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
Final Words
The launch of the Radeon HD 7970 has presented us with a great deal of data and even more subjects to consider, so it’s difficult in the best of times to try to whittle this down to a single conclusion. Nevertheless, based on our testing I believe there are two distinct conclusions to be drawn: the case for gaming, and the case for computing.
Gaming
At the end of the day the 7970 is specifically targeted as a gaming workhorse. Regardless of any architecture changes, what’s important is how fast the card is, how much it costs, whether it works correctly, and what its physical attributes are like. With respect to all of these aspects AMD has made an acceptable card, but this is not a groundbreaking product like we’ve seen in the past.
The fact of the matter is that since 2008 we’ve become spoiled by AMD’s aggressive pricing. More than anything else the low prices of the Radeon HD 4870 and Radeon HD 5870 made those products superstars thanks to their performance for the price and their undercutting of NVIDIA’s competing cards. The Radeon HD 5870 was definitely fast, but at $379 it was a steal, which is part of the reason prices for it never stabilized at that low a level.
At the same time the 7970 is not the 5870. The 5870 relative to both NVIDIA and AMD’s previous generation video cards was faster on a percentage basis. It was more clearly a next-generation card, and DX11 only helped to seal the deal. Meanwhile if you look at straight averages the 7970 is only around 15-25% faster than the GTX 580 in our tests, with its advantage being highly game dependent. It always wins at 2560 and 1920, but there are some cases where it’s not much of a win. The 7970’s domination of the 6970 is more absolute, but then again the 6970 is a good $200 cheaper at this point in time.
Meanwhile the presence of previous generation dual-GPU cards will continue to muddle the picture a bit further. We remain as sheepish as ever on multi-GPU cards and believe a high performance single GPU card is still a better investment in most situations, but there’s no denying that the GTX 590 and Radeon HD 6990 are quite capable cards today if you can put up with the noise and the inherent issues with alternate frame rendering.
Ultimately the past few years have seen AMD make great technical progress, but on the business side of things it’s NVIDIA that has made all the money. GCN will help AMD here by improving their professional product line, but the other part of that equation is for AMD to stop selling their cards for so little when they don’t have to. And this is what we’re seeing with the Radeon HD 7970. AMD has chosen to price the 7970 like a current generation card – it’s priced relative to a 3GB GTX 580 – and that’s a fair metric. What it isn’t is groundbreaking in any sense.
So at the end of the day AMD has once again retaken the performance crown for single-GPU cards, bringing them back to a position they last held nearly 2 years ago with the 5870. To that AMD deserves kudos, and if you’re in the market for a $500+ video card the 7970 is clearly the card to get – it’s a bit more expensive than the GTX 580, but it’s reasonably faster and cooler all at once. However if you’ve been waiting for 28nm GPUs to bring about another rapid decrease in video card prices as we saw with the 5870, you’re going to be waiting a bit longer.
Compute
The Radeon HD 7970 may be a gaming product, but today was just as much a launch for AMD’s Graphics Core Next architecture as it was for their new single-GPU king. GCN is the biggest architecture overhaul for AMD since R600 in 2007, and it shows. AMD has laid out a clear plan to seriously break into the GPU computing market and GCN is the architecture that will take them there. This is their Fermi moment.
At this point I’m not comfortable speaking about the compute performance of GCN in absolutes, but based on our limited testing with the 7970 it’s clear the potential is there. At times it’s competitive with the Fermi-based GTX 580 and at other times it’s quite a bit faster. In the hands of experienced developers and given enough time to learn the quirks of GCN, I believe GCN will prove itself. It’s much too early to tell if it will be able to withstand the eventual arrival of NVIDIA’s Kepler, but certainly this is the best shot AMD has ever had.
Performance aside, it’s clear that AMD’s SIMD architecture will make GPU compute development for GCN much easier; of that there is no question. This is important as GCN isn’t just about HPC computing, it’s about fully embracing Fusion. AMD’s CPU plans are built upon GCN just as much as they’re built upon Bulldozer, and for GCN to deliver on its half of the heterogeneous computing aspect of Fusion it will need to be easy to program and it will need to perform well. It would appear AMD has the hardware to make the former happen, now time will tell if GCN Fusion can deliver on the latter.
Facebook
Twitter
RSS
292 Comments
View All Comments
CeriseCogburn - Thursday, March 8, 2012 - link
Interesting, amd finally copied nvidia..." This problem forms the basis of this benchmark, and the NQueen test proves once more that AMD's Radeon HD 7970 tremendously benefits from leaving behind the VLIW architecture in complex workloads. Both the HD 7970 and the GTX 580 are nearly twice as fast as the older Radeons. "
When we show diversity we should also show that amd radeon has been massively crippled for a long time except when "simpleton" was the key to speed. "Superior architecture" actually means "simple and stupid" - hence "fast" at repeating simpleton nothings, but unable to handle "complex tasks".
