Introduction to GK106 – The Affordable Kepler
The GK106 chip was introduced on 13th September with the launch of GeForce GTX 660 and GeForce GTX 650 graphic cards which paved NVIDIA’s way in to the sub-$250 market.
NVIDIA initially has access to a much lower TSMC 28nm capacity which affected its long term GPU supply. This caused a long delay for sub-$300 GPUs to arrive after the launch of GTX 680 and GTX 670. A month before the GK106’s official debut, NVIDIA had launched the GTX 660 TI. Once again featuring its highly acclaimed Kepler GK104 architecture, the GPU was available at a sweet price point of $299 pumping out incredible performance to consumers. However there was yet a bigger gap for NVIDIA to fill in which was already dominated by AMD’s HD 7800 series GPUs, the $150-$250 inventory was missing from NVIDIA’s lineup.
Only a month after the launch of GeForce GTX 660 Ti was it to be filled with the simultaneous launch of two GK106 GPUs, the GeForce GTX 660 and GTX 650. NVIDIA has always heavily depended on its sub-$250 price-range cards but with AMD dominating it with their own Southern Islands cards, the competition was though and today we are gonna show how NVIDIA’s GeForce GTX 660 fares against the GPUs from Red Team.
A Brief Look at the NVIDIA GK106 Architecture
Judging from the block diagram NVIDIA provided, the GK106 reuses the same principals and design scheme of the GK104 architecture. This is the first time that we have seen the same level of consistency between NVIDIA’s GPU for its entire GeForce Kepler lineup ranging from the Entry Level GK107, Mid-End GK106 and High-End GK104.
At first glance, we can see that the GK106 incorporates three GPC’s (Graphics Processing Clusters). One of those three has a single SMX unit within it, one SMX unit is either missing or left out a whole. Each SMX unit features 192 cores which equals to a total of 960 Cores on the GeForce GTX 660’s GK106 die. Each GPC is assosiated with its own memory controller. Among the Kepler GK106 die, you can see a PCI-e Gen 3.0 Host interface, 192-bit wide GDDR5 memory interface and NVIDIA’s latest GigaThread Engine situated underneath those two.
The memory runs at 6 GHz effective frequency but due to a cheaped out interface like its bigger sibling, the GTX 660 ends up with only 144 GB/s bandwidth compared to 192 GB/s on High-End GK104 chips.
Each SMX has its own dedicated and shared resources with the new Polymorph 2.0 engine handling raster operations such as Vertex Fetch, Tessellator, Viewport Transform, Attribute Setup and Stream output hence pumping two times the primitive and tessellation performance compared to Fermi SM units. There is one Raster Engine per GPC, three in total that handles Edge setup, Rasterizer, Z-Cull through 24 Raster Operation Processors or ROPs. Another improvement over Fermi is the implementation of ‘Kepler Bindless Textures’ which increases the number of textures a shader can reference to over a million, whereas this was restricted to 128 on Fermi. The new feature allows faster rendering of textures and provides richer texture detail in a scene. In total there are 112 Texture memory Units on-board the Kepler GK106 die.
Aside the technical bits, the GK106 retains the features of its bigger brother (GK104) such as TXAA/FXAA, GPU Boost, Adaptive V-Sync, 3D Vision Surround, NVIDIA NVENC and PCI-Express 3.0 compatibility. Brief details on these technologies can be found in our review here.
What Does NVIDIA GK106 Means to Gamers?
To gamers, NVIDIA’s latest GK106 chip means great performance with the best power efficiency at an affordable price range. Aside from features such as GPU Boost, TXAA, Adaptive V-Sync, etc which we mentioned above, the GK106 from NVIDIA offers 60% better performance over its Fermi GTX 460 and 40% better performance over GTX 560.
With the adoption rate to DirectX 11 increasing with each upcoming titles, developers have started to add new features such as Tessellation, Depth of Field and High-Resolution Textures. To enable these effects you got to have the right hardware to run them. Gamers have been stuck with old DirectX 10 cards for a while, they offer a good punch but they just can’t handle the new DirectX 11 effects. One thing which matters to gamers most other than performance is price-range. As i detailed earlier that gamers rely more towards the Sub-$250 range while Kepler has only been available at the lowest of $299 (GTX 660 Ti), till now.
