... and here's Newegg with a GTX 680 leak

Subject: General Tech, Graphics Cards | March 21, 2012 - 09:51 PM |
Tagged: pelly wants revenge, nvidia, leak, gtx 680, fermi, 28nm

Not to be outdone by NCIX, NewEgg also managed to jump the gun on the GTX 680 earlier today. The screengrab that was sent tp Bright Side of News shows their pricing of the soon to be released GTX 680 with models ranging from $500 to $535.  The specs are there for all to see, a GPU running at 1.006GHz, Shader clock of 2.012GHz, effective memory of 6.008GHz and 1536 Stream Processors.  Contrast that with the last GTX 580 that Josh reviewed which had a 782 MHz core, 1.564GHz shader, memory at 4.008GHz and 512 SPs and you can see it is a big step up!

Oh_Newegg.jpg

If you visit NewEgg now you will be greeted with a different result, a page describing the GTX 680's various features and a Buy Now button which unfortunately doesn't work at this moment.  That is a situtation which obviously cannot last as NewEgg would not have put it up.  Of course the realization that you can pick up a pair of GTX 570's for the same price might just mean some recalculations will be in order once we see the performance of the actual card.

2012-03-21_2137.png

Anyone want a GTX580 for $360? (Counting MIR)

Subject: Graphics Cards | March 21, 2012 - 05:12 PM |
Tagged:

You can get a Galaxy GeForce GTX 580 from NewEgg at this very moment for the measly sum of $390, $360 after the MIR and get it shipped to you for free!  If you prefer an overclocked card the the EVGA SuperClocked GTX580 will run you a bit more at $440, with a variety of other models available between those two benchmarks.

GTX580deal.jpg

That reduction of over $100 makes the price to performance ratio change significantly as now AMD's HD 7970 costs $150 more than the GTX 580; however the performance difference between the two cards is only about 10%.  While a difference of $50 did represent about a 10% price difference, after these cuts that is no longer true.  NVIDIA has changed the high end graphics card market already, without having released the GTX 680 yet.  Once that hits the market in the not too distant future, AMD is going to have to rethink their pricing in order to stay competitive.  The mid-ranged HD 7870 is within $40 of the current price of the GTX 580 which makes those two cards direct competitors, which was probably not AMD's intention, though the performance numbers are close enough to make it a contest.

Source:

MSI's Lightning series strikes as many times as it likes

Subject: Graphics Cards | March 20, 2012 - 06:53 PM |
Tagged:

MSI's Lightning Series of graphics cards are among Josh's favourites and once he manages to claw enough time together to wrap up his testing you shall see his impressions of the latest member of that laudable series.  In the meantime, [H]ard|OCP have put up their review of the MSI R7970 Lightning, clocked at an impressive 1070MHz which ensures you will not see a GHz Edition label on the card, though from [H]'s testing you might not get much more out of the card.  This card is also the first chance we have to see the Twin Frozr IV cooling system in action and it kept the GPU cooler than the stock model even when the fully overclocked card was set to full load and did it quietly as well.  You will pay a bit of a premium over stock models but you also get a card with a lot more to offer.

lightning7970.jpg

"MSI is launching its new flagship Radeon HD 7970 based Lightning series video card this week. This highly customized video card takes the Radeon HD 7970 and adds all sorts of features. Will the extra customizations like "GPU Reactor" add up to a stellar overclock? We'll put this video card to the test and find out."

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

Graphics Cards

 

Source: [H]ard|OCP

Announcing the MSI R7970 Lightning Graphics Card with Unlocked Digital Power Architecture

Subject: Graphics Cards | March 16, 2012 - 02:29 PM |
Tagged: MSI R7970 Lightning, msi, factory overclocked

MSI is taking full advantage of AMD's permission to wander away from the reference design with their brand new 7970 Lightning Edition.  Instead of putting a stable overclock on it and selling it at a mark up, they've completely redesigned the power architecture as well as replacing the cooler with one that is quieter and more effective.  From the proprietary "GPU Reactor" which increases the amount of current available for your GPU to a significantly higher maximum setting on Power Tune, this card is for the serious overclocker who is experienced with over-volting.

