TechieGroups

CHIP DESIGNER AMD has released the Radeon HD 7970 based on its Tahiti GPU chip.

AMD’s Radeon HD 7970 is the first graphics board design based on its 28nm Southern Islands Tahiti GPU. The chip, which AMD claims has 4.3bn transistors, has been significantly changed from the previous Northern Islands generation Cayman Radeon HD 6970, has more on-chip cache and the firm claims it has greater overclocking headroom.

AMD’s Tahiti architecture has up to 32 compute units with 32 colour render output units. A 384-bit memory interface results in memory bandwidth of over 264GB/s, with the firm spending a great deal of effort telling journalists about the need for 3GB GDDR5 memory by the latest triple-A games titles.

The firm’s Radeon HD 7970 reference graphics board design has 2,048 stream processors, 3GB of GDDR5 memory, one DVI port, an HDMI port and two mini-Displayport outputs supporting a total of six displays. This power hungry graphics card has one six-pin and one eight-pin power connectors.

Listening to AMD’s spiel there’s no doubt that the firm is positioning the Radeon HD 7970 as a significant step beyond Nvidia’s Geforce GTX 580. Internal “reviewer’s documents” circulated to journalists suggest the firm is seeing between 70 to 90 per cent increase in performance over its previous generation Radeon HD 6970 in games running at 2550×1600, though as usual it is best to take such figures with a pinch of salt.

Like all chip vendors, AMD didn’t waste time to extol the virtues of a process node shrink. The firm not only claimed that the 28nm process node allows a 3W idle power draw by its chips, but that through its Powertune software users can automatically receive 33 per cent overclocks.

AMD told journalists it wouldn’t be limiting board vendors by prescribing clock speeds and the ability to slap intricate cooling units onto the boards. While that sounds great, browsing through the current Radeon HD 6970 boards on sale, it looks like few board vendors bothered to do much more than slap a sticker onto AMD”s reference cooler.

TSMC is the wafer baker for AMD’s 28nm chip. Traditionally AMD prefers to release chips made using a new process node on mainstream boards, but the firm wouldn’t explain to journalists why it will have only ultra high-end 28nm parts from the outset. However, with TSMC becoming busier punching out Apple’s A6 chips, perhaps AMD’s relatively low-volume discrete graphics chips had to take a back seat.

AMD is pricing Radeon HD 7970 boards around £450 at launch, a hefty £200 premium over its current single-GPU range topper. At that price it really has to be trying to embarrass Nvidia’s Geforce GTX 590 rather than show up the significantly less expensive single-GPU boards from either AMD or Nvidia. µ

At AMD’s Fusion Developer Summit 2011 AMD announced Graphics Core Next, their next-generation GPU architecture. GCN would be AMD’s Fermi moment, where AMD got serious about GPU computing and finally built an architecture that would serve as both a graphics workhorse and a computing workhorse. With the ever increasing costs of high-end GPU development it’s not enough to merely develop graphics GPUs, GPU developers must expand into GPU computing in order to capture the market share they need to live well into the future.

At the same time, by canceling their 32nm process TSMC has directed a lot of hype about future GPU development onto the 28nm process, where the next generation of GPUs would be developed. In an industry accustomed to rapid change and even more rapid improvement never before have GPU developers and their buyers had to wait a full 2 years for a new fabrication process to come online.

All of this has lead to a perfect storm of anticipation for what has become the Radeon HD 7970: not only is it the first video card based on a 28nm GPU, but it’s the first member of the Southern Islands and by extension the first video card to implement GCN. As a result the Radeon HD 7970 has a tough job to fill, as a gaming card it not only needs to deliver the next-generation performance gamers expect, but as the first GCN part it needs to prove that AMD’s GCN architecture is going to make them a competitor in the GPU computing space. Can the 7970 do all of these things and live up to the anticipation? Let’s find out…

In our first run with the Alienware M18x, we sat down and took a look at the notebook itself along with NVIDIA's current top shelf mobile graphics part, the GeForce GTX 580M. We came away from the experience with mixed impressions of the M18x itself, a notebook that is by all means incredibly powerful but also seems to lose a lot of the balance that made the M17x R3 so desirable. On the other hand, the GeForce GTX 580M wound up being the fastest mobile GPU we'd yet tested, made only more formidable through the SLI configuration the M18x enables.

