NVIDIA GTX670 Review

Based on Kepler architecture, the NVIDIA GTX670 has the potential to be a very powerful yet more affordable graphics card than the GTX680. See how it compares against today’s leading graphics cards…

Product on Review: NVIDIA GTX670 2GB GDDR5
Manufacturer and Sponsor: NVIDIA
Street Price: £319.99

NVIDIA are currently performance kings with their flagship GTX680 dethroning the AMD7970. Up until today, NVIDIA had little answer to the HD7970’s little brother, the HD7950 other than the GTX570 and GTX580 series based on older technology. Today however see’s the GTX670 break into the foray hoping to grab back the mid/high market performance crown from the HD7950.

The GTX670 is heavily based on the GTX680, having a very similar core that while trimmed back from the flagship GTX680, still retains its Kepler foundations. With 7 SMX units, one less than the GTX680, the GTX670 still carries 1344 CUDA cores. The GTX670 also inherits the GTX680’s memory subsystem configuration of 8x256MB modules (2GB) which are kept in check by four 64-bit memory controllers making a 256-bit memory interface. The baseclock of the GTX670 is set to 915MHz with a typical GPU Boost speed of 980MHz depending on load conditions. This along with a 6008MHz memory data rate makes for some impressive figures which will hopefully be translated to our screens in terms of performance.

In-game performance however is not all the GTX670 has to offer. Like the GTX680, NVIDIA are keen to push the power efficiency of the GTX670 GPU. As you will see later in the review, the mainboard in quite unique in terms of high end graphics cards and is deserving of close investigation but to summarise, the power circuitry has pretty much been redesigned, turned around, flipped back to front and moved from one area of the card to the other. While this makes obvious visual differences, none more so than the PCB length, crucially it improves power efficiency and integrity as the power source is much closer to the core.

Here’s what NVIDIA had to say about their latest graphics card:

The GeForce GTX 670 is built from the same DNA as the GTX 680, using the same GK104 GPU, and 2GB of GDDR5 memory running at the same clock speeds as GTX 680. As a result, the GTX 670 delivers best-in-class gaming performance that is faster than AMD’s competing Radeon 7950 GPU. In fact, across a suite of more than 25 of the most popular games/benchmarks, the GeForce GTX 670 ties the competition’s flagship Radeon 7970 in performance! For performance-minded gamers that want to experience the Faster, Smoother, Richer gaming experience that our newest GeForce products offer, the GeForce GTX 670 is the perfect choice!

Specification & Kepler Architecture

It was almost two years to the day that we saw the introduction of NVIDIA’s Fermi, NVIDIA’s previous architectural change. The GF100 featured 512 stream processors in a 16×32 format built by TSMC in a 40nm process. Sporting OpenGL 4.0 and DirectX 11, enthusiasts climbed over each other to get the latest and greatest GPU from NVIDIA. While the performance was there, power efficiency was very poor with the cards consuming lots of power and running very hot.

Enter the 5 series 8 months later and many would say the GTX580 was the card the GTX480 should have been. It was more powerful thanks to the fully unlocked memory controller (6x64bit), ran cooler and thus became a firm favourite among the high end GPU market.

For a little over a year the GTX580 enjoyed sitting atop of the GPU pile (save for dual GPU variants) and it wasn’t until the AMD HD7970 emerged in December 2011 that the GTX580 lost it’s performance crown. NVIDIA however had not been resting on their laurels…

Kepler Core
The successor to Fermi is codenamed Kepler. Listening to feedback of Fermi from gamers around the world, NVIDIA sought to create a graphics card that was not only the best money could buy in terms of performance but crucially it had to run cool and quiet to make for a power efficient model. Kepler addresses these issues in two ways, GPU Boost which we will discuss further in our overclocking section of the review and a redesigned streaming multiprocessor.

The GTX670 is equipped with the same GK104 core of the GTX680 which NVIDIA claim is their highest and most power efficient GPU to date. Fabricated on the 28nm process, every component was designed with power efficiency in mind to ensure the GPU gave the best performance-per-watt possible.

While the 28nm manufacturing process holds the bulk of the power saving features, the way the new architecture works is also key to furthering Kepler’s power reduction. SMX, an evolution of the SM from Fermi is NVIDIA’s new streaming multiprocessor:

GTX680 Kepler Core

To feed the new SMX, each unit has four warp schedulers, each capable of firing off two instructions per warp, every clock. With a redesigned scheduling function, the GTX680 is a lot less complex and much more streamlined allowing the compiler to determine which instructions will be issued and can provide this information direct to the hardware block rather than going around the houses using Multi-port decode and a register scoreboard along with the dependency check before the information gets issued. This method is both quicker and more importantly, more power efficient.