msi_lightning7970.png

Leading international graphics card and mainboard maker MSI today announced the release of the MSI R7970 Lightning, the new heir to the throne of Lightning graphics cards. Equipped with AMD's 28 nm Radeon HD 7970 GPU, the MSI R7970 Lightning features an all-new Unlocked Digital Power Architecture that incorporates an Unlocked BIOS, Digital PWM Controller, and Enhanced Power Design to boost overclocking potential to new heights and make overclocking easier than ever. In an industry first, the proprietary "GPU Reactor" power supply module reduces power supply noise and also boosts overclocking stability as well. To keep this beast cool, the MSI R7970 Lightning utilizes the latest Twin Frozr IV Thermal Design equipped with Dust Removal Technology. The dual 10 cm fans with Propeller Blade Technology generate massive airflow for fast heat dissipation while remaining whisper silent. The two form-in-one heat sinks improve cooling for memory and the power supply module as well ensure structural integrity. The R7970 Lightning uses Military Class III components which have passed rigorous third-party testing to meet MIL-STD-810G standards, guaranteeing the card's stability and reliability under actual use conditions. Moreover, the "3X3 OC Kits" are designed to simplify overclocking, which makes it easier than ever for enthusiasts to fine-tune the performance of their graphics cards. For both professional users and gaming enthusiasts alike, the R7970 Lightning's ability to simultaneously run 6 displays makes it the natural choice!

Unlocked Digital Power Provides Record-Breaking Potential
The R7970 Lightning boasts an all-new Unlocked Digital Power architecture that provides record breaking potential. The key components involved include the Unlocked BIOS, digital PWM chipset, and an improved power supply design. Unlocked BIOS removes CCC overclocking limits, Power Tune limit is increased by 180%, and OCP limits are relaxed to completely unleash the graphics card's overclocking potential. The digital power supply signal provides voltage signals that are more stable and accurate than conventional analog designs, meaning the voltage can be adjusted more quickly and precisely during overclocking. The improved power supply design provides double the power of the reference board and consists of 17 power supply parameters, dual 8-pin power supply connectors, and the Lightning Power Layer (LPL) design. For true overclocking enthusiasts, the R7970 Lightning with Unlocked Digital Power is simply a dream come true!

GPU Reactor for the Ultimate Power Core
The MSI R7970 Lightning implements the innovative "GPU Reactor" power supply module which, when installed on the back of the GPU, increases current volume by 88%, reduces power supply noise by 13%, and improves overall overclocking stability. MSI GPU Reactor is easy to install and has built in safety features that make it easy even for ordinary users to install and remove.

Extreme Cooling Design for Better Cooling and Structural Strength
The MSI R7970 Lightning incorporates the next-generation Twin Frozr IV Thermal Design. The striking design of the new Twin Frozr IV comes from the two large 10cm PWM fans with Propeller Blade Technology that cool the advanced cooling body of the Twin Frozr IV. Under the aluminum Twin Frozr IV body, you can find a high density fin grid array that provides heat dissipating area that is fed by heat-pipes featuring MSI's SuperPipe technology. MSI has also incorporated its exclusive Dust Removal Technology. Fans are running in reverse for 30 seconds after booting to remove dust from the heat sinks and keep the graphics card's cooling performance running at optimum levels. The R7970 Lightning also boasts two form-in-one heat sinks. One heat sink is located on the front of the graphics card to cool the memory and power supply modules, while the second heat sink on the back of the card helps to protect and reinforce the card structure. This extreme cooling design provides the R7970 Lightning with the best cooling performance and the most reliable structure.

Premium Materials and User-friendly Overclocking Design
MSI has always led the industry thanks to its unyielding commitment to product stability and quality and made sure that the R7970 Lightning was equipped with Military Class III components certified to MIL-STD-810G military standards in seven different categories by a third-party laboratory. Be it tantalum core Hi-c CAP around the graphics card, the CopperMOS cooling design, the form-in-one Golden SSC, or as the card's moisture/rust-proof Dark Solid CAP, all work together to provide the MSI R7970 Lightning with the best possible stability.

For overclocking enthusiasts, MSI has developed the 3X3 OC Kits: V-Check Points enable GPU, Memory and VDDCI voltage to be monitored while Triple Overvoltage and Triple Temperature Sensor enable overclockers to quickly fine-tune and track the performance of their graphics card using enthusiasts favorite Afterburner overclocking software. The 4 Mini DisplayPorts and 2 DVI ports on the R7970 Lightning enable AMD Eyefinity technology to drive 6 screen output with just one card, providing just the kind of performance industry professionals and gaming enthusiasts need.

Source: MSI

A possible GTX 680 specs leak?

Subject: General Tech, Graphics Cards | March 14, 2012 - 05:29 PM |
Tagged: rumour, nvidia, leak, gtx 680

Below you can see a screen grab from PConline which purports to show the specifications of the GTX 680. While the specs are well within reason, without any way to verify this leak, or to translate the Chinese characters it is hard to have these specs confirmed or denied as they stand.  Whether you should take the below with a good dose of NaCl is as of yet unknown but for now we can enjoy the speculation until NVIDIA finally releases the cards for review.

