Details Leak on AMD's Sea Islands HD 8900 Series Graphics Cards

Subject: Graphics Cards | September 21, 2012 - 02:55 PM | Tim Verry
Tagged: tenerife, Sea Islands, radeon, GCN, amd, 8970

(Updated to add additional information on the 8900 series rumors – mainly on Radeon 8950.)

Earlier this week, we reported on rumors of two upcoming mid-range AMD 8800 series graphics cards based on the Sea Islands architecture. As mentioned previously, Sea Islands is the successor to the Southern Islands architecture used on the 7000 series. It features an improved Graphics Core Next GPU processor architecture based on TSMC's 28nm process. With that said, the chip will draw less power and be faster on GPGPU workloads thanks to several efficiency tweaks. Graphics cards based on Sea Islands will support DirectX 11, and will be available early next year.

While the 8850 and 8870 are based on the Oland GPU, this newly leaked Radeon HD 8970 will use the "Sea Islands" Tenerife GPU. New information seems to suggest that AMD will actually brand it the Venus XTX for 8970 cards and Venus XT/Pro for 8950 cards, though Oland would remain the chip name for 8800 series cards.

Tenerife offers up some impressive (but realistic) specifications, including 2,560 shaders, 160 texture units, 48 ROPs, and a relatively massive 384-bit memory bus. Also impressive is an alleged transistor count of 5.1 billion, which puts it a great deal above the Radeon 7970's 4.31 billion transistors. This rumored Tenerife/Venus XTX GPU (whichever AMD ends up calling it) will have a 250W TDP and will be use in the 8970 flagship graphics card. Venus XT/Pro will scale back the chip a bit by featuring 2,304 shaders, 144 texture units, and 32 ROPs. No word yet on what the TDP will be.

Both the HD 8970 and HD 8950 are said to support 3GB of GDDR5 memory running at 6GHz on a 384-bit bus, which works out such that the cards have approximately 322 GB/s of bandwidth! Further, the 16 additional ROP units in the Radeon HD 8970 will give it a nice performance boost over the 8950 and 8800 series, especially when running multiple monitors in Eyefinity configurations.

As far as specifications go, we do not yet know the die size of the GPU or what the GPU base (and boost) clockspeeds are beyond a source indicating the boost frequency of the 8970 will be above 1050 MHz. According to PC Perspective's GPU packrat reviewer Josh Walrath, the Tenerife GPU will have a much larger die than that of Oland. Because it will feature a sizeable increase in number of transistors, but still be based on a 28nm process, the die size will be somewhere between 380mm^2 and 420mm^2.

To put that in perspective, the 8850/8870 has a die size of 270mm^2, and the current generation predecessor (7950/7970) has a die size of only 365mm^2.

The following chart compares the various rumored Radeon 8000-series graphics cards to their previous generation counterparts.

*Tenerife die size is estimate only, actual die size is still unknown.

The AMD Radeon HD 8970 will be AMD's next generation single-GPU flagship graphics card, and it looks to offer up some respectable hardware. The Radeon HD 8950 should be a decent step up in performance versus the 7950, though it would have been nice to see the 8970's additional ROP units stick around in the 8950. Unfortunately we do not know what this Tenerife (aka Venus) GPU-based  graphics card will be priced at. For now, we will just have to be cautiously optimistic and wait a few months to see how much this card will cost. The wait should not be very long either, if rumors are true as they seem to indicate that the 8970 will enter manufacturing in late 2012 and launched in early (January/February) 2013.

Are you excited for AMD's next-generation flagship?

Fastest isn't necessarily best when it comes to GTX 660s

Subject: Graphics Cards | September 20, 2012 - 04:35 PM | Jeremy Hellstrom
Tagged: overclock, gtx 660, DirectCU II, asus

As promised [H]ard|OCP has spent some time overclocking the ASUS GTX 660 DirectCU II card and have come back with their results.  The highest GPU clock they managed was a reported 1170MHz Boost clock in GPU Tweak but which was 1215MHz in actual in-game performance.  While that was the high speed record it did not provide the best performance as the frequency often dipped much lower because of the heat produced, [H]'s sweet spot was actually a 1100MHz Boost clock, in-game a much more steady 1152MHz though it did still dip occasionally.  They also upped the memory, but again because of the heat produced by the overclock they could not raise voltage without negative consequences.  Check the whole review here.

"We put our new ASUS GeForce GTX 660 through the ringer of overclocking and make real world gaming comparisons. If you are thinking the new GTX 660 (GK106) GPU will be a good overclocker like its bigger brother GK104, you may be in for a surprise that puts the new GTX 660 in a new light."