The GeForce 660 enables these gamers to get better performance and better visuals out of upcoming gaming titles at an affordable price range, hence if you’re stuck with a old-gen 8800 GTX or 9600 GTX GPU, now’s the right time to upgrade.
The bigger memory buffer of 2 GB is also an improvement over NVIDIA’s past GPUs which were limited to 1024 MB. The higher memory buffer enables gamers to run the latest titles at 1920 x 1080 HD resolution which has become the resolution of choice for PC gamers over the past couple of years. The GK106 enable GTX 660 also features 3D Vision support and can be easily enabled via single GPU.
ASUS GeForce GTX 660 DirectCU II – DIGI+ Goodness!
ASUS has given its GeForce GTX 660 the DirectCU II treatment coupled with a non-reference PCB. The GeForce GTX 660 is also the first GPU to make use of the latest 28nm GK106 chip, followed by GTX 650 and the upcoming GTX 660 SE. Continue reading onward to see what specifications does the ASUS GTX 660 DirectCU II holds along with its GPU-Z shot.
The ASUS GeForce GTX 660 DirectCU II is based on a non-reference PCB design and equipped with the DirectCU II series cooling solution. The PCB is equipped with a 6 Phase Digi+ VRM with Super Alloy Power, the reference GTX 660 ships with a 4 Phase VRM. The beefed up power design allows superior stability, reliability and performance through overclocking. The GPU is powered by a single 6-Pin connector and has a rated TDP of 140W, almost 10W lower than the GTX 660 Ti.
Specifications wise, the ASUS GeForce GTX 660 DirectCU II features 960 Cores, 24 ROPs, 112 TMUs, 2540 Million transistors and a 2 GB GDDR5 memory. Clocks are maintained at 980 MHz core and 1033 MHz Boost frequency while memory clock is configured at 6 GHz (6008 MHz) Effective speed along a 192-bit bus interface.
|Radeon HD 6970||Radeon HD 7870||Radeon HD 7970||GeForce GTX 560 Ti||GeForce GTX 660||GeForce GTX
|Core Clock (MHz)||880||1000||925||950||980||772||1006|
|Boost clock (Mhz)||–||–||–||–||1033||–||1056|
|Memory Clock (MHz)||5500||4800||5500||6008||6008||4008||6008|
Time to look at the GPU itself!
Unboxing the Package
The ASUS GeForce GTX 660 DirectCU II ships inside a rectangular box with the ‘GeForce GTX 660’ label at its right corner, DirectCU II label at the left side and highlights features such as 2 GB memory, DIGI+ VRM, GPU Tweak, etc. Three claws in red color are embedded on the box illustrating the design theme of the DirectCU II cooler which add a nice touch.
Flip the box and you will find detailed information of the technologies powering the ASUS GTX 660 DCII such as the DirectCU II Cooler, GPU Tweak and DIGI+ VRM. A label on the top says ‘Born Faster. Stay Cooler and Stable. The backside also mentions and points out the Input/Output points on the GeForce GTX 680 DirectCU II.
A second box is contained inside the original package which has a ‘ASUS’ monogram etched in the center. The GPU and accessories are held inside it.
Inside the package is the GPU itself, contained in a ridiculously annoying cardboard material which is a burden to open. The GPU is protected by a piece of plastic and held over a foam material. The packaging is worse compared to that of other GPUs. ASUS did a pretty well job packaging their GTX 680 DirectCU II, i don’t know why they cheaped out here.
The accessories themselves are a let down, a huge let down as there’s no accessory at all except a DVI to VGA connector shipped in a separate box which is almost the same length as the GPU itself. Aside from that, A CD Manual is located underneath the absurd packaging. The reason i mentioned the packaging so wildly is that given the space ASUS could have done better provided the space they had, look at Noctua as an example. They can fit a cooler as gigantic as the NH-D14 along with its fans in a Box fairly equivalent to what ASUS had.
Well, this is the unboxing bit covered. Let’s move onwards and hope that the card itself gives us a better impression than its packaging.