670leakage.png

Please feel free to add any speculations, doubts or other leaks in the comments below ... or even a decent translation would be great!  You can catch the Google Translation here, if you wish to torture your brain with exclusive exposure.

Source: PConline

Graphics Core Next versus The Penguin

Subject: Graphics Cards | March 13, 2012 - 05:41 PM |
Tagged: linux, GCN, southern islands, hd 7950

After a delay of several weeks AMD has finally released a hot fix for Linux to allow for the usage of their new generation of video cards but they've not provided updates that can be rolled into the Linux kernel DRM driver, the X.Org DDX driver, or the new Gallium3D driver.  However, since the new features seem to have been enabled with this hot fix, Phoronix picked up an XFX Radeon HD 7950 Black 3GB to test for performance on Ubuntu 12.04 LTS.  The good news is that they saw 40~50%+ faster performance than an HD6950 but unfortunately not at stock speeds, the driver did not fully recognize the card and would not let them set the GPU and memory speeds to their full defaults.

phor_GCN.jpg

"The Radeon HD 7900 series were announced at the end of 2011 and since then the Linux support status for this hardware has remained a big question. For the Radeon HD 7000 series "Southern Islands" GPU launch, they did not send over any hardware samples so Linux consumers have left to be confused over the state of the non-Windows support for AMD's hardware based on the "Graphics Core Next" architecture. Fortunately, here is finally an extensive look at the Radeon HD 7000 series on Linux with testing of a Radeon HD 7950."

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

Graphics Cards

 

Source:

GTX 680, Turbo Cores, and Cuda Cores!

Subject: Graphics Cards | March 8, 2012 - 06:59 PM |
Tagged: nvidia, kepler, gtx 680, GDC

It seems that there have been a few leaks on NVIDIA's first Kepler based product.  Techpowerup and Extreme Tech are both reporting on leaks that apparently came from Cebit and some of NVIDIA's partners.  We now have a much better idea what the GTX 680 is all about.

mark-rein-kepler-nvidia-gk104.jpg

Epic's Mark Rein is showing off his own GTX 680 which successfully ran their Samaritan Demo.  It is wrapped for his protection.  (Image courtesy of Extreme Tech)

The chip that powers the GTX 680 is the GK104, and it is oddly enough the more "midrange/enthusiast" offering.  It has a total of 1536 CUDA cores, runs at 703 MHz core and 1406 MHz hot clock, has a 256 bit memory bus pumping out 196 GB/sec, and has a new and interesting feature that is quite a bit like the Turbo core functionality we see from both AMD and Intel in their CPUs.  Apparently when a scene gets very complex, the chip is able to overclock itself up to 900 MHz core/1800 MHz hot clock.  It will stay there for either as long as the scene needs it, or the chip approaches its upper TDP limit.

These reports paint the GTX 680 as being about 10% faster than the HD 7970 in certain applications, but in others it is slower.  I figure that when reviews are finally released the two cards will have traded blows with each other over who has the fastest graphics card.  Let's call it a draw.

The GTX 680 should be unveiled in the next week or so, but initial reviews will not surface until later in the month.  Retail availability will be relegated until then, but with the issues that TSMC has had with their 28 nm process (it has been stopped since the middle of February) we have no idea how much product NVIDIA and its partners has.  Things could be scarce after the introduction for some time.

Source: NVIDIA

Alleged NVIDIA GK104 Kepler GTX 670 Ti Photo Leaked

Subject: Graphics Cards | March 8, 2012 - 03:41 PM |
Tagged: nvidia, kepler, graphics card, gpu, GK104, gaming, 28nm

GDC 2012 is upon us, and in addition to the Samaritan demo and some gaming goodness, we spotted a leaked image over at Legit Reviews that is allegedly a photo of a production NVIDIA GTX 670 Ti graphics card.

GTX670Ti.jpg

The cooler looks to cover the whole PCB and be of the blower design, funneling hot air of the of the front of the card and out of the case.  The connectors include two DVI, one HDMI, and one Display Port.  Rumors suggest that the latest NVIDIA cards will be capable of multi-display (>2) from a single card much like AMD cards have been doing for some time.

Not a whole lot is known about the upcoming GK104 "Kepler" GPUs with a good deal of certainty, but we have reported on a few leaks including that the cards will have 2 GB of GDDR5 RAM on a 256 bit memory bus, and that the cards may just be coming out in May. Due to Epic using a working Kepler GPU in their Samaritan demo, that launch date does not sound too far fetched either. On the performance front, there are conflicting rumors; some rumors state that the cards will blow AMD out of the water and other people swear the cards will not be as powerful as the rumors suggest. I suppose we'll find out soon though!

