Subject: Graphics Cards | June 20, 2013 - 04:28 PM | Tim Verry
Tagged: nvidia, kepler, gtx 760, GK104, gk-104, gaming
There have been rumors of a new mid-range Kepler-based graphics card coming that will be next entry in the GTX 700-series. This new GPU is rumored to be called the GeForce GTX 760. If the specifications are true, the card will fit between the existing GTX 660 and GTX 660 Ti graphics cards as far as hardware specifications and pricing. While it will be under the GTX 700-series, it will not have the faster 7Gbps memory clockspeed of the other 700-series cards.
As far as specifications, Videocardz claims to have the final specifications list in a recent news post. The GTX 760 is rumored to be the latest graphics card to use NVIDIA's GK-104 "Kepler" GPU. The GTX 760 will have some units disabled for a GPU with 1,152 CUDA cores, 96 Texture Manipulation Units (TMUs), and 32 Raster Operations Processors (ROPs). The GPU supports NVIDIA's latest GPU Boost 2.0 technology which will automatically ratchet up the Boost clockspeed so long as temperature allows. It has a base clockspeed of 980 MHz and a boost clockspeed of 1,033 Mhz.
GTX 760 graphics cards will allegedly come in both 2GB and 4GB GDDR5 memory flavors. NVIDIA is clocking the memory at 6 Gbps (1502 MHz), which makes it the fist 700-series part to not take advantage of faster memory chips. However, there is a bit of saving grace as NVIDIA has moved to a 256-bit memory bus. This allows the card to still see a respectable bump in memory bandwidth of 192 GB/s on the GTX 760 versus the GTX 660/GTX 660 Ti's 144.2 GB/s bandwidth.
Compared to the existing mid-range 600-series cards, the GTX 760 has base and boost GPU clockspeeds equal to the GTX 660 (and faster than the GTX 660 TI). Memory clockspeed is also unchanged on the new card, though it has a wider memory bus. The GTX 760 has 192 more CUDA cores than the GTX 660, but 192 fewer CUDA cores versus the GTX 660 Ti. TMUs are also sit evenly between the two 600-series cards, but the GTX 760 does have 8 more ROPs enabled than both the 660 and 660 Ti.
Graphics cards with the upcoming GTX 760 GPU will be powered by two 6-pin PCI-E power connectors, and it has a 170W TDP. That power consumption puts the card between the 150W GTX 660 Ti and the higher-end 230W GTX 770. It appears that the card will not come with the high-end stock metallic cooler used in the other 700-series cards, though the various AIBs are likely to fit the GPU with their own custom aftermarket coolers. Video outputs on the cards will incluce DVI-I, DVI-D, HDMI, and DisplayPort.
The chart below compares the specifications between the GTX 660, GTX 660 Ti, GTX 770, and the rumored GTX 760.
|GTX 760||GTX 660||GTX 660 Ti||GTX 770|
|GPU Base||980 MHz||980 Mhz||915 Mhz||1046 Mhz|
|GPU Boost||1033 MHz||1033 MHz||980 Mhz||1085 MHz|
|Memory Clock||1502 MHz||1502 MHx||1502 Mhz||1752 Mhz|
|Bandwidth||192 GB/s||144.2 GB/s||144.2 GB/s||224 GB/s|
|TDP||170 W||140 W||150 W||230 W|
The card is supposedly going to be released on June 25th for around $300. It will compete with AMD's 7950 with boost graphics card. Further, the card will be an alternative to NVIDIA's own GTX 660 Ti and an upgrade for gamers still running GTX 560 cards with the company's older Fermi-based GPU.
Subject: General Tech | June 20, 2013 - 01:51 AM | Josh Walrath
Tagged: Volta, nvidia, maxwell, licensing, kepler, Denver, Blogs, arm
Yesterday we all saw the blog piece from NVIDIA that stated that they were going to start licensing their IP to interested third parties. Obviously, there was a lot of discussion about this particular move. Some were in favor, some were opposed, and others yet thought that NVIDIA is now simply roadkill. I believe that it is an interesting move, but we are not yet sure of the exact details or the repercussions of such a decision on NVIDIA’s part.
The biggest bombshell of the entire post was that NVIDIA would be licensing out their latest architecture to interested clients. The Kepler architecture powers the very latest GTX 700 series of cards and at the top end it is considered one of the fastest and most efficient architectures out there. Seemingly, there is a price for this though. Time to dig a little deeper.
Kepler will be the first technology licensed to third party manufacturers. We will not see full GPUs, these will only be integrated into mobile products.
