NVIDIA and ATI HDCP Compatible Graphics Cards Roundup
by Josh Venning on November 16, 2006 12:00 AM EST- Posted in
- GPUs
CPU Utilization
Of course gaming performance is only part of the equation when it comes to looking at these HDCP compliant cards, the other major aspect is CPU utilization during high definition movie playback. Today we're only able to provide a small subset of HD movie playback performance as we're only testing with a MPEG-2 encoded Blu-ray title. We're still waiting for a PC HD-DVD player which will let us test VC1 and H.264 decode performance as well, but for now we're only able to look at high bitrate MPEG-2 content. VC1 and H.264 encoded content will put more stress on the CPU and GPU as a whole, but we'll unfortunately have to wait a little longer before testing it.
Just like when graphics cards started becoming important for offloading graphics processing with games like GLQuake, we are in a kind of transition period where it is becoming necessary to also have cards that can process our video playback for us. For the past couple of years ATI and NVIDIA products have been handling video decode acceleration, but it hasn't started to be really necessary until HD-DVD and Blu-Ray came around. The complex video formats they provide require more processing power to decode, meaning that slower processors won't be able to play them back without help from a graphics card.
Right now, since Blu-Ray titles are predominantly MPEG-2, having lots of extra power in a graphics card to accelerate the decode process isn't extremely important, but we still want to take a look at how much load the cards can take away from the CPU. With this in mind we put together a benchmark, recording the average CPU utilization of a period of about one minute of Blu-Ray movie playback. The movie we used was Click, and we tested each of the cards with the exact same one-minute segment of the movie. Audio was also enabled for this test.
Here are the CPU utilization results from each of our cards.
Video decode acceleration on NVIDIA GPUs is handled by the PureVideo processor, which is tied directly to the core clock speed, so the CPU utilization of each card will reflect this. The end result is that an NVIDIA card with more pipelines that is better at 3D performance will not necessarily be better at video decoding. With ATI, its AVIVO decoding is also tied to the processing power of the card, but is not quite as related to the clock speed as it is with NVIDIA. We also found that there was a bit of variance between multiple runs of the same tests, but these tests give us a general view of the CPU utilization of each of these cards.
We can see that the X1900 XT 256 gets a very low average CPU utilization compared to the other cards. Also, the 8800 GTX and 8800 GTS offloaded more processing from the CPU than the other NVIDIA cards, which isn't very surprising given that NVIDIA mentioned that the PureVideo core is a bit faster in G80. For reference, we measured the CPU utilization of the Blu-Ray playback benchmark with hardware acceleration disabled, and we got an average of 51.0%, giving us an idea of how much work these graphics cards take off the CPU. The Gigabyte 7600 GS doesn't seem to help in this area at all, and it makes sense when we consider that it's the slowest clocked NVIDIA card of the group. It would appear that a 400MHz clock speed doesn't provide enough power with PureVideo to make a difference in CPU utilization.
Even taking into account these results, CPU utilization isn't going to make a big difference between which of these cards would be better choices than others. Until we can look at H.264 and VC1 decode performance we will have to focus on other important factors to consider such as power, heat and noise.
Of course gaming performance is only part of the equation when it comes to looking at these HDCP compliant cards, the other major aspect is CPU utilization during high definition movie playback. Today we're only able to provide a small subset of HD movie playback performance as we're only testing with a MPEG-2 encoded Blu-ray title. We're still waiting for a PC HD-DVD player which will let us test VC1 and H.264 decode performance as well, but for now we're only able to look at high bitrate MPEG-2 content. VC1 and H.264 encoded content will put more stress on the CPU and GPU as a whole, but we'll unfortunately have to wait a little longer before testing it.
Just like when graphics cards started becoming important for offloading graphics processing with games like GLQuake, we are in a kind of transition period where it is becoming necessary to also have cards that can process our video playback for us. For the past couple of years ATI and NVIDIA products have been handling video decode acceleration, but it hasn't started to be really necessary until HD-DVD and Blu-Ray came around. The complex video formats they provide require more processing power to decode, meaning that slower processors won't be able to play them back without help from a graphics card.