GTX670 x7 SMX

The Block diagram above shows the Kepler core layout with one less SMX than it’s bigger brother, the flagship GTX680.

Perhaps the biggest change to the processor core is the omission of the old Shader Clock. The shader clock was getting tired as it was part of the old Tesla architecture which was implemented as an area optimisation. Because of the way Kepler executes instructions at a much more streamlined manner and at a higher clock rate, fewer copies of the execution unit need be made.

Another improvement over Fermi with the introduction of SMX is the redesigned Polymorph engine (2.0). The Polymorph engine takes card of the tessellation workload of the GTX680. The design of the new Polymorph engine is to ensure that the tessellation we see on screen has little (as possible) impact on the rendering performance. What you may find bizarre though is that NVIDIA have cut the Polymorph engine count in half to 8 from Fermi’s 16 yet claim it is almost twice as quick. This is thanks to the improved core an memory clockpeed.

Overall then, it seems NVIDIA have outdone themselves. Higher clockspeeds on both core and memory, 3x the amount of stream processors yet streamlined by eliminating the shader clock to cut the amount of power consumption without compromising overall performance.

Here are the official specifications of the NVIDIA GTX670:

Processing Units
Graphics Processing Clusters
7 SMXs
1344 CUDA Cores
112 Texture Units
32 ROP Units

Clock Speeds
915 MHZ Base Clock
980 MHz Boost Clock
6008 MHz Memory Clock (Data rate)
512KB MHz L2 Cache Size

Memory
2048MB Memory Total Video Memory
256-bit GDDR5 Memory Interface
192.2 GB/s Total Memory Bandwidth
102.5 GigaTexels/sec GB/s Texture Filtering Rate (Bilinear)

Physical
28 nm Transistor Count
3.54 Billion Connectors
2 x Dual-Link DVI 1 x HDMI 1 x DisplayPort Form Factor
Dual Slot Power Connectors
2 x 6-pin Recommended Power Supply

Power & Thermal
500 Watts Thermal Design Power (TDP)1
170 Watts Thermal Threshold2
98° C

Features

SMX
Kepler GPUs feature our next-generation Streaming Multiprocessor, SMX. To improve performance, SMX features substantially more shader, texture, and geometry processing units, while the double speed processor clock present in prior GeForce GPUs has been eliminated in favor of more CUDA cores operating at the lower-speed graphics clock. This change dramatically improves Kepler’s performance per watt.

GPU Boost
GPU Boost dynamically adjusts the GPU’s clock speed automatically based on GPU operating conditions. Dedicated hardware circuitry constantly monitors GPU power consumption. GPU Boost automatically adjusts clocks to achieve the maximum possible clock speed while remaining within a predefined power target. GPU Boost operates completely autonomously with no game profiles and no intervention required by the end user, providing an instant performance boost to gamers.

Anti-Aliasing
NVIDIA FXAA technology harnesses the power of the GPU’s CUDA Cores to reduce visible aliasing. It is applied with other post-processing steps like motion blur and bloom. For game engines making use of deferred shading, FXAA provides a performance and memory advantage over deferred shading with multi-sample anti-aliasing (MSAA). FXAA reduces but does not completely eliminate shader aliasing. FXAA’s chief advantage over traditional MSAA is higher performance. In many cases, FXAA can be applied at a cost of 1ms per frame or less, resulting in frame rates that are often 2x higher than 4xMSAA with comparable image quality.
TXAA is a new film-style AA technique that’s designed to exploit GeForce GTX 690’s high texture performance. TXAA combines the raw power of MSAA with sophisticated resolve filters similar to those employed in CG films. TXAA is available with two modes: TXAA 1 and TXAA 2. TXAA 1 offers visual quality on par with 8xMSAA with the performance similar to 2xMSAA, while TXAA 2 offers image quality that’s superior to 8xMSAA, with performance comparable to 4xMSAA.

HDMI Support
NVIDIA offer the HDMI functionality to provide access to premium digital content. HDMI enables gaming enthusiasts to seamlessly connect to their LCD monitor to bring the ultimate multimedia experience. (Only 1 single HDMI cable is required while streaming audio/video data to flat-panel display devices, such as Plasma/LCD TVs, or projector.)

