When the Radeon HD 7970 launched at £450, it looked like a reasonable alternative to the GeForce GTX 590 and Radeon HD 6990. Both dual-GPU boards are measurably faster, but they’re also roughly £600, power-hungry, and in the case of the 6990, embarrassingly loud. Even still, the 7970's asking price is still pretty steep.
And that’s why a card like the Radeon HD 7950 is such a welcome addition to AMD’s portfolio. The company is, as of this writing, unwilling to comment on the 7950’s anticipated price tag. However, we’ve already run the benchmarks. We know how it stacks up to the Radeon HD 7970 and GeForce GTX 580. So, we know what we’d pay for this new board. If our target is close, we’d be looking for something under £400/under $500 USD (the Radeon HD 7970 currently retails for $550 in the U.S.).
What makes the Radeon HD 7950 worth a few bucks more than Nvidia's GeForce GTX 580? Well, let’s have a closer look at the card itself…
Update: Before publication, but after our launch coverage was finalized for international translation, AMD let us know that the Radeon HD 7950 should sell for $450 in the U.S. That's well below where I thought the company would target, given its competition. Clearly, AMD is pricing the 7950 to out-value Nvidia's GeForce GTX 580 (or force its competitor to adjust downward) rather than exist in a price structure defined by the company's single-GPU flagship. Advantage: AMD. Sadly, no word on UK pricing just yet.

That's a Radeon HD 7970 up top and a Radeon HD 7950 down below. In the right light, they'd pass as twins.
Meet AMD’s Radeon HD 7950
Physically, the Radeon HD 7950 is identical to AMD’s already-available Radeon HD 7970—save one distinguishing feature: a second six-pin auxiliary power connector. That’s a telltale indication of a sub-225 W maximum board power (75 W from the slot, plus up to 75 W from each plug). In fact, AMD rates the 7950 right at 200 W. In comparison, the Radeon HD 7970’s power ceiling is 250 W, necessitating its eight- and six-pin power connectors.
A 10.5” PCB is extended out an additional half of an inch by a metal base plate and plastic shroud. So, plan accordingly when you pick a chassis. This card is fairly long.
As with the Radeon HD 7970, AMD employs a centrifugal fan mounted on one end of the Radeon HD 7950, which blows across the length of the card and exhausts heated air out the back of your chassis. This is the design we prefer. It wasn’t possible to cool the Radeon HD 6990 or GeForce GTX 590 the same way. In both examples, a centre-mounted fan exhausted some air from a rear I/O slot and everything else was recirculated.
Because it relies on effective exhaust, one of the card’s two slots is grated for unrestricted air flow. The other slot is populated with four display outputs: one dual-link DVI connector, one full-sized HDMI port, and a pair of mini-DisplayPort outputs.
Board partners will almost certainly bundle a variety of adapters, so be sure you’re getting the components you need before making a purchase. The two Sapphire Radeon HD 7970s we bought came with DVI-to-VGA, mini-DisplayPort-to-DisplayPort, mini-DisplayPort-to-single-link DVI, and HDMI-to-DVI adapters. Meanwhile, the XFX R7950 Black Edition card we received only included an HDMI-to-DVI adapter.
More notable, though, is that all four outputs can be active at the same time, supporting extensive display configurations that you simply cannot achieve on a single Nvidia-based board.
Tahiti Pro: Same GPU, But On A Diet
Radeon HD 7950 centres on the same 4.31 billion-transistor Tahiti GPU as AMD’s faster, more expensive flagship, manufactured on TSMC’s 28 nm node.
However, instead of sporting 32 Compute Units, this scaled-back model comes equipped with 28 Compute Units. As you know, each CU plays host to four Vector Units, each with 16 shaders, ALUs, Stream Processors, or whatever else you’d like to call them. That’s a total of 64 SPs per CU. A quick little multiplication (64*28) gives you a grand total of 1792 SPs on this chip.
And because each of those four missing CUs also included four texture units, that specification drops from 128 to 112.
To help differentiate the Radeon HD 7950 even further, AMD dials back its core clock rate to 800 MHz (down from 925 MHz on the reference Radeon HD 7970). Peak compute performance correspondingly drops to 2.87 TFLOPS from 3.79 TFLOPS.
