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
Tahiti: The First Direct3D 11.1 GPU
One of the many changes coming in Windows 8 next year will be the next iteration of Direct3D, which will be Direct3D 11.1. More so than any other version of Direct3D so far, D3D11.1 is best summed up as a housekeeping release. There will be some new features, but compared to even past point releases such as 10.1 and 9c it’s a small release that’s going to be focusing more on improving the API itself – particularly interoperability with SoC GPUs for Windows 8 – than it will be about introducing new features. This is largely a consequence of the growing length of time for all matters of development hardware and software. By the time Windows 8 ships Direct3D 11 will be 3 years old, but these days that’s shorter than the development period for some AAA games. Direct3D 11/11.1 will continue to be the current Windows 3D API for quite some time to come.
With regards to backward compatibility in D3D11.1, there’s one new feature in particular that requires new hardware to support it: Target Independent Rasterization. As a result AMD’s existing D3D11 GPUs cannot fully support D3D11.1, thereby making Tahiti the first D3D 11.1 GPU to be released. In practice this means that the hardware is once again ahead of the API, even more so than what we saw with G80 + D3D10 or Cypress (5870) + D3D11 since D3D11.1 isn’t due to arrive for roughly another year. For the time being Tahiti’s hardware supports it but AMD won’t enable this functionality until the future – the first driver with D3D11.1 support will be a beta driver for Windows 8, which we expect we’ll see for the Windows 8 beta next year.
So what does D3D11.1 bring to the table? The biggest end user feature is going to be the formalization of Stereo 3D support into the D3D API. Currently S3D is achieved by either partially going around D3D to present a quad buffer to games and applications that directly support S3D, or in the case of driver/middleware enhancement manipulating the rendering process itself to get the desired results. Formalizing S3D won’t remove the need for middleware to enable S3D on games that choose not to implement it, but for games that do choose to directly implement it such as Deus Ex, it will now be possible to do this through Direct3D.
S3D related sales have never been particularly spectacular, and no doubt the fragmentation of the market is partially to blame, so this may be the push in the right direction that the S3D market needs, if the wider consumer base is ready to accept it. At a minimum this should remove the need for any fragmentation/customization when it comes to games that directly support S3D.
With S3D out of the way, the rest of the D3D11.1 feature set isn’t going to be nearly as visible. Interoperability between graphics, video, and compute is going to be greatly improved, allowing video via Media Foundation to be sent through pixel and compute shaders, among other things. Meanwhile target independent rasterization and some new buffer commands should give developers a few more tricks to work with, while double precision (FP64) support will be coming to pixel shaders on hardware that has FP64 support.
Finally, looking at things at a lower level D3D11.1 will be released alongside DXGI 1.2 and WDDM 1.2, the full combination of which will continue Microsoft’s long-term goal of making the GPU more CPU-like. One of Microsoft’s goals has to been to push GPU manufacturers to improve the granularity of GPU preemption, both for performance and reliability purposes. Since XP things have gotten better as Vista introduced GPU Timeout Detection and Recovery (TDR) to reset hung GPUs, and a finer level of granularity has been introduced to allow multiple games/applications to share a GPU without stomping all over each other, but preemption and context switches are still expensive on a GPU compared to a CPU (there are a lot of registers to deal with) which impacts performance and reliability.
To that end preemption is being given a bit more attention, as WDDM 1.2 will be introducing some new API commands to help manage it while encouraging hardware developers to support finer grained preemption. Meanwhile to improve reliability TDR is getting a major addition by being able to do a finer grained reset of the GPU. Currently with Windows 7 a TDR triggers a complete GPU reset, but with Windows 8 and WDDM 1.2 the GPU will be compartmentalized into “engines” that can be individually reset. Only the games/applications using a reset engine will be impacted while everything else is left untouched, and while most games and applications can already gracefully handle a reset, this will further reduce the problems a reset creates by resetting fewer programs.