A Look at the GTX 660 DirectCU II
Out of box, the first thing to notice of the ASUS GeForce GTX 660 is its DirectCU II cooler. The DirectCU II label is etched in the left corner of the card and we see the claw line (previously noted on the box) running through the center of the card. There are two 100mm noise dampening fans which provide air to the central parts of the GPU.
The backside of the GPU has four memory units, rest of the four are located at the front of the PCB. We can see that most of the electrical components are concentrated beneath the GK106 GPU.
We can see heatpipes coming out from sides of the cooler shroud. The GPU takes a total of two expansion slot space so it can easily fit inside PC cases. The PCI-Express slot connector is protected by a slot cover.
On the opposite side, we can see a large metallic bar holding the GPU and PCB in place which prevents the card from bending due to added weight of DirectCU II cooler. Three massive heatpipes come out through the middle of the shroud. Aside them is a single SLI connector that allows upto 2-Way SLI. On the far end, we can spot a 6-Pin PCI-e connector.
Display options on ASUS GeForce GTX 660 DirectCU II include Dual Link DVI, HDMI and a full length display port. This allows Single-GPU 3D Vision surround gaming setups. There’s a small exhaust vent on the upper slot through which is used to dissipate heat out of the GPU shroud.
A Much Closer Look at the GTX 660 DirectCU II
We take an even closer look at the ASUS GeForce GTX 660 DirectCU II to see what’s kept on and under the GPUs hood.
First of all we would like to mention the cooler again. DirectCU II cooling solution on the ASUS GTX 660 uses three heatpipes bend to form an ‘S’ shape. These three massive heatpipes span the entire length of the GPU through an aluminum fin array heatsink. At the center of the GPU, these heatpipes make direct contact with GK106 core dissipating heat to the aluminum fin array and cooled off by the 100mm PWM fans.
On a closer look, we noticed that ASUS has made use of memory chip by Samsung whereas the reference model come with Hynix built memory chips. There are a total of 8 memory chips on board the GTX 660 running at 6 GHz frequency.
We can spot the MOSFETs and VRMs lying under the GPU shroud. The ASUS GTX 660 PCB is well built and managed hence resulting in lots of spare room on the PCB. ASUS can’t make use of the extra space but lesser electrical components near the core components means lesser heat produced.
You can view close up shots of the ASUS GeForce GTX 660 in the thumbnails below (Click Thumbnail to Enlarge picture).
|Processor||Intel Core i5-3570K @ 4.5 GHz|
|Motherboard:||ASRock Z77 Extreme6|
|Power Supply:||Xigmatek NRP-MC1002 1000 Watt|
|Hard Disk:||Seagate Barracuda 500GB 7200.12
Kingston HyperX 3K 90GB
|Memory:||2 x 4096 MB G.Skill ARES 2133 MHz DDR3|
|Case:||Cooler Master HAF 932|
|Video Cards:||ASUS GTX 680
ASUS GTX 660
ASUS GTX 580
MSI GTX 560 Ti
MSI HD 7970
MSI HD 7870
MSI HD 6970
|Video Drivers:||NVIDIA ForceWare 310.90
AMD Catalyst 12.11
|OS:||Windows 7 Ultimate 64-bit|
- All games were tested on 1920×1080 and 2560×1600 resolutions.
- Games with PhysX were benchmarked with the setting either kept on Low or Off for fair comparison.
Benchmark – Aliens vs Predators
Rebellion Studios bring back the action to their Alien and the Predators franchise with the launch of 2010’s Alien vs Predators. The PC version of the title was one of the first games to feature DirectX 11 and tessellation.
Benchmark – Batman: Arkham City
The second title in the Batman: Arkham series has also been developed by Rocksteady Studios. Batman: Arkham City takes place in (isn’t it obvious by the name?) Arkham City which is infested with all the super-villains and their minions which Batman has previously met past his journey.
The game was released on PC in November 2011 and runs on the latest Unreal Engine 3 which features rich DirectX 11 detail, tessellation and PhysX support for NVIDIA cards.
Benchmark – Battlefield 3
Battlefield series is a name loyal to any PC gamer. Developed by DICE and published by EA, Battlefield 3 brings back the action, being one of the largest multiplayer launch titles of 2011. The game features both infantry and vehicular combat on some of the largest landscapes ever built in game with a total of 64 players pitted against each other.