Are you still waiting for NVIDIA's Kepler GPUs or have you jumped on the latest Radeon series?

Intel in the Cloud with Ray-traces

Subject: General Tech, Graphics Cards, Processors, Mobile | March 8, 2012 - 04:02 AM |
Tagged: ray tracing, tablet, tablets, knight's ferry, Intel

Intel looks to bring ray-tracing from their Many Integrated Core (Intel MIC) architecture to your tablet… by remotely streaming from a server loaded with one or more Knight’s Ferry cards.

The anticipation of ray-tracing engulfed almost the entirety of 3D video gaming history. The reasonable support of ray-tracing is very seductive for games as it enables easier access to effects such as global illumination, reflections, and so forth. Ray-tracing is well deserved of its status as a buzzword.

intel-ray.jpg

Render yourself in what Knight’s Ferry delivered… with scaling linearly and ray-traced Wolfenstein

Screenshot from Intel Blogs.

Obviously Intel would love to make headway into the graphics market. In the past Intel has struggled to put forth an acceptable offering for graphics. It is my personal belief that Intel did not take graphics seriously when they were content selling cheap GPUs to be packed in with PCs. While the short term easy money flowed in, the industry slipped far enough ahead of them that they could not just easily pounce back into contention with a single huge R&D check.

Intel obviously cares about graphics now, and has been relentless at their research into the field. Their CPUs are far ahead of any competition in terms of serial performance -- and power consumption is getting plenty of attention itself.

Intel has long ago acknowledged the importance of massively parallel computing but was never quite able to bring products like Larabee against anything the companies they once ignored could retaliate with. This brings us back to ray-tracing: what is the ultimate advantage of ray-tracing?

 

Ray-tracing is a dead simple algorithm.

 

A ray-trace renderer is programmed very simply and elegantly. Effects are often added directly and without much approximation necessary. No hacking around is required in the numerous caveats within graphics APIs in order to get a functional render on screen. If you can keep throwing enough coal on the fire, it will burn without much effort -- so to speak. Intel just needs to put a fast enough processor behind it, and away they go.

Throughout the article, Daniel Pohl has in fact discussed numerous enhancements that they have made to their ray-tracing engine to improve performance. One of the most interesting improvements is their approach to antialiasing. If the rays from two neighboring pixels strike different meshes or strike the same mesh at the point of a sharp change in direction, denoted by color, between pixels then they are flagged for supersampling. The combination of that shortcut with MLAA will also be explored by Intel at some point.

intel-41914.png

A little behind-the-scenes trickery...

Screenshot from Intel Blogs.

Intel claims that they were able to achieve 20-30 FPS at 1024x600 resolutions streaming from a server with a single Knight’s Ferry card installed to an Intel Atom-based tablet. They were able to scale to within a couple percent of theoretical 8x performance with 8 Knight’s Ferry cards installed.

I very much dislike trusting my content to online streaming services as I am an art nut. I value the preservation of content which just is not possible if you are only able to access it through some remote third party -- can you guess my stance on DRM? That aside, I understand that Intel and others will regularly find ways to push content to where there just should not be enough computational horsepower to accept it.

Ray-tracing might be Intel’s attempt to circumvent all of the years of research that they ignored with conventional real-time rendering technologies. Either way, gaming engines are going the way of simpler rendering algorithms as GPUs become more generalized and less reliant on fixed-function hardware assigned to some arbitrary DirectX or OpenGL specification.

Intel just hopes that they can have a compelling product at that destination whenever the rest of the industry arrives.

Source: Intel Blog

MSI Shows of Next Generation Twin Frozr IV Cards at Cebit

Subject: Graphics Cards | March 6, 2012 - 08:55 PM |
Tagged: Twin Frozr, R7970, R7870, msi, Lightning, hd 7950, hd 7850, HD 77750, hd 7770, hawk

The Romanian site Lab 501 was able to snap some shots and get some information about the latest generation of custom built graphics products from MSI.  We had actually talked to Alex Chang of MSI about what Twin Frozr IV would bring to the table, but today we actually get to see the (nearly) finished parts.

lightning_1.JPG

It looks as if MSI is changing around their color scheme, but the heatsink remains as big as the previous generation's.  (image courtesy of Lab 501)

The products shown were of course only the AMD based parts, as the NVIDIA Kepler products are still under wraps (but apparently should see the light of day later this month).  MSI is giving the full Twin Frozr IV treatment to every HD 7750 and above part.  The HD 7970 is getting the Lightning edition with all the bells and whistles, while the HD 7870 is going under the Hawk brand.

