AMD Radeon HD 7970 Review: 28nm And Graphics Core Next, Together As One
by Ryan Smith on December 22, 2011 12:00 AM EST- Posted in
- GPUs
- AMD
- Radeon
- ATI
- Radeon HD 7000
Crysis: Warhead
Kicking things off as always is Crysis: Warhead. It’s no longer the toughest game in our benchmark suite, but it’s still a technically complex game that has proven to be a very consistent benchmark. Thus even 4 years since the release of the original Crysis, “but can it run Crysis?” is still an important question, and the answer continues to be “no.” While we’re closer than ever, full Enthusiast settings at a 60fps is still beyond the grasp of a single-GPU card.
This year we’ve finally cranked our settings up to full Enthusiast quality for 2560 and 1920, so we can finally see where the bar lies. To that extent the 7970 is closer than any single-GPU card before as we’d imagine, but it’s going to take one more jump (~20%) to finally break 60fps at 1920.
Looking at the 7970 relative to other cards, there are a few specific points to look at; the GTX 580 is of course its closest competitor, but we can also see how it does compared to AMD’s previous leader, the 6970, and how far we’ve come compared to DX10 generation cards.
One thing that’s clear from the start is that the tendency for leads to scale with the resolution tested still stands. At 2560 the 7970 enjoys a 26% lead over the GTX 580, but at 1920 that’s only a 20% lead and it shrinks just a bit more to 19% at 1680. Even compared to the 6970 that trend holds, as a 32% lead is reduced to 28% and then 26%. If the 7970 needs high resolutions to really stretch its legs that will be good news for Eyefinity users, but given that most gamers are still on a single monitor it may leave AMD closer to 40nm products in performance than they’d like.
Speaking of 40nm products, both of our dual-GPU entries, the Radeon HD 6990 and GeForce GTX 590 are enjoying lofty leads over the 7970 even with the advantage of its smaller fabrication process. To catch up to those dual-GPU cards from the 6970 would require a 70%+ increase in performance, and even with a full node difference it’s clear that this is not going to happen. Not that it’s completely out of reach for the 7970 once you start looking at overclocking, but the reduction in power usage when moving from TSMC 40nm to 28nm isn’t nearly large enough to make that happen while maintaining the 6970’s power envelope. Dual-GPU owners will continue to enjoy a comfortable lead over even the 7970 for the time being, but with the 7970 being built on a 28nm process the power/temp tradeoff for those cards is even greater compared to 40nm products.
Meanwhile it’s interesting to note just how much progress we’ve made since the DX10 generation though; at 1920 the 7970 is 130% faster than the GTX 285 and 170% faster than the Radeon HD 4870. Existing users who skip a generation are a huge market for AMD and NVIDIA, and with this kind of performance they’re in a good position to finally convince those users to make the jump to DX11.
Finally it should be noted that Crysis is often a good benchmark for predicting overall performance trends, and as you will see it hasn’t let us down here. How well the 7970 performs relative to its competition will depend on the specific game, but 20-25% isn’t too far off from reality.
Looking at our minimum framerates it’s a bit surprising to see that while the 7970 has a clear lead when it comes to average framerates the minimums are only significantly better at 2560. At that resolution the lowest framerate for the 7970 is 23.5 versus 20 for the GTX 580, but at 1920 that becomes a 2fps, 5% difference. It’s not that the 7970 was any less smooth in playing Crysis, but in those few critical moments it looks to be dipping a bit more than the GTX 580.
Compared to the 6970 on the other hand the minimum framerate difference is much larger and much more consistent. At 2560 the 7970’s minimums are 29% better, and even at lower resolutions it holds at around 25%. Clearly even with AMD’s new architecture their designs still inherit some of the traits of their old designs.
Facebook
Twitter
RSS
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/$.