Powering the game is DICE’s own Frostbite 2.0 engine. The successor to the original Frostbite engine that powered Battlefield: Bad Company 2. Battlefield 3 makes use of a highly detailed DirectX 11 engine, hardware accelerated tessellation and new lightning effects which deliver some of the most amazing visuals ever to be seen in a game.
Benchmark – Borderlands 2
Borderlands 2, developed by Gearbox Studios is one of the hottest titles released in 2012. The game runs on a highly modified version of Unreal Engine making use of PhysX and rich DirectX 9 detail.
During our test, we set the PhysX low for a fair comparison between the video cards.
Benchmark – Crysis
The first things to pop up on forums after Crysis’s launch was ‘Can my system run Crysis’. Almost every forum in the world, gaming or tech related was filled with the same question. This was not because of any bug but because of the technical and graphical achievement Crytek achieved with Crysis.
In 2007, Crytek released Crysis, A Sci-Fi FPS set on a jungle. The first few scenes were enough to determine the graphical leap the game took over others available at its time and still remains one of the most gorgeous looking titles to date. The game quickly became a benchmark to test modern PC’s performance. Crysis is powered by CryEngine 2 which makes use of a highly modified DirectX 10 set with technologies such as Ambient Occlusion and Parallax mapping detailing the rich Jungle in Crysis.
Benchmark – Crysis 2
Crysis 2 is the second title to be released by Crytek under their Crysis Franchise. The game is set in New York and revolves in the footsteps of Alcatraz who has to take out the Ceph and Cell along his path.
The game makes use of CryEngine 3 but at the time of its launch was shipped with DirectX 9 only. The game was later given DirectX 11 and High-Res textures through patches. We had our Crysis 2 with the latest DirectX 11 and High Res patch installed.
Benchmark – Dues EX: Human Revolution
Dues EX: Human Revolution developed by Edios Montreal brings us back in Adam Jensen’s footsteps and is set 25 years before the events of the original Dues EX. The game makes use of a modified version of the Crystal Engine which features DirectX 11 capabilities.
Benchmark – F1 2012
F1 2012 bring back formula racing with an actual representation of teams, drivers and cars. The game is developed on the Ego 2.0 engine by Codemasters which makes use of DirectX 11 feature set.
Benchmark – Far Cry 3
Developed by Ubisoft Montreal, Far Cry 3 is one of 2012’s hit titles which makes us take the role of Jason Brody, a tourist stranded on a tropical jungle along with his friends which is filled with pirates and a mad man known by the name of ‘Vaas’.
The game runs on Dunia Engine 2 and features DirectX 11 effects along with making use of Havok Physics effects. The game is one of the most graphically intensive titles released.
Benchmark – Hitman Absolution
Hitman Absolution is the fifth entry to Agent 47’s Hitman franchise. Developed by IO Interactive and published by Square Enix, the game revolves around 47 once again, betrayed by his former handler Diana in order to protect Victoria, a teen girl. Mystery solves about the girl as the game progress.
The game makes use of a highly improved Glacier 2 engine making use of DirectX 11 effects, Tessellation, Global Illumination and Depth of Field. Hitman Absolution is also one of the most demanding and visually impressive titles to be released in 2012.
Benchmark – Metro 2033
Metro 2033 is a post-apocalyptic FPS set under the streets of Moscow, Russia. Yes, the game is set within the Metro system to be exact which has become the last refuge to humans since the world above them is now infected with various creatures and rouge human factions.
The game uses rich DirectX 11 tessellation and lightning effects along with high quality textures. The game is on par with Crysis 1 being the most hardware demanding titles ever released.
Benchmark – Stalker: Call of Pripyat
Stalker: Call of Pripyat is developed by Ukrainian studios GSC Games World. The game takes place after the events of Stalker: Shadow of Chernobyl.
The game uses an updated X-Ray Engine 1.6 which features DirectX 11 effects such as Tessellation and dynamic shadows.
Benchmark – Sleeping Dogs
The last game in our list is Sleeping Dogs. The game gives us the role of Wei Shen, a Chinese-American undercover cop who has to infiltrate the Sun On Yee Triad organization. The game uses a powerful DX11 engine developed and tweaked by Square Enix that makes use of High-Resolution Textures.