We have few details about what all Twin Frozr IV includes, but it keeps the propeller blades and the anti-dust technology that we first saw in the N580GTX Lightning.  From the shots we have, it does not appear that they will be using the temperature sensitive fan units that actually change color when going above 45C.

lightning_2.JPG

They were able to take a good shot of the board without the heatsink, and it is just as jam packed as the previous Lightning products.  (image courtesy of Lab 501)

The Lightning will feature a total of 4 Display Ports and 2 DVI ports, so it can support up to 6 monitors at once.  This appears similar to what Asus did with the EAH6950 and EAH6970 cards that were recently reviewed here.  The Hawk will only feature 2 Display Ports, HDMI, and DVI-I.  The rest of the lineup looks like reference based cards with custom Twin Frozr IV coolers.

hawk_3.jpg

It is good to see MSI continues with the more affordable Hawk brand.  (image courtesy of Lab 501)

Of particular interest is the board design of the Lightning card.  It is simply jam packed with power regulation components and the new "Twin Form-in-One" bracing system which supports both sides of the PCB with metal plates to minimize warping, improve cooling, and funnel airflow.  Looking at the back of the card reveals the plate having a nice sized hole in it which would be perfect for another fan to cool all of the components on the back.  More digging has informed us that it is actually a removable "GPU Reactor Core".  More details should be available soon.

Source: MSI Computer

Radeon HD 7870 2GB vs HD 7850 2GB vs HD 5870 1GB Quick Look

Subject: Graphics Cards | March 6, 2012 - 05:42 PM |
Tagged: radeon, pitcairn, hd 7870, hd 7850, amd, 7870, 7850

After the launch of our Radeon HD 7870 and HD 7850 review this week, I got a couple of emails asking for another data point around the Radeon HD 5800 cards that many users might be looking to upgrade from.  Well, since everyone asked so nicely and I felt bad for not including it in the first place, I decided to quickly throw a HD 5870 1GB card on the test bed and run some 3DMark11 action.

gpuz.png

Using the same hardware test bed as the other graphics cards, we ran the HD 5870 1GB using the 12.2 pre-certified driver, the same we used on the rest of our non-7000 series Radeon cards.  Here are the results.

3dm11-p.png

3dm11-x.png

How does this compare to the new Pitcairn GPUs?

  • 3DMark11 Performance Preset
  • HD 5870 1GB: 4832
  • HD 7870 2GB: 6601 (+36%)
  • HD 7850 2GB: 5497 (+13%)
     
  • 3DMark11 Extreme Preset
  • HD 5870 1GB: 1649
  • HD 7870 2GB: 2058 (+25%)
  • HD 7850 2GB: 1645 (+0%)

It looks like with just this simple glance, the HD 7870 2GB card would be the only upgrade worth really stretching towards based on performance alone.  There are definitely going to be cases where the 2GB frame buffer will help over the 1GB included in most HD 5870/5850 cards including Eyefinity and titles like Battlefield 3, so even if you go with the HD 7850 card you should see some gains. 

Pitcairn is finally here, low on power and high on performance per dollar

Subject: Graphics Cards | March 5, 2012 - 12:40 PM |
Tagged: southern islands, radeon, pitcairn, hd 7870, hd 7850, amd, 7870, 7850

To give the end of the story away at the beginning, sometime around March 19th you should be able to find an HD 7870 for about $350 and an HD 7850 for around $250.   The HD 7870 not only costs less than the 6970 it consumes less power and can outperform it, making the HD 7870 the more attractive of the two cards.  [H]ard|OCP was less impressed with the HD7850 as it costs about $40 more than a GTX 560 Ti but only performs a small amount better.  It does consume a lot less power than the NVIDIA card though, which can be a big deal for some users and hints at possible overclocking potential. 

Ryan had a slightly better experience with the HD 7850, which might attract those who cannot justify spending over $300 on a graphics card but still want multi-monitor functionality.

H_7870.jpg

"AMD is introducing the performance mainstream Radeon HD 7870 and Radeon HD 7850 today. We'll look at performance compared to the competition and talk about pricing and explore value. If you are in the market for a video card between $249 and $349 these video cards will likely need to be on your short list."