Today, Alienware has graciously provided us with the second half of the current top shelf performance equation in the form of a near-identically configured M18x, this time with two AMD Radeon HD 6990Ms in CrossFire. We'll also take a look at the Intel Core i7-2920XM's stock performance and compare it against the overclocked settings Alienware allows you to configure it with.

Thanks X-bit labs for the image

Intel's Developer Forum and Microsoft's BUILD conference are both underway but to not make this week any quieter, AMD is also having their own event in San Francisco, California. In the event, AMD demonstrated a fully working Mobility Radeon HD 7000 GPU. The demonstration was done by running Dirt 3 but details such as graphics settings, resolution and FPS are unknown. Specifications of the test setup were not disclosed either.

Not much is known about Radeon HD 7000 series as a whole, but a small brief is still in place. Radeon HD 7000 series carries the codename "Southern Islands" and will be manufactured using TSMC's 28nm process. Other than that, there isn't anything concrete, only a bunch of rumors. NordicHardware has a good overview of the rumors and possible specifications, but they should all be taken with grain of salt. 

Public release is still a question too. Earlier reports have suggested Q4'11 but the reports of TSMC's issues with 28nm chips could push the mass availability to Q1'12. 

Source: X-bit labs

GRAPHICS CARD VENDOR HIS launched its 6770 IceQ X and 6770 IceQ X Turbo cards.

These HIS 6770 IceQ cards are based on AMD’s reference Radeon HD6770 with 1GB GDDR5 memory, but they feature the firm’s trademark IceQ heatsink and fan, which has two heatpipes, and the firm claims it is quieter than the heatsink fan on reference boards. The considerable cooling also helps HIS ship its graphics cards factory overclocked.

The HIS 6770 IceQ has the GPU is clocked at 850MHz and the memory at an effective 4.8GHz. On the HIS 6770 IceQ Turbo the GPU runs at 880MHz with the 1GB GDDR5 memory running at 5GHz.

Both HIS 6770 IceQ boards have two dual-link DVI outputs as well as Displayport and HDMI outputs. Like all AMD Radeon HD6770 boards, the HIS 6770 IceQ units support Microsoft’s DirectX 11 and AMD’s Eyefinity multi-display software.

Although HIS didn’t announce pricing for its 6770 IceQ graphics cards, similar cards from other vendors such as Gigabyte, MSI, Sapphire and XFX all retail from £100 and go up to £120, though Gigabyte’s most expensive board in that price range has the AMD Radeon HD6770 GPU running at 900MHz.

It is likely that HIS will price its two boards somewhere in the middle of that pack, at around £105, more or less. µ

AMD’s last update to their mobile GPU lineup is now over six months old, which means we’re about due for another new part. Right on cue, and not long after NVIDIA’s GTX 580M speed bump, AMD briefed us on their latest update. Prior to agreeing to the NDA, all we got was that AMD Graphics would be making a “major mobile announcement”. That piqued our interest, as it could mean either new mobile GPUs, some other technology, or perhaps both. The major announcement goes by the name of Radeon HD 6990M, but what does it actually bring to the table? Read on….

IN THE HIGH END ARENA the AMD Radeon HD6990 and Nvidia Geforce GTX590, both dual GPU cards, now share the top performance position in PC 3D. Both cards have very high power usage, large size and lots of RAM. The 3GB of memory on the GTX590 and the 4GB on the HD6990 equal the average mainstream PC main system memory capacity.

The Radeon HD6990 is particularly interesting as there has been barely any clock frequency sacrifice over the single GPU HD6970, despite fitting two of these on a single card and adhering to all the power limitations. The only other performance penalty (and very slight at that – below one per cent) is the PLX PCIe bridge chip on each card, required to enable two GPUs to share one PCIe x16 interface to the host computer.

In applications beyond gaming, multi GPU setups like this are usable in workstations and even in supercomputing application niches, where each GPU can run a task, handling accelerated threads or specific routines that make sense to run on them. After all, the single HD6990 can offer nearly 6TFLOPs in single precision and 1.5 TFLOPs in double precision. However, running a single thread across multiple GPUs efficiently is right now still very hard to do as there is no clear shared memory model between two or more GPUs due to the PCI express bus communication. Once this is solved, though, there will be many more suitable applications for multiple GPU usage.