Here are some more Graphics Card articles from around the web:

Graphics Cards

• ASUS GeForce GTX 660 Ti DirectCU II TOP @ [H]ard|OCP
• GeForce 9800 GT vs GeForce 660 GTX @ Guru of 3D
• Zotac GTX680 AMP Edition @ Bjorn3D
• EVGA GeForce GTX 660 SuperClocked Video Card Review @ Hardware Secrets
• Zotac GeForce GTX 660 with GK106 GPU @ @ X-bit Labs
• NVIDIA GeForce GTX 660 2GB Review @ Techgage
• Sparkle GTX650 OC Dragon Series @ Kitguru
• GeForce GTX 650 MSI Power edition @ Guru3D
• KFA GeForce GTX 650 EX OC 1 GB @ techPowerUp
• EVGA GeForce GTX 660 SC @ Guru of 3D
• MSI GeForce GTX 650 Power Edition OC 1 GB @ techPowerUp
• NVIDIA Chips Comparison Table @ Hardware Secrets
• NVIDIA FXAA Anti-Aliasing Performance @ Phoronix
• Seven Nvidia GeForce GTX 680 round-up: Super cards @ Hardware.info
• Desktop Graphics Card Comparison Guide @ TechARP
• Arctic Accelero Twin Turbo 6990 VGA Cooler Review @ eTeknix
• Sapphire Radeon HD 7750 1GB Low Profile Review @ Neoseeker
• ARCTIC Accelero Hybrid 7970 @ Hardwareoverclock
• PowerColor Devil 13 HD 7990 Review @ OCC
• Sapphire Radeon HD 7770 Flex Edition Review @ Hi Tech Legion
• XFX Radeon HD 7770 Black Edition Overclocked 1GB Graphics Card Review @ eTeknix
• Sapphire HD7770 GHZ FleX Edition @ Kitguru
• Sapphire Radeon Flex HD 7770 GHz Edition Video Card @ Pro-Clockers
• Sapphire Radeon HD 7950 3GB Vapor-X Review @ OCC
• HD 7990 Review; PowerColor’s Devil 13 @ Hardware Canucks
• MSI HD7850 Power Edition Video Card @ Bjorn3D

AMD Sea Islands HD 8850 and 8870 Specifications Leaked

Subject: Graphics Cards | September 18, 2012 - 06:34 PM | Tim Verry
Tagged: Sea Islands, oland, hd8870, hd8850, gpu, amd radeon, amd

AMD beat NVIDIA to the punch with its 7000-series “Southern Islands” graphics cards, and if the rumors hold true the company may well accomplish the same feat with its next generation architecture. Codenamed Sea Islands, the architecture of AMD’s 8800-series is set to (allegedly) debut around January 2013 time frame. Featuring DirectX 11, GPGPU and power efficiency improvements, 3.4 billion transistors on a 28nm process, and a rumored sub-$300 price, will the 8850 and 8870 win over enthusiasts?

AMD launched its Southern Island graphics cards with the Graphics Core Next (GCN) architecture and Pitcairn GPU in March of this year. Since then NVIDIA has moved into the market with the 660 and 660Ti, and budget gamers have lots of options. However, yet another budget gaming GPU from AMD will be coming in just a few months if certain sources' leaks prove correct. The 8850 and 8870 graphics cards are rumored to launch in January 2013 for under $300 and offer up some significant performance and efficiency improvements. Both the 8850 and 8870 GPUs are based on the Oland variant of AMD’s Sea Islands architecture. As a point of reference, AMD’s 7850 and 7870 are using the Pitcairn version of AMD’s Southern Islands architecture – thus Sea Islands is the overarching architecture and Oland is an actual chip based on it.

Sea Islands is essentially an improved and tweaked Graphics Core Next design. It will continue to utilize TSMC's 28 nm process, but will require less power than the 7000-series while being much faster. While the specifications for the top-end 8900-series is still up in the air, Videocardz is claiming sources in the know have supplied the following numbers for the mid-range 8850 and 8870 Oland cards. 

Videocardz put together a table comparing AMD's current and future GPU series.