The very latest Tegra parts from NVIDIA do not feature the Kepler architecture for the graphics portion. Instead, the units featured in Tegra can almost be described as GeForce 7000 series parts. The computational units are split between pixel shaders and vertex shaders. They support a maximum compatibility of D3D 9_3 and OpenGL ES 2.0. This is a far cry from a unified shader architecture and support for the latest D3D 11 and OpenGL ES 3.0 specifications. Other mobile units feature the latest Mali and Adreno series of graphics units which are unified and support DX11 and OpenGL ES 3.0.
So why exactly does the latest Tegras not share the Kepler architecture? Hard to say. It could be a variety of factors that include time to market, available engineering teams, and simulations which could dictate if power and performance can be better served by a less complex unit. Kepler is not simple. A Kepler unit that occupies the same die space could potentially consume more power with any given workload, or conversely it could perform poorly given the same power envelope.
We can look at the desktop side of this argument for some kind of proof. At the top end Kepler is a champ. The GTX 680/770 has outstanding performance and consumes far less power than the competition from AMD. When we move down a notch and see the GTX 660 Ti/HD 7800 series of cards, we see much greater parity in performance and power consumptions. Going to the HD 7790 as compared to the 650 Ti Boost, we see the Boost part have slightly better performance but consumes significantly more power. Then we move down to the 650 and 650 Ti and these parts do not consume any more power than the competing AMD parts, but they also perform much more poorly. I know these are some pretty hefty generalizations and the engineers at NVIDIA could very effectively port Kepler over to mobile applications without significant performance or power penalties. But so far, we have not seen this work.
Power, performance, and die area aside there is also another issue to factor in. NVIDIA just announced that they are doing this. We have no idea how long this effort has been going, but it is very likely that it has only been worked on for the past six months. In that time NVIDIA needs to hammer out how they are going to license the technology, how much manpower they must provide licensees to get those parts up and running, and what kind of fees they are going to charge. There is a lot of work going on there and this is not a simple undertaking.
So let us assume that some three months ago an interested partner such as Rockchip or Samsung comes knocking to NVIDIA’s door. They work out the licensing agreements and this takes several months. Then we start to see the transfer of technology between the companies. Obviously Samsung and Rockchip are not going to apply this graphics architecture to currently shipping products, but will instead bundle it in with a next generation ARM based design. These designs are not spun out overnight. For example, the 64 bit ARMv8 designs have been finalized for around a year, and we do not expect to see initial parts being shipped until late 1H 2014. So any partner that decides to utilize NVIDIA’s Kepler architecture for such an application will not see this part be released until 1H 2015 at the very earliest.
Sheild is still based on a GPU posessing separate pixel and vertex shaders. DX11 and OpenGL ES 3.0? Nope!
If someone decides to license this technology from NVIDIA, it will not be of great concern. The next generation of NVIDIA graphics will already be out by that time, and we could very well be approaching the next iteration for the desktop side. NVIDIA plans on releasing a Kepler based mobile unit in 2014 (Logan), which would be a full year in advance of any competing product. In 2015 NVIDIA is planning on releasing an ARM product based on the Denver CPU and Maxwell GPU. So we can easily see that NVIDIA will only be licensing out an older generation product so it will not face direct competition when it comes to GPUs. NVIDIA obviously is hoping that their GPU tech will still be a step ahead of that of ARM (Mali), Qualcomm (Adreno), and Imagination Technologies (PowerVR).
This is an easy and relatively painfree way to test the waters that ARM, Imagination Technologies, and AMD are already treading. ARM only licenses IP and have shown the world that it can not only succeed at it, but thrive. Imagination Tech used to produce their own chips much like NVIDIA does, but they changed direction and continue to be profitable. AMD recently opened up about their semi-custom design group that will design specific products for customers and then license those designs out. I do not think this is a desperation move by NVIDIA, but it certainly is one that probably is a little late in coming. The mobile market is exploding, and we are approaching a time where nearly every electricity based item will have some kind of logic included in it, billions of chips a year will be sold. NVIDIA obviously wants a piece of that market. Even a small piece of “billions” is going to be significant to the bottom line.
Kepler-based Mobile GPUs
Late last month, just before the tech world blew up from the mess that is Computex, NVIDIA announced a new line of mobility discrete graphics parts under the GTX 700M series label. At the time we simply posted some news and specifications about the new products but left performance evaluation for a later time. Today we have that for the highest end offering, the GeForce GTX 780M.