Right now, since Blu-Ray titles are predominantly MPEG-2, having lots of extra power in a graphics card to accelerate the decode process isn't extremely important, but we still want to take a look at how much load the cards can take away from the CPU. With this in mind we put together a benchmark, recording the average CPU utilization of a period of about one minute of Blu-Ray movie playback. The movie we used was Click, and we tested each of the cards with the exact same one-minute segment of the movie. Audio was also enabled for this test.
Here are the CPU utilization results from each of our cards.
|
CPU Utilization |
Avg | Min | Max |
| NVIDIA Gigabyte GeForce 7600 GS | 51.5 | 41.4 | 58.2 |
| NVIDIA ASUS GeForce EN7600 GT | 45.5 | 38.8 | 50.8 |
| NVIDIA MSI GeForce NX7600 GT Diamond Plus | 46.9 | 38.3 | 52.9 |
| NVIDIA MSI GeForce NX7600 GT | 45.8 | 39.1 | 51.6 |
| NVIDIA Albatron GeForce 7900 GS | 45.8 | 36.7 | 54.7 |
| NVIDIA EVGA e-GeForce 7900 GS KO | 44.5 | 37.5 | 52.3 |
| NVIDIA Leadtek WinFast PX7900GS TDH Extreme | 44.8 | 36.7 | 51.6 |
| NVIDIA MSI GeForce 7900 GS | 45.9 | 38.3 | 52.3 |
| NVIDIA MSI GeForce NX7900 GT | 44.9 | 38.3 | 51.6 |
| NVIDIA EVGA e-GeForce 7950 GT KO | 43.9 | 35.9 | 50.0 |
| NVIDIA Gigabyte GeForce NX7950 GT | 44.4 | 36.7 | 51.6 |
| NVIDIA PNY GeForce 7950 GT | 44.3 | 36.7 | 52.3 |
| NVIDIA XFX GeForce 7950 GT HDCP | 44.1 | 35.2 | 53.1 |
| NVIDIA Sparkle Calibre 7950 GT | 44.1 | 35.9 | 64.1 |
| NVIDIA BFG GeForce 7950 GX2 | 46.3 | 36.7 | 53.1 |
| NVIDIA EVGA e-GeForce 7950 GX2 | 46.2 | 39.8 | 53.1 |
| NVIDIA GeForce 8800 GTX | 38.7 | 29.7 | 46.9 |
| NVIDIA GeForce 8800 GTS | 39.8 | 31.2 | 48.8 |
| ATI Powercolor Radeon X1600 PRO HDMI | 40.6 | 28.1 | 50.0 |
| ATI Sapphire Radeon X1950 XTX | 36.3 | 28.9 | 44.5 |
| ATI Radeon X1900XT 256 (reference) | 34.2 | 28.1 | 39.8 |
| ATI Radeon X1650XT (reference) | 38.3 | 28.1 | 46.1 |
Video decode acceleration on NVIDIA GPUs is handled by the PureVideo processor, which is tied directly to the core clock speed, so the CPU utilization of each card will reflect this. The end result is that an NVIDIA card with more pipelines that is better at 3D performance will not necessarily be better at video decoding. With ATI, its AVIVO decoding is also tied to the processing power of the card, but is not quite as related to the clock speed as it is with NVIDIA. We also found that there was a bit of variance between multiple runs of the same tests, but these tests give us a general view of the CPU utilization of each of these cards.
We can see that the X1900 XT 256 gets a very low average CPU utilization compared to the other cards. Also, the 8800 GTX and 8800 GTS offloaded more processing from the CPU than the other NVIDIA cards, which isn't very surprising given that NVIDIA mentioned that the PureVideo core is a bit faster in G80. For reference, we measured the CPU utilization of the Blu-Ray playback benchmark with hardware acceleration disabled, and we got an average of 51.0%, giving us an idea of how much work these graphics cards take off the CPU. The Gigabyte 7600 GS doesn't seem to help in this area at all, and it makes sense when we consider that it's the slowest clocked NVIDIA card of the group. It would appear that a 400MHz clock speed doesn't provide enough power with PureVideo to make a difference in CPU utilization.