Facebook
Twitter
RSS
292 Comments
View All Comments
Zingam - Thursday, December 22, 2011 - link
I think this card is a kinda fail. Well, maybe it is a driver issue and they'll up the performance 20-25% in the future but it is still not fast enough for such huge jump - 2 nodes down!!!It smell like a graphics Bulldozer for AMD. Good ideas on paper but in practice something doesn't work quite right. Raw performance is all that counts (of course raw performance/$).
If NVIDIA does better than usual this time. AMD might be in trouble. Well, will wait and see.
Hopefully they'll be able to release improved CPUs and GPUs soon because this generation does not seem to be very impressive.
I've expected at least triple performance over the previous generation. Maybe the drivers are not that well optimized yet. After all it is a huge architecture change.
I don't really care that much about that GPU generation but I'm worried that they won't be able to put something impressively new in the next generation of consoles. I really hope that we are not stuck with obsolete CPU/GPU combination for the next 7-8 years again.
Anyway: massively parallel computing sounds tasty!
B3an - Thursday, December 22, 2011 - link
You dont seem to understand that all them extra transistors are mostly there for computing. Thats mostly what this was designed for. Not specifically for gaming performance. Computing is where this card will offer massive increases over the previous AMD generation.Look at Nvidia's Fermi, that had way more transistors than the previous generation but wasn't that much faster than AMD's cards at the time. Because again all the extra transistors were mainly for computing.
And come on LOL, expecting over triple the performance?? That has never happened once with any GPU release.
SlyNine - Friday, December 23, 2011 - link
The 9700pro was up to 4x faster then the 4600 in certian situations. So yes it has happened.tzhu07 - Thursday, December 22, 2011 - link
LOL, triple the performance?Do you also have a standard of dating only Victoria's Secret models?
eanazag - Thursday, December 22, 2011 - link
I have a 3870 which I got in early 2007. It still does well for the main games I play: Dawn of War 2 and Starcraft 2 (25 fps has been fine for me here with settings mostly maxed). I have eyeing a new card. I like the power usage and thermals here. I am not spending $500+ though. I am thinking they are using that price to compensate for the mediocre yields they getting on 28nm, but either way the numbers look justified. I will be look for the best card between $150-$250, maybe $300. I am counting on this cards price coming down, but I doubt it will hit under $400-350 next year.No matter what this looks like a successful soft launch of a video card. For me, anything smokes what I have in performance but not so much on power usage. I'd really not mind the extra noise as the heat is better than my 3870.
I'm in the single card strategy camp.
Monitor is a single 42" 1920x1200 60 Hz.
Intel Core i5 760 at stock clocks. My first Intel since the P3 days.
Great article.
Death666Angel - Thursday, December 22, 2011 - link
Can someone explain the different heights in the die-size comparison picture? Does that reflect processing-changes? I'm lost. :D Otherwise, good review. I don't see the HD7970 in Bench, am I blind or is it just missing.Ryan Smith - Thursday, December 22, 2011 - link
The Y axis is the die size. The higher a GPU the bigger it is (relative to the other GPUs from that company).Death666Angel - Friday, December 23, 2011 - link
Thanks! I thought the actual sizes were the sizes and the y-axis meant something else. Makes sense though how you did it! :-)MonkeyPaw - Thursday, December 22, 2011 - link
As a former owner of the 3870, mine had the short-lived GDDR4. That old card has a place in my nerd heart, as it played Bioshock wonderfully.Peichen - Thursday, December 22, 2011 - link
The improvement is simply not as impressive as I was led to believed. Rumor has it that a single 7970 would have the power of a 6990. In fact, if you crunch the numbers, it would be at least 50% faster than 6970 which should put it close to 6990. (63.25% increase in transistors, 40.37% in TFLOP and 50% increase in memory bandwidth.)What we got is a Fermi 1st gen with the price to match. Remember, this is not a half-node improvement in manufacturing process, it is a full-node and we waited two years for this.
In any case, I am just ranting because I am waiting for something to replace my current card before GTA 5 came out. Nvidia's GK104 in Q1 2012 should be interesting. Rumored to be slightly faster than GTX 580 (slower than 7970) but much cheaper. We'll see.