NVIDIA 3D Vision
NVIDIA® 3D Vision™ technology is a combination of Graphics Processor Units (GPU), specialized 3D glasses, software, and certified displays and projectors that deliver an immersive 3D experience on your PC or workstation. For a complete list of system requirements for NVIDIA 3D Vision Technology

NVIDIA 3D Vision Surround
NVIDIA 3D Vision Surround expands your field of view across three 3D monitors for Breathtaking panoramic gaming. At an ultra-wide resolution of 5760×1080, games like Battlefield Bad Company 2 have to be played to be believed.

CUDA
CUDA is NVIDIA’s parallel computing architecture that enables dramatic increases in computing performance by harnessing the power of the GPU to speed up the most demanding tasks you can run on your PC.

SLI
NVIDIA SLI technology links multiple GeForce GPUs together for dramatically improved graphics performance. With over 1000 supported applications and used by over 94% of multi-GPU PCs on Steam, SLI is the technology of choice for gamers who demand the very best.

NVIDIA PureVideo
Blu-ray and HD DVD movies are bringing a new level of movie-viewing experience; with high-definition image quality far surpassing standard-definition DVDs. NVIDIA PureVideo™ HD2 technology provides unsurpassed Blu-ray and HD DVD movie picture quality.

Dual Link DVI
Dual-link DVI convertible output supports Video/Audio signal integration through DVI to HDMI interface, which drivers resolution of a digital display up to 1920×1200 or higher.

PhysiX
PhysX™ is designed specifically for hardware acceleration by powerful processors with hundreds of cores. Combined with the tremendous parallel processing capability of the GPU, PhysX™ will provide an exponential increase in physics processing power and will take gaming to a new level delivering rich, immersive physical gaming environments

First Look

Top

The top of the card features a new black plastic shroud which houses the heatsink along with the fan which is placed slightly off centre towards the end of the card. The shroud feels slightly hollow and light with little substance – something we will investigate later.

Bottom

Flipping the card over, we see that the power circuit board is much shorter than the shroud. Amazingly the circuitry takes up just 66% of the overall card length with the area where we would usually find the voltage regulation completely missing! You may also notice the card has memory modules on the rear of the card with 4 empty spaces hinting at 4GB GTX670s in the future perhaps?

I/O Area

The I/O area is identical to the GTX680 in that it has 2x Dual-Link DVI ports, a DisplayPort along with a HDMI port. Because the card is a dual slot design, there is a small cut-out area for venting which is the only vent on the card being that the shroud fully encloses the heatsink.

Power Ports

The GTX670 requires two 6pin PCIe power connectors capable of delivering 75W each. NVIDIA recommend a 500W PSU with the thermal design power of the card being 170W during average use.

SLI Tabs

Twin SLI tabs mean the GTX670 can be linked with other GTX670’s in a multi card SLI configuration; something we will be looking at a later date.

Overview

Overall, the new design is typical of today’s graphics cards designs with the fan being at the opposite end to the venting area. the card is surprisingly small being just 26.5cm in length. Below are just a few sample shots of what we expect to see from NVIDIA’s board partners and of course, what we intend to be looking at in the very near future here at Vortez:

Let’s go a little deeper and see what lies at the heart of the GTX670…

Closer Look (Heatsink)

The cooler is relatively easy to remove although it was a little confusing at first owing to the fact the cooling shroud is in two parts – the fan section and main shroud.

The fan is the same design used on the reference GTX680 which as we saw in our previous ZOTAC GTX680 review was quiet during normal running but became noticeable under load.

With the fan removed we can see that the shroud is very large but serves little purpose other than to accommodate the cooling fan and small heatsink. Were the core closer to the I/O area, I have no doubt the cards length could be cut down to the size of the PCB as this would allow the fan to be positioned mid card rather than at the end.

The heatsink is a very basic design. A thick finned aluminium finned array sits on top of a copper plate which makes direct contact to the core. Hopefully the GTX670 will be a very cool card as the heatsink design leaves does not bestow a huge amount of confidence in cooling an inferno.

Let’s take a look at the GTX670 circuitry and components…

Closer Look (Circuitry & Components)

With all of the cooling shroud and heatsink removed we get to see the GTX670 circuit board or more accurately the lack of it! NVIDIA have done a fantastic job of cramming all of the circuitry and components into such a small area. Of the 8 memory module slots available, only four are populated which mirrors the rear of the PCB. These modules frame the main GPU Kepler core with VRM situated closest to the I/O area.