As with most mobility GPU releases it seems, the GTX 700M series is not really a new GPU and only offers cursory feature improvements. Based completely on the Kepler line of parts, the GTX 700M will range from 1536 CUDA cores on the GTX 780M to 768 cores on the GTX 760M.
The flagship GTX 780M is essentially a desktop GTX 680 card in a mobile form factor with lower clock speeds. With 1536 CUDA cores running at 823 MHz and boosting to higher speeds depending on the notebook configuration, a 256-bit memory controller running at 5 GHz, the GTX 780M will likely be the fastest mobile GPU you can buy. (And we’ll be testing that in the coming pages.)
The GTX 760M, 765M and 770M offering ranges of performance that scale down to 768 cores at 657 MHz. NVIDIA claims we’ll see the GTX 760M in systems as small as 14-in and below with weights at 2kg or so from vendors like MSI and Acer. For Ultrabooks and thinner machines you’ll have to step down to smaller, less power hungry GPUs like the GT 750 and 740 but even then we expect NVIDIA to have much faster gaming performance than the Haswell-based processor graphics.
Subject: Graphics Cards | June 4, 2013 - 04:04 AM | Tim Verry
Tagged: poseidon, nvidia, kepler, gtx 770, gk-104, computex 2013, computex, ASUS ROG, asus
NVIDIA took the wraps off of its latest-generation Geforce GTX 770 GPU last week, and manufacturers have begun announcing not only reference designs but custom and factory overclocked versions of this GK-104 "Kepler" GPU refresh. One card in particular that caught my attention was the ASUS GTX 770 Poseidon graphics card, which combines NVIDIA's GK-104 GPU with a hybrid heatsink and fan combo that allows the simultaneous use of water and air cooling!
According to the branding, and a hands-on report by Tech Power Up at Computex in Taipei, Taiwan, the GTX 770 Poseidon graphics card is part of the company's Republic of Gamers (ROG) line and likely sports beefy VRM hardware and factory GPU overclocks. Of course, the GTX 770 GPU uses NVIDIA's Kepler architecture and is essentially the GTX 680 with some seriously overclocked memory and refined GPU Boost technology. That means 1,536 CUDA cores, 128 texture units, and 32 ROPs (raster operation units) within 4 GPCs (Graphics Processing Clusters). This is the full GK-104 chip, desite the x70 name. For more information on the GTX 770 GPU, check out our recent review of the NVIDIA GTX 770 card.
Update: ASUS has just launched the new ROG graphics cards at a Computex press conference. According to the ASUS press release:
"ROG Poseidon graphics card with hybrid DirectCU H2O cooling
The new ROG Poseidon graphics card features an NVIDIA® GeForce® GTX 700 Series GPU and a hybrid DirectCU H2O thermal design that supports both air and liquid cooling. Developed by ASUS, its CoolTech fan combines blower and axial fans in one design, forcing air in multiple directions over the heatsink to maximize heat dissipation. Liquid cooling reduces operating temperatures by up to 31 degrees Celsius for cooler running with even greater overclocking potential. ROG Poseidon also features a red pulsing ROG logo for a distinctive dash of style."
Back on the Poseidon specifcally, the card is a short GTX 770 with a distinctive cooler that uses a full cover water block that covers the entire card and includes the GPU, memory, and VRM areas. ASUS further added a more-traditional air cooler to the area above the GPU itself to help dissapate heat. The air cooler is a circular aluminum fin array with a fan that sits in the middle. The air entire hybrid cooler is then covered by a ROG-themed shroud with a configurable LED-backlit Republic of Gamers logo on the side that can be controlled via software.
The water cooling portion acts as any other full cover water block, allowing cool water to move heat away from the metal contact (the bottom of the block) touching the various components. The inlet and outlets poke out from the side of the card, which is a bit odd but the shroud prevents them coming out at 90-degrees like typical blocks. If your case width is tight, you may need to get creative to fit a 90-degree barb extender (I apologize if that's not the technical term) on to the existing tubing connectors (heh). The cooler can be operated with the air cooler's fan running with or without being connected to a water loop. When water cooling is used, the fan can be turned off to reduce noise or left on to allow for higher overclocks and/or lower temperatures.
Unfortunately, that is all of the information that is currently available
as ASUS has not yet officially launched on the custom GTX 770 graphics card. Pricing, availability, and clockspeed details are still unknown.
For more information, stay tuned to the press.asus.com/events livestream page as it might be announced at a Computex press conference this week since the company is showing off the hardware at the show!