The render back-ends are independent of the CUs, and AMD leaves all eight ROP partitions enabled, yielding up to 32 raster operations per clock cycle. Six 64-bit memory controllers feed the partitions through a crossbar. An aggregate 384-bit data path populated with 3 GB of GDDR5 memory operating at 1250 MHz adds up to 240 GB/s of bandwidth. That’s a slight drop from the Radeon HD 7970’s 264 GB/s, but still a very substantial increase over the Radeon HD 6970.
| Radeon HD 7950 | Radeon HD 7970 | Radeon HD 6970 | GeForce GTX 580 | |
|---|---|---|---|---|
| Stream processors | 1792 | 2048 | 1536 | 512 |
| Texture Units | 112 | 128 | 96 | 64 |
| Full Colour ROPs | 32 | 32 | 32 | 48 |
| Graphics Clock | 800 MHz | 925 MHz | 880 MHz | 772 MHz |
| Texture Fillrate | 89.6 Gtex/s | 118.4 Gtex/s | 84.5 Gtex/s | 49.4 Gtex/s |
| Memory Clock | 1250 MHz | 1375 MHz | 1375 MHz | 1002 MHz |
| Memory Bus | 384-bit | 384-bit | 256-bit | 384-bit |
| Memory Bandwidth | 240 GB/s | 264 GB/s | 160 GB/s | 192.4 GB/s |
| Graphics RAM | 3 GB GDDR5 | 3 GB GDDR5 | 2 GB GDDR5 | 1.5 GB GDDR5 |
| Die Size | 365 mm2 | 365 mm2 | 389 mm2 | 520 mm2 |
| Transistors (Billion) | 4.31 | 4.31 | 2.64 | 3 |
| Process Technology | 28 nm | 28 nm | 40 nm | 40 nm |
| Power Connectors | 2 x 6-pin | 1 x 8-pin, 1 x 6-pin | 1 x 8-pin, 1 x 6-pin | 1 x 8-pin, 1 x 6-pin |
| Maximum Power | 200 W | 250 W | 250 W | 244 W |
| Price (Street) | £450 | ~£270 | ~£370 |
- AMD's Tahiti Pro Goes Heads-Up With Nvidia's GF110
- Tessellation Performance And Audio Output
- Overclocking With XFX’s R7950 Black Edition
- Test Setup And Benchmarks
- Benchmark Results: 3DMark 11
- Benchmark Results: Battlefield 3
- Benchmark Results: Crysis 2
- Benchmark Results: The Elder Scrolls V: Skyrim
- Benchmark Results: DiRT 3
- Benchmark Results: World Of Warcraft: Cataclysm
- Benchmark Results: Metro 2033
- Benchmark Results: Sandra 2012
- Benchmark Results: MediaEspresso 6.5 And LuxMark
- Benchmark Results: vReveal
- 2D Performance Via GDI And GDI+
- CrossFire And SLI: 3DMark 11
- CrossFire And SLI: Battlefield 3 And Crysis 2
- CrossFire And SLI: DiRT 3, Metro 2033, And LuxMark
- Power, Temperatures, And Noise
- CrossFire And SLI: Power Consumption And Noise
- One Year Later: A Great GeForce GTX 580 Alternative




It will never be a fair game if physX is still a factor in this equasion. Pity, as Im very much for AMD GPUs (own a 5870 Lightning with joy and proud) but my next card will be 'green' just because of that simple fact
On topic though these new cards are really exciting! It's great to see AMD really making up for mistakes in the CPU sector. My next card will definitely be a 7000 series
And again - as I said - big fan of AMD, have spent loads of bucks on MSI 5870 Lightning when was released, but having came across some games that simply demanded of me to switch off PhysX just because my card doesnt do it, left me with rather mixed feelings.... It has nothing with big/small company or advertising/researches etc... I just dont like being limited, and unfortunatelu - PhysX is in use and game devs will keep on using it whether you like it or not...
I wouldnt declare myself yet as for next card, as you should really wait for a reply from green team. so far - you are comparing 2 products with a year-difference in concept and manufacturing, and thats a lightyear in industry.
cheers.
Another reason I prefer AMD is that I would like to discourage the adoption of PhysX - as I said I prefer open standards to closed proprietary, and the only reason PhysX gains so much ground is because people buy into it. Therefore I prefer to "vote against" it by buying AMD cards. That way hopefully more game developers will be encouraged to program their games to use Havok (or another similar open physics engine) which is supported by both platforms.
Your "voting against" seem to me like shooting yourself in the foot, as you gain pretty much nothing and PhysX will still be in use...
I hear what you say, AMD has still alot of good features superior to Nvidia on some fields, but they are irrelevant for me as I simply dont need/use them. Lack of physic cpu however - is not.
My general point is - when I was buying my AMD card I knew PhysiX might be an issue in future, but the price of the card (100e less then top-of-the-line Nvidia, that was back then similary powerful but much more power/heat hungry) and it capabilities justified choosing it over Nv. But now, with current pricing sheme from AMD and soon-to-be released Nvidia - It doesnt seem justified to buy AMD, atleast at that very moment.
It is true that we all make judgements before making our purchase one way or the other, and this discussion between you and I just highlights the fact that everyone can have very different values for those judgements
I remember only a couple of years agothis would have been amazing result. Great work from both team with multi-GPU drivers!