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

Graphics Cards

 

Source: [H]ard|OCP

Feast your eyes on four overclocked HD7970s crushing benchmarks

Subject: Graphics Cards | February 28, 2012 - 02:28 PM |
Tagged: quad crossfire, hd7970, amd, overclocking

It would be quite the feat to find a case to contain the system below, with four HD7970s powered by two 1200W PSUs plus other assorted components, not to mention the heat this system will produce.  Not even the ASUS MARS 2 in SLI can keep up with this monstrosity and the scaling from a pair of HD7970s is rather impressive as in the past adding the third and fourth card did not lead to large gains.  The Core i7-3960X @ 4.8GHz simply can't keep up with the GPUs, implying that this system could actually be more impressive.  If you want to see $2200+ of GPUs in action then head to OC3D.

OMG.JPG

"In combination with ASUS we're rerunning our Quadfire HD7970 test with the benefit of overclocking. Roll up, roll up."

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

Graphics Cards

 

Source: Overclock3D

Sapphire overclocks the HD7950

Subject: Graphics Cards | February 20, 2012 - 02:48 PM |
Tagged: sapphire, hd 7950, hd 7950 OC, factory overclocked, cape verde, amd

There are a lot of custom Cape Verde boards to chose from, with varying clock speeds and custom coolers which is great for those who like something unique out of the box.  X-bit Labs received an overclocked HD7950 board from Sapphire which sports both a 100MHz overclock on the GPU and a custom low noise cooler.  The back of the card is fairly normal, with a dual-link DVI-I port, one HDMI 1.4a connector and two DisplayPort 1.2 ports available.  Overclocking potential on the card was impressive, with a final 1.15 volts allowing stable performance at 1100MHz GPU and 7360 MHz effective on the memory and a temperature of 74C at full load thanks to the cooler.  Even better is the fact that the cooler operates relatively quietly even at that high overclock.

XBT_04_sp795_fr_big.jpg

"Today we are going to review a graphics accelerator with phenomenally efficient cooling system with very low noise, high performance and superb overclocking potential, which even some Radeon HD 7970 graphics cards could wish for."

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

Graphics Cards

 

Source: X-bit Labs

Meet the new mid-range; AMD's HD7770 and HD7750

Subject: Graphics Cards | February 15, 2012 - 02:33 PM |
Tagged: xfx, southern islands, hd 7770, hd 7750, cape verde, amd, radeon, factory overclocked

The days of the HD 6870 are numbered as today we see the arrival of the new sub-$200 GPUs from AMD, the HD7770 and HD7750.  The stock HD 7770 run at 1GHz with 640 stream processors, 40 texture units and 16 ROPs and the 1GB of memory rides on a 128-bit bus at 4.5GHz.  The stock HD7750 has a slower core, running at 800MHz and a lower stream processor count of 512 as well as only 32 Texture units, with the memory subsystem unchanged from the HD7770.

Those who were disappointed by the lack of custom coolers and factory overclocks at the release of the HD 7970 will be happy to see the variety of HD7700 series cards.  For instance [H]ard|OCP reviewed the XFX R7770 Black Edition Super Overclocked which has a custom cooler, a 120MHz overclock on the core and a 300Mhz on the memory, effectively 5.2GHz.  [H] proved that there is more memory headroom available in this card, adding another 1.1GHz without needing to adjust the voltage.  For those who are willing to risk upping the power there might be even more speed possible from this card. 

You can also catch Ryan's review of the same card as well as an MSI version and a stock HD 7750.

H_7770.jpg

"Today marks the launch of AMD's Radeon HD 7700 series of GPUs in the sub-$200 bracket. We've got a retail XFX R7770 Black Edition Super Overclocked video card just itching to show us what it can do. Will this Radeon HD 7770 based video card hold up to the likes of the Radeon HD 6870 and GeForce GTX 560 Ti? You may be surprised."

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

Graphics Cards

 

Source: [H]ard|OCP

CTO Eric Demers to Leave AMD

Subject: Editorial, Graphics Cards | February 14, 2012 - 02:13 PM |
Tagged: demers, cto, amd

An interesting quarter for AMD continues as I learned today that AMD's Corporate Vice President and CTO of the Graphics Business Unit, Eric Demers, has decided to leave the company.  Having just had dinner with Eric and other AMD executives last week I am more than surprised about this sudden change since Demers' opinions of the roadmap for AMD were very positive.

amdfad02.jpg

First, here is the official statement from AMD:

"Eric Demers, AMD Corporate Vice President and CTO, Graphics Business Unit, has decided leave AMD to pursue other opportunities.

AMD Chief Technology Officer Mark Papermaster will assume interim responsibility for the Graphics Business Unit CTO role until a replacement is found.

AMD remains fully committed to our critical graphics IP development and discrete GPU products.  We have a tremendous depth of talent in our organization, a game plan that is resonating with our customers and our team, and we are continuing to bring graphics-performance-leading products to market.  We will attract the right technology leader for this role.