The GPU die size has reportedly increased to 270mm^2 (squared) versus the 7850/7870’s 212mm^2 die. This increase is the result of AMD packing an additional 600 million transistors for a total of 3.4 billion. 3D Center further breaks the GPU down in stating that the 8870 will feature 1792 shader units, 112 texture manipulation units (TMU), 32 ROPs, and support a 256-bit memory interface. The 8850 graphics card will scale the Oland GPU down a bit further by featuring only 1536 shader units and 96 TMUs, but keeping the 32 ROPs and 256-bit interface.

For comparison, here’s a handy table comparing the 8850/8870 to the current-generation 7850/7870 (which we recently reviewed).

So while the memory bus and number of ROP units is staying the same, you are getting more shaders and texture units along with a boost to the overall memory bandwidth with the larger die size – sounds like an okay compromise to me!

AMD has managed to increase the clock speeds and GPGPU performance with Oland/Sea Islands as well. On the clockspeed front, the 8850 has a base boost GPU clockspeed of 925 MHz and 975 MHz respectively. Further, the 8870 has base/boost clocks of 1050 MHz/1100 MHz. That is a nice improvement over the 7850’s 860 MHz clockspeed, and 7870’s 1000 MHz clockspeed. AMD is also adding its PowerTune with Boost functionality to the Oland-based graphics cards which is a welcome addition. The theoretical computational power of the graphics chips has been increased as well, by as much as 75% for single precision and 60% for double precision (7870 to 8870). The single precision performance has been increased to 2.99 TFLOPS on the 8850 (1.76 TFLOPS on the 7850), and 3.94 TFLOPS on the 8870 (7870 has 2.25 TFLOPS). The single precision numbers are relevant to gaming and general applications that consumers would run that are GPU accelerated. The figures are not really suited/representative of high performance computing (HPC) workloads where precision is important (think simulations and high-end mathematics), and that is where the double precision numbers come in. The 8800 series gets a nice boost in potential performance as well, topping out at 187.2 GFLOPS for the 8850 and 246 GFLOPS for the 8870. That is in comparison the 7850’s 110 GFLOPS and 7870’s 160 GFLOPS.

The sources also disclosed that while the 8850 would have the same TDP (thermal design power) rating as the 7850, the higher-end 8870 would actually see a decreased 160W TDP versus the previous generation’s 175W. Unfortunately, there were not any specific power draw numbers talked about, just that the cards were more power efficient, so it remains to be seen just how much (if at all) less power the GPUs will need. The sources put the 8870 at the same performance level as the NVIDIA GeForce GTX 680, which would mean that this will be an amazing mid-range card if true. Especially considering that the cards have a rumored price of $279 for the 8870 and $199 for the 8850. Granted, those prices are likely much lower than what we will actually see if AMD does indeed launch the cards in January as the company will not have competition from NVIDIA’s 700 series right away.

In some respects, the rumored specifications seem almost too good to be true, but I’m going to remain hopeful and am looking forward to not only seeing the mid-range Oland GPU coming out, but the unveiling of AMD’s top-end 8900 series (which should be amazing, based on the 8800-series rumors).

What do you think of the rumored 8850 and 8870 graphics cards from AMD? Will they be enough to temp even NVIDIA fans?

Live Borderlands 2 Launch Event with PC Perspective and NVIDIA!!

Subject: Editorial, Graphics Cards | September 17, 2012 - 02:23 PM | Ryan Shrout
Tagged: pcper, nvidia, live, giveaway, contest, borderlands 2

I hope your day is going to be free tomorrow - we have some big stuff planned!  In cooperation with NVIDIA, Gearbox and PC Perspective, we'll be hosting a multi-hour live streaming launch party for Borderlands 2!  We'll be going over some of the unique PC-exclusive features, showing off gameplay in the crazy co-op mode and we'll have some giveaways for viewers as well including a pair of Zotac GeForce GTX 660 Ti cards!

Tomorrow, Sept 18th, from 4pm ET until at least 8pm ET, staff from PC Perspective and NVIDIA will be using our PC Perspective Live! channel to discuss and show off the new "shoot and loot" title from Gearbox. 

Come join us to see Borderlands 2 in action, hang out with PC Perspective and NVIDIA reps and enter for a chance to win one of two Zotac GeForce GTX 660 Ti cards!

Be sure to set your calendars and join us for the Borderlands 2 launch live streaming celebration!!

• PC Perspective Live! channel - pcper.com/live
• Start time: 4pm ET / 1pm PT

Lucid Dynamix adjusts mobile gaming quality in real-time

Subject: Graphics Cards, Mobile | September 13, 2012 - 06:42 PM | Ryan Shrout
Tagged: lucid, dynamix, ultrabook

Lucid has a history of fast product development as a software company.  It wasn't too long ago that Lucidlogix was a fabless semiconductor company that made chips for motherboards to enabled multi-GPU solutions across card models and GPU vendors.  Since then we have seen them move to GPU virtualization tasks like enabling discrete and integrated GPUs to work seamlessly without user interaction on the same notebook. 