The Voltage Regulation Module (VRM) is made up of a 4+2 digital design. The core 4 phase design is made up of YAGEO inductors, each set with 3 MOSFETs and a solid capacitor. The GDDR5 memory has 2 phase control , each with a single MOSFET which makes the 4+2 design.

NVIDIA has used 2GB, or 8x256MB GDDR5 modules with a product code of H5GQ2H24AFR R0C which are specified to 1500 MHz (QDR 6000 MHz) clock. Hopefully we will be able to push these a little further than spec.

The Kepler core is clocked to 915MHz (980MHz typical Boost speed). With 1344 CUDA cores and 7 SMX units bolstered by the 256-bit (4x64bit) memory controller, we hope to see some serious performance out of this card.

Here you can see just how small the PCB of the GTX670 really is. The board measures just 17.5cm and could quite easily be mistaken for an entry level graphics card or even a sound card, it really is that small. Hopefully, women across the world will be proven right when the say ‘size doesn’t matter’!

Test Setup

With the latest Intel chipset release we decided to update our ageing X58 setup to the new X79 chipset. Not only that but we will be using the flagship Core i7-3960X Extreme Edition processor clocked to 4.5GHz to ensure we have no CPU bottlenecks. With 16GB of ram on board there should be minimal paging so the benchmarks we run today will hopefully give a true reflection of the graphics card’s performance.

Some of the components for our test bench were kindly donated by CORSAIR who provided the majority of components without whom we would not have been able to bring you this review so a big thanks to them.

Graphics cards on test:

NVIDIA GTX670

NVIDIA GTX670 OC

HIS HD 7870 IceQ Turbo
MSI HD 7870 Twin Frozr III OC
GIGABYTE HD7850 OC WindForce x2
ZOTAC GTX680 2GB GDDR5
AMD HD7870 2GB GDDR5
Zotac GTX580 AMP2! 3GB GDDR5
XFX R7970 Black Edition 3GB GDDR5
XFX R7770 Black Edition ‘S’ 1GB GDDR5
AMD HD7750 1GB GDDR5
AMD HD7770 1GB GDDR5
HIS HD7970 3GB GDDR5
XFX DD Radeon R7950 3072MB GDDR5
PowerColor PCS+ Radeon HD7950 3072MB GDDR5
AMD Radeon HD7950 3072MB GDDR5
AMD Radeon HD7970 3072MB GDDR5
ZOTAC GTX570 AMP! 1280MB GDDR5
NVIDIA GTX570 1280MB GDDR5
MSI GTX560Ti-448 Twin Frozr III 1280MB GDDR5
MSI GTX560Ti-384 Twin Frozr III 2GB GDDR5
AMD HD6990 4GB GDDR5

NOTE: For this review we will be using the very latest 301.33 drivers which is a change of driver from the 301.10 drivers used on the GTX680 series.

Motherboard: MSI X79 Big Bang X-Power II
CPU: Intel Core i7-3960X Extreme Edition @ 4.5GHz
RAM – 16GB (4x4GB) Corsair Vengeance (Red) DDR3 @ 1866MHz 9-10-9-27
Power Supply – ANTEC High Current Pro 1200W
Hard Drive – Kingston HyperX 240GB
Cooler – Corsair H100

Benchmarks
We have also updated our range of benchmarks to include the following games which will give the graphics cards a challenge and sort the wheat from the chaff. Each benchmark will be run at both stock and maximum overclock settings and utilise 1920×1080 and 2560×1600 resolutions along with AA at various levels (application dependent):

Battlefield 3
Crysis 2
Crysis Warhead
Metro 2033
Batman: Arkham City
Elder Scrolls: Skyrim
DiRT 3
Futuremark 3DMark 2011
Unigine: Heaven 2.5

Let’s see how today’s graphics card performed…

Overclocking (GPU Boost)

Overclocking via NVIDIA’s GPU Boost was covered in our ZOTAC GTX680 review so I won’t go into detail here on the attributes and pitfalls of using this method to overclock a GPU. Suffice to say though it is effective and as we shall see below, can be used to great effect..

The reference card comes with the core clocked at a rather conservative clockspeed of 915MHz. This will however boost up to around the 980MHz mark depending on load conditions.