Even taking into account these results, CPU utilization isn't going to make a big difference between which of these cards would be better choices than others. Until we can look at H.264 and VC1 decode performance we will have to focus on other important factors to consider such as power, heat and noise.
Facebook
Twitter
RSS
48 Comments
View All Comments
JarredWalton - Thursday, November 16, 2006 - link
Testing was done with an HDTV, because that's almost guaranteed to get HDCP support these days. Some of the newer LCDs have HDCP support (Dell's 2407 and 2007 do I believe), but most do not. That should change, but for now you are less likely to get HDCP with a standard PC display than with an HDTV. So, for HTPCs, you're better off getting just about any LCDTV or plasma in my opinion - watch out for projection HDTVs, as the text for PC use can get pretty garbled. Also beware of plasma burn-in possibilities. My rear-projection HDTV has a bit of burn-in already, and no matter what companies may say, plasma as I understand it is far more prone to such problems. (ESPN HD's logo is burned in on my TV, in case you want to know.)For the cards, features and performance are the two big factors - do you want gaming + HDCP support, just HDCP, or somewhere in between? What about HDMI? If you plan on connecting directly to a TV and using the TV speakers, you'll want HDMI that can include audio (several of the cards reviewed do this). My HDTV for example has an HDMI port, and I can use a DVI-to-HDMI cable to connect to it via just about any modern GPU. The problem is, I can't get audio from the TV without a true HDMI connection.
Finally, OS support is either via Vista, or else you can get an appropriate media player that will handle HDCP content. Testing here was done on XP, so it works already. Will Vista make it better? I personally doubt it, but it won't require extra software apparently (beyond whatever Vista already includes, of course, which is already a lot of "extra").
This article is more intended as an introduction to HDCP cards rather than being the final word. It will become more important over the next year or two, certainly. We'll have discussions on displays and HDCP support in the future.
DerekWilson - Friday, November 17, 2006 - link
Might I also add that 1080p HDTVs seem to make excellent computer monitors. If you want something to do dual duty as a TV and a PC monitor, I can highly recommend a 1080p LCD like the westinghouse we used in this review.If I had the money for either a new monitor or a new TV I'd go with one of these and kill two birds with one stone. And I'd be very very happy about it.
Tujan - Thursday, November 16, 2006 - link
Come on man.Desktop HD "? Smack some of that power onto those 32 to 40 in LCD sets. I know,I know,the angle is just around the corner. The LCD vendors are going have to,sooner,or later realize what their sets mean to the market.The market different from what is being portrayed. And what performance of them mean in it.Has there been any consideration of this.? And in doing so is there any caveats to using the HDTVs when involved with the drivers/hardware..there probably are. Since HDTV sets have somewhat sutured chipsets involved with them.
So in so doing,the idea here for HDCP,being that most of these cards have DVI(HDMI transformer connector)- problems/caveats for proper sound output was not considered. What to look for to consideration of other components,and compatability to HDCP.
Perahps for example I want to look at HD.And HDCP,are we going to limit our computers to a non-player in this area.For example,get on the wire-less keyboard in the living room already.
If I was to realize that electronics stores for example had 'none'of these HDCP enable cards I would be fixing some faces.
But BD,or HD-DVD on the computer screem ?
Come on man. Its chow on those 32",40" LCD HDTV monitors already.
As if Tiawan,Japan,South Korea aren't already in the weeds.I mean helloo.
And AMD-ATI,...-dont be such a lard bottom.!(AMD-ATI).
I mean(Anandtech) easily,get Fries,or Bestbuy to give you the keys to those isles for a night or two.Im sure they'd appreciate your tender convention.
thanks for ability to post here.And good article.
DigitalFreak - Friday, November 17, 2006 - link
Damn dude. I didn't understand a thing you said. Was that Far Eastern Jive or something?Tujan - Friday, November 17, 2006 - link
Here is the test setup page..http://www.anandtech.com/video/showdoc.aspx?i=2874...">http://www.anandtech.com/video/showdoc.aspx?i=2874...