The Lucid MVP software is the most recent version of that track and it has been very well received, find its way onto most motherboard brands and recently the Origin gaming notebook line. 

While huddling in San Francisco during IDF, we stopped by Lucid's suite to see what new stuff they were cooking up.  One of the products was called Dynamix and it has the goal of adjusting the image quality of games in real time to help users hit minimal gaming experience levels.  Lucid isn't adjusting the settings on your games but rather is intercepting calls from the game to the graphics solution (integrated or discrete) and altering them slightly to adjust performance.

Above you'll see the beta user interface for Dynamix that allows the user to configure it and assign which titles it should operate on.  Two sliders, one for a frame rate and one for a somewhat subjective "quality" level can be moved in order to alter the algorithms Lucid has set in the place. 

When you set the minimum frame rate, that is the "threshold" with which you would like to make sure all of your games run at.  The default was 30 FPS when I played with it and left the quality slider where it started as well.  If you start a game that does NOT run at 30 FPS with the settings you have (or maybe it won't with any settings) Lucid's software will attempt to change some quality and rendering settings completely transparently to bring the frame rate up.

In our demo we saw Crysis 2 running on a Dell Ultrabook at 1366x768 and a reported frame rate of 9 from FRAPS.  Obviously a game at that frame rate is pretty much unplayable, so when you enable the Dynamix software via a hotkey it attempts to bring up the frame rate; not by adjusting settings in the game engine but rather by changing DX calls to the GPU itself.

Examples given were that Dynamix might change the color depth requested by the game, or it might lower the texture resolutions and anti-aliasing passes.  It gradually degrades image quality until it is close to reaching your desired minimum frame rate.  When I enabled it on Crysis 2, my frame rate went from 9 to 28 or so - a sizeable difference that made the game mostly playable.

It's not magic though - there are degradations in quality that are visible.

Here you can see a close up of the game running without Dynamix at work.  The quality is good but the frame rate was again at 9 FPS or so.

This image shows the game after enabling Dynamix, with a frame rate of 28 or so.  You can definitely see blurrier textures, less sharpness around the gun and the foliage quality has gone done some as well. 

So why is this even interesting?  There are several reasons.  First there are some games that may not have quality settings low enough to run on an Ultrabook with HD 2500 graphics; kind of like Crysis 2.  Lucid is able to change things that the developer might not have thought of (or might not have wanted) with its access to the graphics pipeline. 

Secondly, as the name implies, the software is dynamic.  If you already running a game OVER your minimum threshold then the software will not change anything.  But if you are running in an indoor area at 40 FPS and then drop to 20 FPS when you go outdoors, the software will kick in and attempt to adjust quality to get you back up to the 30 FPS mark. 

Finally, the UI remains untouched - the informational points that were part of the game's interface were untouched so you don't have to worry about blury text or anything like that.  Lucid's capability to know about the back end of the 3D engines allows them to tweak things like this pretty easily.

Lucid says the goal is to make games that would otherwise be unplayable on a system, playable for consumers.  Without a doubt the target is Sandy Bridge and Ivy Bridge notebooks and the somewhat limited performance of the HD 2500 graphics system.  While this could also be applied to discrete graphics system from AMD and NVIDIA, I don't see that being necessary. 

Currently the software works with DX9 and DX10 games though they are still working to get DX11 covered completely.  And while the software worked find our demo, we only tried out one game on one notebook - there is still a lot of proving that Lucid needs to do for us to buy in completely.  If Lucid's bragging was anything to judge by though you should see Dynamix in quite a few major notebook brands later this year. 

What do YOU think?  Is this a technology you are interested in and do you see a place for it?

AMD's Radeon HD 7000 Series Graphics Cards Reportedly Receiving Price Cuts Soon (Update: AMD denies further price cuts)

Subject: Graphics Cards | September 13, 2012 - 05:25 PM | Tim Verry
Tagged: Radeon HD 7000, price cuts, pitcairn, HD7000, gpu, amd

Update: AMD has stated that there will not be any price cuts.