But back to the gaming world. Since new AMD Catalyst drivers did improve multi GPU Crossfire scaling quite a bit last year, it was an interesting question of how high scores would be achieved in the usual 3Dmark benchmarks with two HD6990 cards, with four GPUs in total. Of course, with that many high end graphics processors there has to be sufficient CPU horsepower to feed them.

So we combined the new Intel Core i7 990X CPU, running at 3.46GHz with the trusted Gigabyte X58A UD9 mainboard, the well featured top end overclocking reference and possibly the most expensive high-end single processor mainboard ever. It has two NF200 Bridge ASICs from Nvidia to enable four full x16 PCIe slots, resulting in a little larger than usual size. The 6GB of GEIL DDR3-2133 gamers’ memory, Intel X25-M 160GB SSD and Antec 1200W high end power supply, are easily capable of feeding the high-end hardware. The 64 bit Windows 7 install used default settings in the drivers and benchmark test applications.

Here are the 3Dmark Vantage and 3Dmark 11 test results. They speak for themselves:

As you can see, the combination of four GPUs and six CPU cores on a good motherboard can – even at default mode without any overclocking – achieve very high scores. This is up to some three times the score of a single HD6970 on the same processor platform, a very reasonable scaling benefit in either test.

Yes, the benchmark is just a benchmark, but it still shows well the scaling results and the platform’s performance potential. Now, the issue of heat does come up, so you’d better ensure that the case is spacious enough with strong airflow to match, as graphics cards these days create way more heat than the processors. µ

Lately we’ve been working on expanding our GPU coverage to include more GPUs that aren't directly sold to consumers discretely or as part of a package. Up until now we’ve mostly focused on 4 classes of GPUs: Desktop, Mobile/IGP, High Performance Computing (HPC), and we’ve spent some time dabbling with System on a Chip (SoC) GPUs for smartphones/tablets/netbooks. This range of products mostly covers the different GPUs seen in consumer products and in commercial supercomputing, but there is still a large gap in there for non-consumer business uses. This is the embedded market, and today we’re expanding our GPU coverage to include those GPUs.

Kicking off our coverage of embedded GPUs is AMD’s Radeon E6760, which is launching today. The E6760 is the latest and greatest AMD embedded video card, utilizing the Turks GPU (6600/6700M) from AMD’s value lineup. The E6760 isn’t a product most of us will be buying directly, but if AMD has it their way it’s a product a lot of us will be seeing in action in the years to come in embedded devices.

Two weeks ago we saw the paper launch of the Radeon HD 6450, the low-end member of AMD’s Northern Islands family of GPUs. It was a solid product for HTPC use and a very notable improvement over the 5450 it replaced, but it was an uncharacteristically delayed launch for AMD. At the same time we noted that the Northern Islands family had one more GPU we had not seen: Turks.

As it turns out, Turks-based video cards will be launching alongside the 6450 today, delivering all of the remaining Northern Islands products in a single push. Turks will be powering the Radeon HD 6670 and Radeon HD 6570, replacing the Redwood-based Radeon HD 5670 and Radeon HD 5570 respectively. Considering that we saw AMD deliver a solid update for their low-end lineup with the 6450, will we see the same with Turks and the 6670/6570? Let’s find out.

AMD’s Northern Islands family is composed of four GPUs, roughly divided into two categories. At the top is the 6900 series powered by Cayman, AMD’s first VLIW4 GPU. Below Cayman are three more GPUs, all derived from the VLIW5 Evergreen generation (5000 series). The first of these GPUs was Barts, which is the basis of the 6800 series that launched back in October of 2010. However up until now we haven’t seen the other two mystery GPUs in the retail market. Today that starts to change.

The final two Northern Island GPUs are Caicos and Turks. They have been available in the OEM market for both desktop and mobile products since the beginning of the year, but as is often common with low-end/high-volume GPUs, a retail presence comes last instead of first. AMD is finally giving Caicos its first retail presence today; it will be powering the new Radeon HD 6450. Packing all the upgrades we saw with Barts last year, it will effectively be replacing the Radeon HD 5450. But how well does AMD’s latest stand up in the crowded low-end market? Let’s find out.