Subject: Systems, Mobile, Shows and Expos | June 4, 2013 - 02:59 AM | Tim Verry
Tagged: computex 2013, computex, nvidia, msi, kepler, Intel, haswell, gtx 700M, gs70, gaming notebook
A couple of weeks ago, MSI revealed the GX70 and GX60 gaming notebooks powered by AMD's latest Richland APUs and 8970M (and 7970M) discrete graphics cards. Today, the company added the GS70 notebook to its lineup, and it is the opposite in terms of underlying technology. Specifically, the GS70 is a 17" gaming notebook with an Intel Haswell processor and a NVIDIA GTX765M. The portable gaming machine is 22mm thick and weighs in at less than 5.7 pounds (2.6kg), which is a noticeably weight reduction versus the Richland-powered models.
Expert Reviews UK goes hands-on with a prototype of the MSI GS70 at Computex 2013.
The GS70 comes clad in glossy black and is constructed of aluminum. External features include a large 17" (likely TN) display with a resolution of 1920 x 1080, a SteelSeries-engineered multicolor backlit keyboard, and a large trackpad. Connectivity options include:
- 4 x USB 3.0
- 1 x RJ45 LAN jack
- 3 x audio jacks (with surround sound support)
- 1 x SD card slot
- 1 x HDMI
- 2 x mini DisplayPort
Internal specifications include a not-yet-named Intel 4th Generation Core "Haswell" CPU, 8GB of DDR3 RAM, and a NVIDIA GTX 765M. The discrete GPU is based on NVIDIA's Kepler architecture and features 768 CUDA cores clocked at 850 MHz and up to 2GB of graphics memory clocked at 1 GHz on a 128-bit bus. The system also uses a Killer NIC networking card and MSI's own SuperRAID technology that pairs two solid state drives in a RAID configuration for pure performance. The system should be able to play all modern PC games, though some details will need to be turned down. Multi-display output is supported for up to three external displays as well.
Unfortunately, MSI has not yet announced pricing or availability for this notebook. I would expect it to (paradoxically, despite the naming conventions) cost more than the existing GX70 (due to the newer, and faster, technology used) which starts at $1,399.99 MSRP. Keep an eye out for reviews later this year if you are interested in a mobile gaming PC, as this one looks interesting. Until then, Expert Reviews UK has some initial impressions and additional photos in this article.
Subject: Systems, Mobile | June 2, 2013 - 11:18 PM | Tim Verry
Tagged: quadro k1000m, origin pc, nvidia, kepler, Intel, haswell, gtx 700M, gaming, eon17-s, eon15-s
Origin PC has announced that it will be integrating Haswell CPUs and GTX700M GPUs into its line of gaming notebooks and desktops. Specifically, Origin PC will add Haswell CPUs to its Genesis, Millennium, and Chronos desktop PCs. Origin PC is also outfitting its EON gaming laptops with both Haswell CPU and GTX700M GPU upgrades. And to sweeten the pot (if only slightly), Origin is bundling a voucher for Grid 2 with each Haswell-equipped Origin PC order.
Both the EON15-S and EON17-S gaming laptops feature Intel Haswell processors, NVIDIA GTX700M or Quadro K1000M mobile graphics cards, and up to five storage drives when the optical drive is removed. The laptops are even able to have an independent RAID of two mSATA SSDs and two hard drives or SSDs along with a non-RAID storage drive in the optical bay—that's a lot of storage for a laptop!
The laptops come with customizable display lids available in red, black, silver, or a custom air brush as well as back-lit keyboards and touchpads. As the SKU names suggest, the EON15-S has a 15.6” display while the EON17-S has a 13.3” display. Origin PC is further offering factory overclocking for the Haswell processors and GTX700M graphics cards. The company claims up to a 20-times power reduction during idle thanks to the more power-efficient hardware.
Unfortunately, all this new tech comes at a premium, and the EON15-S and EON17-S gaming notebooks start at $1,722 and $1,784 respectively. As far as the desktops go, there is also a slight bump in price depending on the Haswell chip you select during the customization process. Upgrading to an Intel Core i7-4770K on the GENESIS desktop costs an extra $193, for example.
You can find more information on the Origin PC website.
Subject: Graphics Cards | June 1, 2013 - 10:00 PM | Tim Verry
Tagged: nvidia, kepler, gtx 770, graphics card
NVIDIA recently unveiled its GTX 770 GPU. Sitting between the GTX 680 and GTX 780, the Geforce GTX 770 is a refined GK104 with higher clockspeeds and improved GPU boost. It features 1536 CUDA cores and a 256-bit memory bus.