NVIDIA launched two budget Kepler-based graphics cards today, and the sub-$250 GPUs are competitively priced. The GTX 650 is a card with an MSRP of $109 and is matched against the Radeon 7750 (which retails for around $110 depending on manufacturer). Further, the $229 GTX 660 is pitted against the Radeon 7850 – an approximately $220 card (some manufacturers beat that price, others are priced higher).

The AMD Radeon HD 7850 Graphics Card from our review.

And while you can find these AMD graphics cards for slightly less than the NVIDIA competition, the green team GPU is a faster card in most games (especially at 1080p). In an attempt to sway gamers towards the AMD choice, the company is preparing to cut prices on the entire 7000-series line – including the 7750 and 7850. These are cuts on the, erm, arleady-cut prices announced last month.

The Price cuts are as follows:

These prices are almost certainly for reference designs, and you can naturally expect to pay for any factory overclocked model. What these price cuts mean, though is that the base versions are now cheaper to get ahold of, which is a good thing (for gamers, not so much for AMD heh).

When specifically talking about the price cuts as a response to budget Kepler cards, both the 7750 and 7850 can be had for anywhere between $5 and $20 cheaper in general. That’s is ~$20 extra dollars that you could devote to more RAM or put you over the edge into getting a better quality PSU. It definitely makes the decision to go AMD or NVIDIA a bit more difficult (but in an exciting/good way).

This is not the first time that AMD has slashed prices on its 7000 series graphics cards and now that it has competition on all fronts, it will be interesting to see how all the prices finally shake out to be. Interestingly, Softpedia seems to have posted the price cut information on Tuesday (two days before Kepler) but states that the cuts will not go into effect until next week – though Newegg seems to have taken some initiative of its own by pricing certain cards at the new prices already. This may have technically been more of a pre-emptive move than a reactionary one, but either way the budget gaming section of the market just got exciting again!

Do the impending price cuts have you reconsidering your budget GPU choice, or are you set on the new Kepler hardware?

ASUS Launches the GeForce GTX 660 DirectCU II Lineup

Subject: Graphics Cards | September 13, 2012 - 05:09 PM | Jeremy Hellstrom
Tagged: nvidia, msi, kepler, gtx 660, gk106, geforce, evga, factory overclocked

As those of you who have already read the post below this one know, ASUS decided to create a DirectCU II model for their GTX 660, with the famous heatpipe bearing heatsink.  They have overclocked the GPU already and the card comes with tools to allow you to push it even further if you take the time to get to know your card and what it can manage.  Check the full press release below.

Fremont, CA (September 13, 2012) - ASUS is excited to release the ASUS GeForce GTX 660 DirectCU II series featuring the Standard, OC and TOP editions. Utilizing the latest 28nm NVIDIA Kepler graphics architecture, the OC and TOP cards deliver a factory-overclock while all three cards feature ASUS exclusive DirectCU thermal design and GPU Tweak tuning software to deliver a quieter, cooler, faster, and more immersive gameplay experience. The ASUS GeForce GTX 660 DirectCU II series set a new benchmark for exceptional performance and power efficiency in a highly affordable graphics card. The ASUS GeForce GTX 660 DirectCU II is perfect for gamers looking to upgrade from last-generation graphics technology while retaining ASUS’ class-leading cooling and acoustic performance.

Superior Design and Software for the Best Gaming Experience ASUS equips the GeForce GTX 660 DirectCU II series with 2GB of GDDR5 memory clocked up to 6108MHz. The TOP edition features a blistering GPU core boost clock of 1137MHz, 104MHz faster than reference designs while the OC edition arrives with a factory-set GPU core boost speed of 1085MHz. Exclusive ASUS DIGI+ VRM digital power delivery and user-friendly GPU Tweak tuning software allows all cards to easily overclock beyond factory-set speeds offering enhanced performance in your favorite game or compute intensive application.

The ASUS GeForce GTX 660 DirectCU II series feature exclusive DirectCU technology. The custom designed cooler uses direct contact copper heatpipes for faster heat transduction and up to 20% lower normal operating temperatures than reference designs. The optimized fans are able operate at lower speeds providing a much quieter gaming or computing environment. For enhanced stability, energy efficiency, and overclocking margins the cards feature DIGI+ VRM digital power deliver plus a class-leading six-phase Super Alloy Power design for the capacitors, chokes, and MOSFETs meant to extend product lifespan and durability while operating noise-free even under heavy workloads.

ASUS once again includes the award winning GPU Tweak tuning suite in the box. Overclocking-inclined enthusiasts or gamers can boost clock speeds, set power targets, and configure fan operating parameters and policies; all this and more is accessible in the user-friendly interface. GPU Tweak offers built-in safe guards to ensure all modifications are safe, maintaining optimal stability and card reliability.

