Serious desktop acceleration issues with discreet gfx - ATI 5 series especially bad

Initial part of Tom's conclusion:

Based on our own hands-on analysis of the current situation, we have to observe that the ATI's Radeon HD 5000-series cards are really struggling with 2D graphics. It’s also somewhat embarrassing that an older on-board graphics chipset is not only faster in a several areas (against both ATI- and Nvidia-based discrete cards), but also that there’s no real workaround for dealing with vector-based programs, either. This is not just a deficiency being measured in our testing; it’s also readily discernable to those who work with 2D graphics on a daily basis. Frankly, it’s quite difficult to imagine how an older Radeon HD 4870 can come so close to matching or beating the newer card in so many tests.

While 2D acceleration (including 2.5D layering) functions well, ATI has not yet managed to implement a number of pure GDI functions in its Radeon HD 5000-series cards. With a number of driver revisions behind us since Windows 7's initial launch, this situation is difficult to comprehend for the folks spending hundreds of dollars on next-gen hardware and running into trouble in 2D apps. We must also point out that this applies not only to our synthetic 2D benchmark, but also to various other real-world programs we used for our testing, including AutoCAD, as well as Corel Draw, Adobe Illustrator, Photoshop CS3/CS4, Microsoft Publisher, PowerPoint, and more. This calls for urgent and dramatic improvements, especially because our test results for Vista demonstrate significantly better scores than those in Windows 7 (we'll get into more depth on this in Part 2).

Click to expand...

Now, before people jump down my throat for being an nvidia fanboy trashing ATI, look at the objective benchmarks in the article and see for yourself. nvidia doesn't come away unscathed either, but does a lot better. Seeing a cheap integrated chipset blow away expensive top-end cards is really eye wateringly painful:


The integrated chipset leads by miles and the 5870 is a distant bottom. Unbelievable. Lots more benchies in the article.

It boils down to bad or non-existent 2D graphics acceleration on the desktop with Aero enabled. If you think that this doesn't affect everyone of us to some degree, think again. It's especially bad for anyone using CAD software or anything that draws 2D vector graphics.

This problem isn't new either, so it begs the question of why it took a major tech website to go public with it before the big graphics boys will fix it in a future driver update. And what does all this say about WHQL certification? Surely Microsoft know about this from their testing and they are stamping their approval anyway. I smell a rat here.

Tom's article is quite deep and pleasurably technical so take your time to read it properly and get the full info.

Tom's Hardware

Anyone? I thought this thread would make for a great talking point.

Look, if no one replies, I'm gonna just have to sit here and cry and cry like a girl until I get some attention!

erocker said:

Yup, very low 2d clocks. Saves power. Great thing is, I notice no performance issues whatsoever at desktop. I guess it works just fine. Not a serious issue at all. Non-issue. qubit, I'll hand it to you, you're good a linking to so called journalists with wierd articles. His call for drastic improvements to increasing 2d clocks is going to fall on deaf ears and is a silly statement to make.

Click to expand...

It's a little more than a low 2D clock, it seems. The acceleration simply doesn't work, as the article explains in detail. The most telling bit is in the conclusion, where Tom's have the update and AMD admits that this is a problem that will be corrected with a later driver.

It's possible that all of us are experiencing this to some extent or another, but are not realising it - a little slowness here, a hitch or lag there might simply not be so obvious that there's a problem. I dunno, I've not got anything to compare against, so I'm not stating this as a definite "fact", just how it seems to me. Also, it appears to me that the people who would notice this the most are the CAD crowd who do complex line drawings extensively and have many windows open at once. The article did state that this was quite noticeable in normal use.

Part 2 of the article should be interesting and I'll link to it when it's published.

Anyway, as far as "weird" articles go, I was simply browsing THG and this was on the front page, kinda hard to miss with its big, bold logo. I had no idea that this problem existed, figured others didn't either and would make for an interesting article to share.

And finally! I have noticed performance differences on the desktop between low end and high end cards on XP (let alone Vista or 7) especially in high res modes displaying something like a complex web page and scrolling it - the high end card can be considerably snappier, even on 2D clocks. This isn't surprising really, as you'd expect the high end card to have more oomph, with it's wider chips and buses.

That update:

Update (1/26/2010): With preliminary research into our 2D performance analysis, AMD reports back with the following:

•Tom’s Hardware has tripped over a workload area (2D lines, etc.) that we have not optimized yet.
•Until this new benchmark, we have not seen any other applications that are bottlenecked by this path, and hence have not focused on it until now.
•Our initial analysis has shown that we have no hardware limitations in this area.
•We now have our driver team engaged to optimize this path and will release a new driver to address this workload as soon as possible.
•We have already found an easy way of increasing our performance greatly, and are now going to try and schedule this in a future Catalyst (need to code in production, validate, ensure it doesn’t break anything else, etc.).

Click to expand...

Hmmm... good point erocker. I guess part 2 and the AMD driver update in particular will help resolve this question.

DRDNA said:

It is for people who are using the following:AutoCAD, as well as Corel Draw, Adobe Illustrator, Photoshop CS3/CS4, Microsoft Publisher, PowerPoint.

Click to expand...

Exactly. I think this problem is more significant than people realize. As I elaborated in post 7:

qubit said:

It's possible that all of us are experiencing this to some extent or another, but are not realising it - a little slowness here, a hitch or lag there might simply not be so obvious that there's a problem. I dunno, I've not got anything to compare against, so I'm not stating this as a definite "fact", just how it seems to me. Also, it appears to me that the people who would notice this the most are the CAD crowd who do complex line drawings extensively and have many windows open at once. The article did state that this was quite noticeable in normal use.

Click to expand...