We thank Eric for his contributions to the business and wish him well in his future endeavors."

As is usually the case with these types of announcements, everyone is being very hush-hush about where Demers will finally land though I can confirm that it is neither Intel nor NVIDIA.  For those of you in the know about the industry and its current direction, that doesn't leave a lot of other options and we are quite positive he will find a spot that fits his expertise.  

ericdemers.jpg

Eric's background goes back quite a ways and includes stops at SGI, ArtX, Matrox, ATI and finally AMD.  He has been with ATI/AMD since April of 2000 (when David Orton first arrived from ATI) and rose to become the Chief Technology Officer of the graphics division as of mid-2009.  I have personally known Eric as one of the best sources of knowledge about GPUs and technology shifts and I will miss being able to question him on the design decisions being made in our industry.

For AMD, this move comes right after the drastic shift announced by AMD's new CEO Rory Read and new CTO Mark Papermaster to turn AMD into an SoC company.  I attended that same analyst day and came away from the event feeling upbeat about the direction of the company and the individuals at the helm, Demers being one of them.  The loss of Eric's talents will definitely be missed though with the rest of the team intact I don't think we'll see any immediate negative impacts from his departure.  Longer term though, we'll just have to see.  

The AMD rep I spoke with reiterated that this move had nothing to do with the newly hired executives and wasn't caused by any kind of internal disagreements.  Also, Demers did not express any kind of dissatisfaction with the direction of the company from a technological standpoint either.  While that is good to hear, you just don't leave a company after 12+ years without some reasons even if that reason is a better opportunity somewhere else.

Update on 2/14/2012 @ 11:53pm EST: According to this update from TheVerge.com, Demers may in fact end up at Qualcomm, the largest SoC vendor on the planet.  

We're hearing rumors that Demers will actually show up for work at Qualcomm, an interesting choice indeed: the company purchased AMD's mobile graphics division and Imageon media processor back in 2009. You now know it as Qualcomm Adreno, and it's the graphics solution in all Snapdragon-powered tablets and phones.

Gigabyte's non-standard HD 7970

Subject: Graphics Cards | February 14, 2012 - 01:54 PM |
Tagged: hd7970, gigabyte, factory overclocked

The most noticeable difference on Gigabyte's HD 7970 is the custom cooler, with three fans and a nice shroud, which should keep this card cool and quiet.  This is a good thing as the card sports a moderate overclock of 1000MHz on the core though the memory remains at stock speeds.  It doesn't need to stay at that speed however, [H]ard|OCP got the card up to 1305MHz for the core and 1605MHz for the memory, 6.42GHz effective.  That overclock is quite noticeable in games over both the GTX580 and the stock HD7970 though the performance comes at a price as the card pulls over 100W more than the stock card at full load.  For those drooling over the performance remember that these cards are intended to power multiple screens; [H] tested at 2560 x 1600 and if your setup is not of that resolution or higher you are tossing away money at a product you will not be using to its full potential.

H_giga7970.jpg

"GIGABYTE has a custom cooled and overclocked version of the Radeon HD 7970. We examine how well GIGABYTE's Windforce 3X cooling technology allows us to overclock this next generation video card. Find out how this GIGABYTE GV-R797OC-3GD monster compares to a GeForce GTX 580, a Radeon HD 6970, and reference HD 7970."

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

Graphics Cards

 

Source: [H]ard|OCP

AMD Verdetrol 1GHz Prescription Pills Arrive at PC Perspective

Subject: Editorial, General Tech, Graphics Cards | February 9, 2012 - 08:48 PM |
Tagged: amd, radeon, southern islands

Working from home comes with a host of stereotypes and assumptions that the rest of world places on people like myself.  I am often accused of working in my underwear, not showering through day-long stretches, not working and instead playing games all day and of course, being a drug dealer.  And NOTHING perpetuates that vision from the outside world like an overnight UPS package arriving with the sound of rattling pills inside.  This is what greeted me after my delivering smirked away:

pills1.jpg

In preparation for an upcoming graphics launch AMD thought up a pretty interesting marketing campaign geared around a "Verdetrol 1GHz" drug that will apparently help the reviewing community "enhance performance".  Hmph.

pills2.jpg

Actually contained within are 28 jelly beans (get it, 28nm???) of a flavor I can't quite detect though I am guessing they are somehow related to this.  And of course, these pills are for "external use only" - a healthy warning.

pills3.jpg

The telephone number is listed as 905-555-7770 so you can probably guess what the hubbub is all about.

pills4.jpg

And while the directions state to take one tablet daily by fan intake, we were never one to conform.