Guess depends on where your standing (and punn ya yes):
-In front of the HDTVs or Video Cards
(retail electronics shop)
- At your work desk putting a computer together (or bench)
- At your desktop reading the Anandtech article....,or In your living room sitting at your couch.
- Maybe looking at your checkbook wondering that you dont 'want to afford a 500$ mistake.
............................
"Far East Jive" ? LOL. Its all Taiwan,Japan,or South Korea making the LCDs. They look really good.
It isn't like you cant see the jungle for the warefare.
________________
Just below here on a forum post the author you'll see that the Display was said to be an HDTV . Though the system stats didn't say "what<- ...uhumn .. Display.
Think that the point of the article was question of fact wether or not the video cards would have performance,and HDCP without sacrificing one or the other.Performance to gaming,and HDCP.
For me as I had first posted would be the testing of these stats/cards to the HDTV LCDs.The author,..again said later within this forum posted that other testing would take place.
Since the caveats against several different HDTV monitors would be exactly different than simply putting together the video card(s).Telling that everything was 'ok'by doing this.With HDTVs you would have to figure compatability via the video cards(to the HDTV) as well as HDTVs (to the video cards.)
This article did not go as far as testing against several HDTVs. With the different video cards(including interaction of software instalation).
The title of my post as 'toes in slippers..hmm". Bears the reasoning that against the backdrop of the 'shelf sets..HD DVD .. Blue-ray..and non-computer .. for the sake of broadcast,and 'media'- the living room LCDTVs are much more than this this.
Its not my business to tell anybody what their business is.Then when electronics vendors are going to ignore the accesories the LCD HDTVs afford to something as 'limited'as broadcast,and media. 'Broadcast,and HD,or Blueray to high definition is 'damn limiting.Thus the 'market'isn't what your being told it is. Just in case you hadn't noticed.
A 500$ mistake makes a difference.The context of that market is all about whats around the corner in so many ways. But where are you standing and whats there to look at ? If that market is ignored in the inventories and on the shelfs...as so on.In that 'limiting'focus.
Now,I've got to figure if my post is 'worth it'. The 32"and 40 LCDTVs are 'worth it. So lets see what they can do. Read some more angles about them before purchasing.
Thanks for reply.
Tarx - Thursday, November 16, 2006 - link
As mentioned above, but worth mentioning again, the X1950Pro is often considered to be the best midrange card currently on the market (relatively fast, not power hungry, fairly low cost, quiet, etc.) - if possible, can this article be amended to include it?DerekWilson - Friday, November 17, 2006 - link
As Josh mentioned above, ATI didn't support playback of HDCP protected content on the X1950 Pro until the release of the 6.11 Catalyst driver which was posted on 11/15/06 (one day before this article was published).We'll absolutely include the X1950 Pro in future articles that cover high definition video playback now that ATI has finally released a public driver for the same.
Spoelie - Thursday, November 16, 2006 - link
article index is broken (fixed)graphic card data is incorrect (x1900xt at 500/600 instead of 625/750? price?)
video table is f*cked up
oblivion settings are not linked (fixed now too)
etc. etc.
still a few cards i would like to see that are still missing, like a x1950pro with 512mb or the x1950xt - and what's the use of testing performance of identical cards, mentioning all hdcp compliant 7950gt and posting performance of one should be sufficient.
Spoelie - Thursday, November 16, 2006 - link
just to be clear, i know what the point is of this article, but since the x1950xt and a comparison between x1950pro 256/512 are both unlikely to get separate articles at this point, using roundups like this would be useful to include them, especially if you're gonna test and post 3d performance in the process :p so that we at least have some point of reference to make buying decisions. maybe something to note for future articles :)Josh Venning - Thursday, November 16, 2006 - link
Thanks for your comment.We did try to test the X1950 Pro for the HDCP review. Unfortunately, there hasn't been a public driver that supports the X1950 Pro since it's launch (that is until Catalyst 6.11 which was posted yesterday). ATI really dropped the ball with X1950 Pro, because the beta drivers they released did not support HDCP either.
We're sorry that we couldn't include this card in the review, but it just wasn't possible to test HDCP with the X1950 Pro until yesterday afternoon.