LOL - the dumb gpu by amd has finally "evolved".
chizow - Thursday, December 22, 2011 - link
....unfortunately its going to be pitted against Kepler for the long haul.There's a lot to like about Southern Islands but I think its going to end up a very similar situation as Evergreen vs. Fermi, where Evergreen released sooner and took the early lead, but Fermi ultimately won the generation. I expect similar with Tahiti holding the lead for the next 3-6 months until Kepler arrives, but Kepler and its refresh parts winning this 28nm generation once they hit the streets.
Overall the performance and changes AMD made with Tahiti look great compared to Northern Islands, but compared to Fermi parts, its just far less impressive. If you already owned an AMD NI or Evergreen part, there'd be a lot of reason to upgrade, but if you own a Fermi generation Nvidia card there's just far less reason to, especially at the asking price.
I do like how AMD opened up the graphics pipeline with Tahiti though, 384-bit bus, 3GB framebuffer, although I wonder if holding steady with ROPs hurts them compared to Kepler. It would've also been interesting to see how the 3GB GTX 580 compared at 2560 since the 1.5GB model tended to struggle even against 2GB NI parts at that resolution.
ravisurdhar - Thursday, December 22, 2011 - link
My thoughts exactly. Can't wait to see what Kepler can do.Also...4+B transistors? mind=blown. I remember when we were ogling over 1B. Moore's law is crazy.... :D
johnpombrio - Wednesday, December 28, 2011 - link
Exactly. If you look at all the changes that AMD did on the card, I would have expected better results: the power consumption decrease with the Radeon 7970 is mainly due to the die shrink to 28nm. NVidia is planning on a die shrink of their existing Fermi architecture before Kepler is released:http://news.softpedia.com/news/Nvidia-Kepler-Is-On...
Another effect of the die shrink is that clock speed usually increases as there is less heat created at the lower voltage needed with a smaller transistor.
The third change that is not revolutionary is the bump of AMD's 7970's memory bus from 384 bits (matching the 580) from the 6970's 256 bits along with 3GB DDR5 memory vs the GTX580's 1.5GB and the 6970's 2GB.
The final non revolutionary change is bumping the number of stream processors by 33% from 1,536 to 2,048.
Again, breaking out my calculator, the 35% bump in the number of stream processors ALONE causes the increase in the change in the benchmark differences between the 7970 and the 6970.
The higher benchmark, however, does not show ANY OTHER large speed bumps that SHOULD HAVE OCCURED due to the increase in the memory bus size, the higher amount of memory, compute performance, texture fill rate, or finally the NEW ARCHITECTURE.
If I add up all the increases in the technology, I would have expected benchmarks in excess of 50-60% over the previous generation. Perhaps I am naive in how much to expect but, hell, a doubling of transistor count should have produced a lot more than a 35% increase. Add the new architecture, smaller die size, and more memory and I am underwhelmed.
CeriseCogburn - Thursday, March 8, 2012 - link
Well, we can wait for their 50%+ driver increase package+ hotfixes - because after reading that it appears they are missing the boat in drivers by a wide margin.Hopefully a few months after Kepler blows them away, and the amd fans finally allow themselves to complain to the proper authorities and not blame it on Nvida, they will finally come through with a "fix" like they did when the amd (lead site review mastas) fans FINALLY complained about crossfire scaling....
KaarlisK - Thursday, December 22, 2011 - link
What is the power consumption with multiple monitors? Previously, you could not downclock GDDR5, so the resulting consumption was horrible.Ryan Smith - Thursday, December 22, 2011 - link
"On that note, for anyone who is curious about idle clockspeeds and power consumption with multiple monitors, it has not changed relative to the 6970. When using a TMDS-type monitor along with any other monitor, AMD has to raise their idle clockspeeds from 350MHz core and 600Mhz memory to 350MHz core and the full 5.5GHz speed for memory, with the power penalty for that being around 30W. Matched timing monitors used exclusively over DisplayPort will continue to be the only way to be able to use multiple monitors without incurring an idle penalty."KaarlisK - Thursday, December 22, 2011 - link
Thank you for actually replying :)I am so sorry for having missed this.
ltcommanderdata - Thursday, December 22, 2011 - link
Great review.Here's hoping that AMD will implement 64-bit FP support across the whole GCN family and not just the top-end model. Seeing AMD's mobile GPUs don't use the highest-end chip, settling for the 2nd highest and lower, there hasn't been 64-bit FP support in AMD mobile GPUs since the Mobility HD4800 series. I'm interested in this because I can then dabble in some 64-bit GPGPU programming on the go. It also has implications for Apple since their iMacs stick to mobile GPUs, so would otherwise be stuck without 64-bit FP support which presumably could be useful for some of their professional apps.
In regards to hardware accelerated Megatexture, is it directly applicable to id Tech 5's OpenGL 3.2 solution? ie. Will id Tech 5 games see an immediate speed-up with no recoding needed? Or does Partially Resident Texture support require a custom AMD specific OpenGL extension? If it's the later, I can't see it going anywhere unless nVidia agrees to make it a multivendor EXT extension.
Ryan Smith - Thursday, December 22, 2011 - link
Games will need to be specifically coded for PRT; it won't benefit any current games. And you are correct in that it will require and AMD OpenGL extension to use (it won't be accessible from D3D at this time).