NVIDIA Kepler Graphics Cards Lineup Leak To Web

Subject: Graphics Cards | February 6, 2012 - 06:23 PM |
Tagged: nvidia, kepler, graphics, gpu

Although there were quite a few rumors leading up to AMD's Radeon 7000 series launch, the Internet has been very quiet on the greener side of the graphics market. Finally; however, we have some rumors to share with you on the Nvidia front. As always, take these numbers with more than your average grain of salt.

Specifically, EXP Review managed to uncover two charts that supposedly detail specifics about a range of GeForce 600 series Kepler cards from the number of stream processors to the release date. Needless to say, it's a lot of rumored information to take in all at once.

Anyway, without further adieu, let's dive into the two leaked charts.

Model Code Name Die Size Core Clock (TBD) MHz Shader Clock (TBD) GHz Stream Processors SM Count ROPs Memory Clock (effective) GDDR5  Bus Width Memory Bus Width
GTX690 GK110x2 550mm2 ~750 ~1.5 2x1024 2x32 2x56 4.5 GHz 2x448bit 2x252GB/s
GTX680 GK110 550mm2 ~850 ~1.7 1024 32 64 5.5 GHz 512bit 352GB/s
GTX670 GK110 550mm2 ~850 ~1.7 896 28 56 5 GHz 448bit 280GB/s
GTX660Ti GK110 550mm2 ~850 ~1.7 768 24 48 5 GHz 384bit 240GB/s
GTX660 GK104 290mm2 ~900 ~1.8 512 16 32 5.8 GHz 256bit 186GB/s
GTX650Ti GK104 290mm2 ~850 ~1.7 448 14 28 5.5 GHz 224bit 154GB/s
GTX650 GK106 155mm2 ~900 ~1.8 256 8 24 5.5 GHz 192bit 132GB/s
GTX640 GK106 155mm2 ~850 ~1.7 192 6 16 5.5 GHz 128bit 88GB/s

 

From the chart above, we can see the entire lineup of Kepler cards from the NVIDIA GTX 640 to the dual GPU GTX 690.  The die size in the higher end GeForce cards is approximately 50% larger than that of the AMD Radeon HD 7970, but not much bigger than that of the GTX 580.  If only we knew the TDP of these cards!  In the next chart, we see alleged performance comparison versus the AMD competition.

Model Bus Interface Frame Buffer Transistors (Billion) Price Point Release Date Performance Scale
GTX690 PCI-E 3 x16 2x1.75 GB 2x6.4 $999 Q3 2012  
GTX680 PCI-E 3 x16 2 GB 6.4 $649 April 2012 ~45%>HD7970
GTX670 PCI-E 3 x16 1.75 GB 6.4 $499 April 2012 ~20%>HD7970
GTX660Ti PCI-E 3 x16 1.5 GB 6.4 $399 Q2/Q3 2012 ~10%>HD7950
GTX660 PCI-E 3 x16 2 GB 3.4 $319 April 2012 ~GTX580
GTX650Ti PCI-E 3 x16 1.75 GB 3.4 $249 Q2/Q3 2012 ~GTX570
GTX650 PCI-E 3 x16 1.5 GB 1.8 $179 May 2012 ~GTX560
GTX640 PCI-E 3 x16 2 GB 1.8 $139 May 2012 ~GTX550Ti

 

If these numbers hold true, NVIDIA will handily beat the current AMD offerings; however, I would wait for reviews to come out before making any purchasing decisions.  One interesting aspect is the amount of GDDR5 memory.  It seems that NVIDIA is sticking with 2GB frame buffers (or less) per GPU while AMD has really started upping the RAM.  It will be interesting to see how this affects gaming in NVIDIA Surround and/or at high resolutions.

What do you guys think about these numbers, do you think Kepler will live up to the alleged performance scale figures?

Source: EXPreview

AMD shows 18mm thin reference ultrathin notebook based on Trinity

Subject: Graphics Cards, Processors, Mobile | February 2, 2012 - 02:02 PM |
Tagged: amd, trinity, hsa, ultrabook, ultrathin

Today at the AMD Financial Analyst day in Sunnyvale, Lisa Su, Senior Vice President and General Manager, Global Business Units, showed off a reference design from Compal of an 18mm think ultrathin notebook that they are obviously hoping to compete with Intel's Ultrabook push.

ultrathin1.jpg

The notebook is based on AMD's upcoming Trinity APU that improves on the CPU and GPU performance of the currently available Llano APU.  There weren't many details though Su did state they were hoping for prices in the $600-800 range would could but a lot of pressure on Intel. 

ultrathin2.jpg