3DMark 11 Performance Test
Futuremark’s 3DMark 11 has been around for a while, being a comprehensive benchmark application to evaluate overall GPU and PC performance. 3DMark 11 as the name suggests makes use of DirectX 11 API and makes use of every DX11 feature at hand such as Tessellation, Depth of Field, Dynamic Lightning, Parallax Occlusion mapping, etc.
- For testing we ran 3DMark 11 in Extreme and Performance presets.
Unigine Heaven 3.0 Performance Test
Based on the Unigine Engine, Unigine Heaven was one of the first demos to feature DirectX 11 effects. We use the latest Unigine Heaven 3.0 to evaluate DirectX 11 performance of GPUs with intensive features such as Tessellation. The demo also supports DirectX 9, DirectX 10 and OpenGL.
Temperature and Thermal Test
It should be noted that the ASUS GeForce DirectCU II makes use of a dual-slot non-reference cooler which provides much better cooling than the reference design.
According to ASUS, the DirectCU II delivers 20% better cooling and is vastly quieter compared to the reference GeForce GTX 660.
We tested the card under different environments – idle/load/load with OC
The ASUS GeForce GTX 660 with DirectCU II cooling stays under optimal temperature even while overclocked. This shows the cooling performance of the ASUS DirectCU II cooler which is remarkable.
Note – We tested load with Kombuster which is known as ‘Power viruses’ and can permanently damage hardware. Use the software at your own risk!
The overclocked settings we used were 1145 MHz on Core, 1198 MHz Boost and 1615 MHz memory clock. You can check out the overclocked results of the ASUS GeForce GTX 660 below.
Overclocking the GTX 660 DirectCU II
The maximum stable overclock we could achieve with the ASUS GeForce GTX 680 is shown below in the GPU-z:
The overclock was achieved with the default GPU Voltage and Fan settings. Please note that the ASUS GTX 660 DirectCU II makes use of a non-reference PCB design featuring better VRM and power phases. This allows better overclocking than reference models of GTX 660.
After overclocking, we evaluated the performance again in 3DMark 11. Following is the max stable clock we achieved with ASUS GeForce GTX 660 DirectCU II:
If you haven’t upgraded over your old DirectX 10 or DirectX 9 GPUs, then now’s the right time to upgrade. NVIDA’s GeForce GTX 660 at a price range around $200 brings the much successful Kepler architecture and brings it to consumers at a much affordable price range. NVIDIA’s Kepler architecture additionally supports the latest features for upcoming gaming titles such as DirectX 11 Tessellation, PhysX, 3D Vision Surround, TXAA and Adaptive V-Sync. The card is the weapon of choice for gamers if you are looking forward to play on HD resolution, e.g 1920 x 1080.
However as much great the card sounds, the GPUs its currently competing with price-wise aka the Radeon HD 7870 GHz happens to offer better performance over the GeForce GTX 660. Both cards trade blows with each other in most titles but the clear winner here is the HD 7870. While the GTX 660 can run games fairly at 1080P, the performance of the HD 7870 tends to outclass it due to better memory interface. Hence leaving the users to lower down AA/AAF options for better performance on GTX 660. The GeForce GTX 660 performance wise is placed between the Radeon HD 7850 and Radeon HD 7870. Its faster than HD 7850 but is $30 more expensive whereas the card is $10 cheaper than the HD 7870 GHz but overall performs slower.
Talking about the ASUS GeForce GTX 660 DirectCU II in specific, its been a great overall experience testing it. The cooler impressed us, the non-reference PCB and added DIGI+ VRM enables better overclocking and the price remains the same as the reference variants starting at $239.99. The only thing the GPU does gets a downvote from me was its packaging otherwise the ASUS GTX 660 is the card of choice for budget gamers, gaming on 1080P Resolution which the card handles perfectly.
In the end, it comes down to the average gamer whether they want added effects and features such as PhysX, TXAA, Adaptive V-Sync at the cost of performance from the GTX 660 or better performance without exclusive features on the Radeon HD 7870 GHz.