Drivers & ISV Relations

As we noted last week with the release of the Catalyst 12.1 preview, AMD has a lot of technical and reputational debt to dig themselves out of when it comes to their Catalyst drivers. AMD dropped the ball this fall a number of times, failing to deliver on appropriate drivers for Rage, Battlefield 3, and The Elder Scrolls V: Skyrim in a timely manner. This isn’t something AMD is shying away from either – they know they screwed up and they’ll admit as much – but the question remains of how they intend to improve from there. Now that they once again have the leading single-GPU video card they need to have the leading drivers to run it.

Part of this redemption will come from the addition of new features, if only to reach parity with NVIDIA. Catalyst 12.1 introduced custom application profiles, while as we discussed with Eyefinity, Catalyst 12.2 will add to AMD’s suite of Eyefinity features with custom resolutions and the ability to relocate the Windows task bar. Furthermore AMD has features in the development pipeline for their Catalyst drivers for introduction later this year, but at this point it’s too early to talk about them.

 

But new features alone can’t fix every single thing that has ailed AMD in the past year, so the question remains: how does AMD intend to fix their poor delivery of optimized drivers for new games? It’s a question AMD cannot (or will not) completely answer in detail, but it’s a question for which there’s at least part of an answer.

The fundamental answer is more. More developers, more quality assurance, and above all more money. By all accounts NVIDIA sinks a lot of money into driver development and ISV and it usually shows. AMD is going to spend more resources on driver development at home and this is going to help a great deal, but at the same time it would seem that they’ve finally come to realize that great ISV relationships require that AMD be more proactive than how they’ve been in the past.

ISV relations covers a large umbrella of activities. Not only does this mean providing support to developers who request it, but it means providing cross-promotion marketing, encouraging developers to make use of your features (if only to help spur the creation of the killer app), and actively seeking out important development houses so that AMD’s interests and concerns are represented and represented early. It’s been said that the most important thing NVIDIA ever did with ISV relations was to send out their own engineers to development houses on their own dime to provide free support – essentially investing at least a small amount of money into a major game. The payoff of this was that NVIDIA was literally there to represent their interests, and conversely they had a chance to evaluate the game early and get to work on optimizations and SLI support well before it shipped. Snark about TWIMTBP aside, that’s where NVIDIA has raised the bar with ISV relations. That’s what AMD needs to follow.

To that extent AMD has reorganized the budget process for their ISV relations department. Neal Robison, the director of ISV relations, now directly controls a much larger ISV relations budget, whereas previously the ISV relations budget was apparently controlled by several parties. Having more funding for ISV relations won’t solve AMD’s issues on its own – It’s all about how that money is spent – but clearly AMD is on the right path by being able to afford to be more proactive about their ISV relationships.

Whether these changes will pay off as AMD is expecting them to remains to be seen, but from our discussions it’s apparent that AMD is trying harder than ever before. A great product requires good hardware and good software; AMD has the former in Tahiti, now it’s time to see if they can deliver on the latter.

Closing out the subject of drivers, AMD is also using the Southern Islands launch to outline their plans for Windows 8. AMD is promising that they will deliver drivers for Windows 8 on the same schedule as they have for Windows 7 and Windows Vista – new drivers will be available for the Windows 8 Beta, RC, and RTM releases. Furthermore as Microsoft has continually iterated on the WDDM driver stack since Vista, AMD will continue to be able to offer a single unified driver that covers all of the WDDM OSes (Vista, 7, and 8).

Image Quality: Anisotropic Filtering Tweaks & Tessellation Speed Meet the Radeon HD 7970
Comments Locked

292 Comments

View All Comments

  • mczak - Thursday, December 22, 2011 - link

    Oh yes _for this test_ certainly 32 ROPs are sufficient (FWIW it uses FP16 render target with alpha blend). But these things have caches (which they'll never hit in the vantage fill test, but certainly not everything will have zero cache hits), and even more important than color output are the z tests ROPs are doing (which also consume bandwidth, but z buffers are highly compressed these days).
    You can't really say if 32 ROPs are sufficient, nor if they are somehow more efficient judged by this vantage test (as just about ANY card from nvidia or amd hits bandwidth constraints in that particular test long before hitting ROP limits).
    Typically it would make sense to scale ROPs along with memory bandwidth, since even while it doesn't need to be as bad as in the color fill test they are indeed a major bandwidth eater. But apparently AMD disagreed and felt 32 ROPs are enough (well for compute that's certainly true...)
  • cactusdog - Thursday, December 22, 2011 - link

    The card looks great, undisputed win for AMD. Fan noise is the only negative, I was hoping for better performance out the new gen cooler but theres always non-reference models for silent gaming.

    Temps are good too so theres probably room to turn the fan speed down a little.
  • rimscrimley - Thursday, December 22, 2011 - link

    Terrific review. Very excited about the new test. I'm happy this card pushes the envelope, but doesn't make me regret my recent 580 purchase. As long as AMD is producing competitive cards -- and when the price settles on this to parity with the 580, this will be the market winner -- the technology benefits. Cheers!
  • nerfed08 - Thursday, December 22, 2011 - link

    Good read. By the way there is a typo in final words.

    faster and cooler al at once
  • Anand Lal Shimpi - Thursday, December 22, 2011 - link

    Fixed, thank you :)

    Take care,
    Anand
  • hechacker1 - Thursday, December 22, 2011 - link

    I think most telling is the minimum FPS results. The 7970 is 30-45% ahead of the previous generation; in a "worse case" situation were the GPU can't keep up or the program is poorly coded.

    Of course they are catching up with Nvidia's already pretty good minimum FPS, but I am glad to see the improvement, because nothing is worse than stuttering during a fasted pace FPS. I can live with 60fps, or even 30fps, as long as it's consistent.

    So I bet the micro-stutter problem will also be improved in SLI with this architecture.
  • jgarcows - Thursday, December 22, 2011 - link

    While I know the bitcoin craze has died down, I would be interested to see it included in the compute benchmarks. In the past, AMD has consistently outperformed nVidia in bitcoin work, it would also be interesting to see Anandtech's take as to why, and to see if the new architecture changes that.
  • dcollins - Thursday, December 22, 2011 - link

    This architecture will most likely be a step backwards in terms of bitcoin mining performance. In the GCN architecture article, Anand mentioned that buteforce hashing was one area where a VLIW style architecture had an advantage over a SIMD based chip. Bitcoin mining is based on algorithms mathematically equivalent to password hashing. With GCN, AMD is changing the very thing that made their card better miners than Nvidia's chips.

    The old architecture is superior for "pure," mathematically well defined code while GCN is targeted at "messy," more practical and thus widely applicable code.
  • wifiwolf - Thursday, December 22, 2011 - link

    a bit less than expected, but not really an issue:

    http://www.tomshardware.co.uk/radeon-hd-7970-bench...
  • dcollins - Thursday, December 22, 2011 - link

    You're looking at a 5% increase in performance for a whole new generation with 35% more compute hardware, increased clock speed and increased power consumption: that's not an improvement, it's a regression. I don't fault AMD for this because Bitcoin mining is a very niche use case, but Crossfire 68x0 cards offer much better performance/watt and performance/$.

Log in

Don't have an account? Sign up now