Upon replying in the affirmative, we got the impression that we should expect the R600 to outperform its competition (the 8800 GTS) in video decode tests. This doesn't seem as certain without UVD, but our marketing speak filters failed to pick up on anything out of the ordinary.
Moving on, we were initially told to expect a driver to enable video decode acceleration shortly before launch. AMD also provided us with a copy of PowerDVD which was said to support AVIVO HD. We did get a newer driver near launch, but in testing it we saw very bad video decode performance. It turns out that we couldn't test video decode at all, as hardware acceleration was not enabled in our press driver. This indicates to us that, even though we saw decode acceleration working in Tunis, AMD was having more trouble than expected in the QA department.
We would expect QA issue with new UVD hardware. If we've got the same video decode hardware as a previous generation part, it seems a little odd to think that we wouldn't have a driver or software to enable the feature.
In going back through our slides for this piece, we noticed that it is explicitly stated that UVD is included on the Radeon Mobility HD 2300. This is an R5xx based part retrofitted with UVD. Of all the parts not to have this new feature, the DX9 class Mobility HD 2300 would have been the one we thought of first. Surely if this part has the new feature, the HD 2900 XT should also include it. The argument for not is, again, that higher end GPUs tend to be paired with CPUs that can handle the workload.
The reason we offer time and again for the fact that G86 and G84 include full video decode while G80 does not is that the slower parts had 6 months more development time. In NVIDIA's case, it makes complete sense that G80 would lack the more refined video decode hardware. For AMD to launch a top to bottom product line and leave a feature like this out of their highest end part is very strange.
So strange, in fact, that combined with all the other experiences we've had with this rather surreal product launch we still just can't help but doubt what we're hearing. To us, the most sensible explanation for all this is that the hardware must be there but is somehow broken - perhaps broken to the point that it will never be fixed on current silicon (i.e. via drivers) and a new spin would be required to address the problems.
In spite of what makes sense to us, AMD has indicated that UVD hardware is not at all present on R600. Their "official" statement has yet to appear, but we'll update this article when/if we get it.
Facebook
Twitter
RSS
53 Comments
View All Comments
LTG - Monday, June 4, 2007 - link
Please ignore the small number of posts who called the article "blame shifting" or to "get over it".This article was not only well done it was important to the integrity of the process because it illuminated what went on behind the scenes.
Whether or not there was intentional deception in the best case there was inadequate information provided (no proof but if I had to bet it would be that someone at AMD didn't act in good faith at some point in time).
This kind of honest and direct reporting is why I come to the site. Likewise whenever AT gets hard questions from readers in the comments section, the authors directly respond much more than some other sites I see.
Keep it up please, you're right on track.
kalrith - Monday, June 4, 2007 - link
I also agree. Those who are calling AT biased, anti-AMD, and pro-Intel are just idiots. AT is for the companies that are providing the best bang for the buck of the average AT reader. AT was pro-AMD for the several years only in the sense that it stated AMD processors provided a much better value than Intel. Now, the tables have turned in Intel's favor somewhat as far as performance goes and lot as far as appropriate release dates and release information goes.coldpower27 - Monday, June 4, 2007 - link
I concur with this.7oby - Monday, June 4, 2007 - link
Both nVidia and ATI are very vage about this topic and have in the past sometimes even released false information.Although you hardly find any information about this on the web, the following restrictions seem to stabilize in my mind:
PureVideo:
. WMV-9/VC-1 Decoding deactivated on AGP Systems in recent driver releases
. partial H.264 hardware assisted decoding only possible with SSE2 (rules out AthlonXP systems for which the assistence would be very helpful)
. remember GeForce 6800 where the H.264, VC-1, WMV9 assisted decoding has been announced a later recalled due to hardware defects in this silicon?
Avivo:
. actually worse: I can not find any information about AGP, SSE(2) requirements
. I remember reading on their webpage: X1000 supports hardware assisted encoding (!) of content. What has survived is "The Avivo Video Converter is only supported on Radeon™ X1000 Series or new GPUs.", which leaves a very bad taste, since it has been proven that this software runs without X1000 hardware and doesn't utilize it for the tasks it offers.
Instead: A lot of confusion and frustration on the consumer side complaining about not properly working hardware assisted decoding.
ViRGE - Monday, June 4, 2007 - link
On hardware assisted encoding:It's actually worse than you think. Both ATI and Nvidia go back to 2004 with promises of this for the R420 and NV40 respectively. I have product overviews and press slideshows from both companies touting hardware encoding of MPEG 1, 2, and 4. Neither company has or will be delivering on this.
I fear GPU-based physics is going to go the same way.
7oby - Monday, June 4, 2007 - link
http://www.amd.com/us-en/assets/content_type/Downl...">http://www.amd.com/us-en/assets/content...eAssets/...states
ATI Avivo HD video and display architecture present in HD 2900, 2600, 2400
UVD (Unified Video Decoder) only present in HD 2600, 2400
Thus pretty much the same as with nvidia
Pure Video HD architecture present in G80, G84, G86
VP2 (for full H.264 decode) only present in G84, G86
Chunga29 - Monday, June 4, 2007 - link
Am I the only one that wonders when that PDF was last updated?PrinceGaz - Monday, June 4, 2007 - link
Well, given that certain review sites which checked their facts before writing their review of the HD 2900 mentioned that it specifically did not include dedicated UVD hardware (instead relying on the shaders to perform the same task because there are enough of them to do it), it would seem the information was available at least a few days before the NDA expired.Chunga29 - Monday, June 4, 2007 - link
Care to enlighten as to which "certain sites checked their facts"? I saw Firingsquad (well, skimmed it), and Tom's and a few others. I'm not sure who got it right at the start, but someone above linked at least four other places that got the UVD informations wrong. Tech Report, AnandTech, Tom's Hardware, and Firingsquad are all (well, not so much FS) pretty major sites, and they don't usually make mistakes of this sort unless someone gave them wrong info. Then there's Gigabyte and a couple other manufacturers that put UVD on 2900 boxes, I think.Goty - Monday, June 4, 2007 - link
http://www.driverheaven.net/reviews/r600reviewz/in...">http://www.driverheaven.net/reviews/r600reviewz/in...