New Kepler on the Block, meet the vanilla GTX 660

Subject: Graphics Cards | September 13, 2012 - 04:49 PM | Jeremy Hellstrom
Tagged: nvidia, msi, kepler, gtx 660, gk106, geforce, evga

The non-Ti version of the GTX 660 has arrived on test benches and retailers, with even the heavily overclocked cards being available at $230, like EVGA's Superclocked model or MSI's OC'd card once you count the MIR.  That price places it right in between the HD 7850 and 7870, and ~$70 less than the GTX 660 Ti, while the performance is mostly comparable to a stock HD7870 though the OC versions can top the GTX660.

[H]ard|OCP received ASUS' version of the card, a DirectCU II based version with the distinctive heatpipes.  ASUS overclocked the card to a 1072MHz base clock and 1137MHz GPU Boost and [H] plans to see just how much further the frequencies can be pushed at a later date.  Their final word on this card for those looking to upgrade, for those of you with "a GTX 560 Ti, and even the GTX 570, the GTX 660 is an upgrade".

"NVIDIA is launching the new GeForce GTX 660 GPU, codenamed GK106. We have a retail ASUS GeForce GTX 660 DirectCU II custom video card fully evaluated against a plethora of competition at this price point. This brand new GPU aims for a price point just under the GTX 660 Ti but still promises to deliver exceptional 1080p gaming with AA."

Here are some more Graphics Card articles from around the web:

Graphics Cards

• Nvidia's GeForce GTX 660 @ The Tech Report
• ASUS GTX 660 Direct CU II TOP Review @ OCC
• NVIDIA GeForce GTX 660 Launch Review @ Neoseeker
• EVGA GeForce GTX 660 SC (SuperClocked) 2GB @ Bjorn3D
• Nvidia GeForce GTX 660 @ Hardware.info
• NVIDIA Geforce GTX 660 Reviews @Hi Tech Legion
• The NVIDIA GeForce GTX 660 Review: GK106 Fills Out The Kepler Family @ AnandTech
• SI GEFORCE GTX 660 Twin Frozr 2GB OC @ Tweaktown
• Gigabyte GeForce GTX 660 @ Legion Hardware
• Gigabyte GTX 660 Overclock 2GB Graphics Card Review @ eTeknix
• EVGA GeForce GTX 660 2GB SuperClocked @ Benchmark Reviews
• MSI GTX 660 OC Edition Twin Frozr @ Kitguru
• Nvidia GeForce GTX 660 @ Techspot
• Gigabyte GTX 660 OC Video Card Review @ Ninjalane
• MSI GTX 660 Twin Frozr 2GB OC @ LanOC Reviews
• NVIDIA GeForce GTX 660 Overclocked Graphics Card Review (EVGA/ZOTAC)@ HardwareHeaven
• EVGA GTX 660 Superclocked 2Gb @ LanOC Reviews
• NVIDIA GeForce GTX 660 Review @ Hardware Canucks
• ASUS, KFA2 and MSI GeForce GTX 660 reviews with 2-way SLI @ Guru of 3D
• MSI GeForce GTX 660 Twin Frozr 2 GB @ techPowerUp
• ZOTAC GeForce GTX 660 2 GB @ techPowerUp
• Gigabyte GTX 660 Windforce OC 2 GB @ techPowerUp
• ASUS GeForce GTX 660 Direct Cu II 2 GB @ techPowerUp
• NVIDIA GeForce GTX 660 Video Card Review w/ MSI and EVGA @ Legit Reviews

   

• Six GeForce GTX 660 Ti graphics cards: ASUS, EVGA, Gigabyte, MSI and Zotac @ Hardware.info
• Gigabyte GTX 660 Ti OC Windforce @ Kitguru
• AFOX Radeon HD 7850 (Single Slot), MSI R7870 Hawk Graphics Cards @ iXBT Labs
• Inno3D GTX 680 iChill Black Series Accelero Hybrid 4GB Overclocked @ Tweaktown
• MSI Geforce GTX 670 Power Edition @ Rbmods
• i3DSpeed, August 2012 @ iXBT Labs
• Arctic Accelero Xtreme 7970 VGA Cooler Review @ eTeknix
• Sapphire Radeon HD 7970 Vapor-X OC 6GB Graphics Card Review @ eTeknix
• Sapphire FleX HD 7770 GHz Edition @ LanOC Reviews