Going straight for the jugular, we ramped up the power target and managed to run a few benchmarks with the core running at a ridiculously fast 1260MHz! Sadly, this was not 100% stable. We did however eventually manage to reach good stability at 1215MHz and so we settled for a final, rock solid stable clockspeed of 1200MHz which we used to run our suite of benchmarks. Memory overclocking went well too with a 105MHz offset attained equating to 6220MHz effective.

Power Consumption, Temperatures & Acoustics

Power Consumption

To test for power consumption we do not use anything too technical, just a wall meter which measures the total system power draw minus the monitor.

Despite the card being touted as very power efficient, it still drew as much power as a HD7970 at reference speeds. Thankfully this measurement did not increase dramatically when the card was overclocked, reaching just 349W, 1W less than a reference GTX680. Compared to the GTX570, it consumed 15W less which is a good achievement, especially considering the performance difference of the two cards.

Temperature

To test temperatures we measured idle temperatures after booting windows, letting all applications finish loading and ran a few benchmarks. Once the benchmarks were complete we left the card to reach a cooling plateau where we then took the idle temperatures. For the load tests, we would normally run Furmark for 20 minutes, taking the absolute maximum temperature attained however we found that this throttled the card and resulted in spurious results. So we set Heaven running continuously for 20 minutes and used this as a temperature result as the card did not throttle with this application.

While the GTX670 did not embarrass itself, it was not as impressive as the GTX680. Despite it’s diminutive size, it still kicked out a fair amount of heat. I am perhaps being a little harsh on the GTX670 because apples for apples, it is cooler than it’s competitor, the HD7950, under load by four degrees while being slightly warmer in idle conditions.

Acoustics
The GTX670 is near as dammit silent when idle in fact anything below a 40% fan speed you would be hard pushed to hear the card in an enclosed unit. At 50% and above there is a dull whine that increases incrementally with the speed set. Under AUTO conditions, the fan noise was audible but not intrusive by any means and certainly quieter than previous GTX incarnations.

Let’s move on to our suite of gaming and synthetic benchmarks…

Battlefield 3

Battlefield 3 leaps ahead of its time with the power of Frostbite™ 2, the next instalment of DICE’s cutting-edge game engine. This state-of-the-art technology is the foundation on which Battlefield 3 is built, delivering enhanced visual quality, a grand sense of scale, massive destruction, dynamic audio and incredibly lifelike character animations. As bullets whiz by, walls crumble, and explosions throw you to the ground, the battlefield feels more alive and interactive than ever before. In Battlefield 3, players step into the role of the elite U.S. Marines where they will experience heart-pounding missions across diverse locations including Paris, Tehran and New York.

Average and minimum frames per second were measured using Fraps during the parking lot scene on Operation Sword Breaker. High and Ultra presets were loaded at both resolutions.

Crysis 2

Crytek took an internet beating from its loyal fans due to the fact that they pandered to the console masses and dumbed down the graphics to DirectX 9. Fortunately, fans of the PC version of Crysis managed to force Cryteks hand and they have since developed a DX11 patch and have also enhanced the textures with added tesselation. It is for this reason that we have decided to include it in our suite of benchmarks.

To test the cards we used the Crysis 2 benchmark courtesy of Adrenaline with both the 1.9 patch, DX11 update and Hi-res texture pack. Settings were manually placed to Ultra, DX11 and tessellation enabled with the Central Park map being run 3 times per resolution benchmark test.

Crysis Warhead

Following the success of Crysis, the stand alone expansion “Warhead” was hotly anticipated to bring more game play, more weapons, improved visuals whilst maintaining better performance, the latter being what gamers wanted most. After all how many people upgraded their rigs just to play this game… In the game, you play as the upbeat Brit Sergeant “Psycho” Sykes, chasing down a Korean nuclear warhead. Throw in some ice shooting aliens and we’re bound to have a great game. It sure delivered.

Testing was done using Framebuffer’s Crysis Warhead benchmarking tool. The tests were configured to DirectX 10 at Enthusiast levels. Each test on the Ambush map was looped three times from which the average FPS was recorded.

Batman: Arkham City

Batman: Arkham City builds upon the intense, atmospheric foundation of Batman: Arkham Asylum, sending players soaring into Arkham City, the new maximum security “home” for all of Gotham City’s thugs, gangsters and insane criminal masterminds. Set inside the heavily fortified walls of a sprawling district in the heart of Gotham City, this highly anticipated sequel introduces a brand-new story that draws together a new all-star cast of classic characters and murderous villains from the Batman universe, as well as a vast range of new and enhanced gameplay features to deliver the ultimate experience as the Dark Knight.

The results below were obtained from the builtin benchmark utility from the game. All the settings were set to

The Elder Scrolls: Skyrim

Skyrim is not a direct successor to the very popular Oblivion. Instead it takes place 200 years after the events of Oblivion. The non-linear playing that made the Elder Scrolls such a popular series does however make a return along with the beautiful scenery the encompasses the world of Skyrim.

Average and minimum frames per second were measured using Fraps during the drop down passage to Riverwood. V-sync was disabled to allow fluctuating (higher the 60) FPS for these runs. It is however recommended that v-sync is left enabled during normal gameplay due to the games dynamics.

DiRT 3

As players race to elevate their global standing, DiRT 3 is back delivering mud, sweat and gears world over: from the intense weather-beaten rally stages of Europe, Africa and the US, to executing performance driving showcases and career challenges where car control is pushed to spectacular limits.

The in-game benchmarking tool was used to test performance. All the display settings were set to the maximum available and DirectX 11 was applied. The average FPS was recorded at the end.

Metro 2033

Based on the novel by the same name, Metro 2033 is a first person shooter with elements of survival horror. As Artyom, you trawl through the mutant infested metro systems of post-apocalyptic Moscow. The game delivers presents a grim ambience that reflects on the overall atmosphere of the underground setting. Metro 2033 uses the setting as a back drop to showcase some of the best visuals of any games out now, making it the ideal benchmark for those looking for the best graphics card.

The bundled benchmarking tool was used on Metro 2033, configuring the settings to High and making use of DirectX 11. The frontline scene was looped 3 times for each configuration. The average FPS was recorded at the end.

Futuremark: 3DMark 11

3DMark 11 is the latest version of the world’s most popular benchmark. Designed to measure your PC’s gaming performance 3DMark 11 makes extensive use of all the new features in DirectX 11 including tessellation, compute shaders and multi-threading. The benchmark was run in both Performance and Extreme presets.

Unigine: Heaven 2.5

Heaven Benchmark is a DirectX 11 GPU benchmark based on advanced Unigine™ engine from Unigine Corp. It reveals the enchanting magic of floating islands with a tiny village hidden in the cloudy skies. Interactive mode provides emerging experience of exploring the intricate world of steampunk.

Conclusion

When I first cast eyes on the GTX670 I was could hardly be described as astounded. The aesthetics of the card are nothing spectacular, much less stunning. The card could quite easily be dismissed as uninspiring truth be told. It’s not an ugly duckling, far from it but as it’s a reference design, the GTX670 shroud is bare and desolate without bright manufacturer stickers. the card only becomes interesting when it is flipped over and you realise that the PCB is so small in comparison to other high end offerings. You may even feel robbed because to look at, the fan shroud makes the card appear much larger than it actually is. If you can see past the uninspired aesthetics and instead concentrate on the physical attributes and performance figures then the story couldn’t be more different.

Being a reference design it would be harsh to be overly critical of the card simply because of it’s looks. What is infinitely more important is the NVIDIA GTX670’s performance output and here is where the GTX670 hits top marks. Not only does it soundly put the AMD HD7950, it’s most direct competitor, in it’s place but it has the means to stand toe to toe with AMD’s flagship GPU, the HD7970.

Throughout our run of benchmarks, the GTX670 impressed. So much so I had to go back and re-run a number of them time and again, such were the unbelievable performance figures. While there have no doubt been driver enhancements with the 301.33 version which may have artificially enhanced the comparative performance against the GTX680, the simple fact remains that the NVIDIA GTX670 is, like for like, apples against apples, a faster card than the AMD HD7950. When you consider the PCB of the GTX670 is over 10cm shorter than a HD7950 yet the card has higher performance, equal power consumption and lower operating temperatures than the HD7950 it is certainly an impressive triumph and judging by the PCB, with 4GB versions no doubt just around the corner, the performance of the card will only increase.

I expect reference card prices to be around the $400 mark which roughly translates to a UK mark-up of £300-330 depending on manufacturer with overclocked editions carrying the usual premium. If these prices transpire at retail then the NVIDIA GTX670 is a no brainer and will no doubt put the ‘price drop ball’ back firmly in AMD’s court. Full range of GTX670 graphics cards.

Pros:
+ Fastest card in it’s class
+ Excellent all round performance
+ Quiet
+ Cool
+ Great Overclocking potential

Cons:
– Uninspired Aesthetics
– Power ports near the centre of the card