While the stock GTX 770 comes clocked at 1046 MHz base and 1085 MHz boost, ASUS is factory overclocking its DirectCU II OC card with a maximum boost GPU clockspeed of 1110 MHz. The 2GB of GDDR5 memory on the card will come clocked at 7010 MHz.
The differentiating factor here (aside from the overclock) is the custom DirectCU II cooler. ASUS has fitted the overclocked GTX 770 with a DirectCU cooler that uses copper heatpipes that directly contact the GPU and attach to an aluminum fin stack. The heatsink is, in turn, cooled by two 80mm fans. ASUS claims that the GTX 770 DirectCU II OC is up to 20% cooler and three-times quieter than the referrence NVIDIA cooler. Other features include a 10-phase DIGI+ VRM, and “Super Alloy Power” capacitors, chokes, and MOSFETs. The dual slot card is 10.7” long and includes two DL-DVI, one HDMI, and one DisplayPort video ouptut. ASUS' GPU Tweak software will allow users to adjust core and memory clockspeeds, voltage, fan speeds, and the power control target.
The ASUS GTX 770 DirectCU II OC is shipping now and will be available at retailers soon. In fact, the card is avaiable at Newegg right now for just under $410.
Read more about NVIDIA's GTX 770 GPU: NVIDIA GeForce GTX 770 Review - GK104 Speed Bump @ PC Perspective!
Subject: Graphics Cards | June 1, 2013 - 09:11 PM | Tim Verry
Tagged: gtx 700M, nvidia, mobile gpu, kepler, 780m, 700m
Earlier this year (beginning of April), NVIDIA introduced the first set of mobile graphics cards in its 700M series. These were relatively low-end cards that features at most 384 CUDA cores and were based on NVIDIA's 600-series Kepler architecture.
NVIDIA is now adding higher-end mobile GPUs to the 700M family with the GTX 760M, GTX 765M, GTX 770M, and GTX 780M. These chips are still based on Kepler (600-series), but feature more CUDA cores, more memory, a wider memory bus, and faster clockspeeds. The GTX 780M is not quite the mobile equivalent to the desktop GTX 680, but NVIDIA is matching it up against AMD's 8970M GPU and claims that it can run games like Sleeping Dogs, Assassins Creed 3, and Borderlands 2 at Ultra settings (1080p). The GTX 770M is also capable of running modern games, though some detail setitng may need to be turned down.
The chart below details the various specifications and compares the new GTX 700M cards to the existing GT 700M GPUs. At the high end, NVIDIA has the GTX 780M with 1,536 CUDA cores, a base clock of 823 MHz, and 4GB of GDDR5 memory (1250 MHz) on a 256-bit bus. The GTX 770M occupies the mid-range mobile gaming slot with 960 CUDA cores, a base clock of 811 MHz, and a memory clock of 1GHz. The GTX 760M and GTX 765M have similar hardware specifications, but the GTX 765M has a higher GPU base clock of 850 MHz versus the GTX 760M's 657 MHz base clock. The low end GTX 700M GPUs (760M and 765M) feature 768 CUDA cores, a 128-bit memory bus, and memory clockspeeds of 1GHz.
|GTX 720M||GTX 735M||GT 740M||GT 750M||GTX 760M||GTX 765M||GTX 770M||GTX 780M|
|GPU Base Clock||938 MHz||889 MHz||980 MHz||967 MHz||657 MHz||850 MHz||811 MHz||823Mhz|
|Memory Clock||1000 MHz||1000 MHz||2500 MHz||2500 MHz||1000 MHz||1000 MHz||1000 MHz||1250 MHz|
Further, GPU Boost 2.0, Geforce Experience software, and NVIDIA Optimus support are features of the new GTX 700M graphics cards. You can read more about these NVIDIA technologies in this article by motherboard reviewer Morry Teitelman.
These cards are based on NVIDIA's 600-series despite the 700M moniker. They should provide OEMs with some good gaming options on the NVIDIA side of things and allow for some more competition in the gaming notebook hardware space against the existing AMD cards.
Subject: Graphics Cards | May 30, 2013 - 06:55 PM | Jeremy Hellstrom
Tagged: nvidia, kepler, gtx 770, gtx 680, GK104, geforce, MSI GTX660 HAWK
$400 is a tempting number, much less expensive than the $650 price tag on the GTX 780 and right in line with the existing GTX670 as well as AMD's HD7970. You will probably not see many at that price, $450 is more likely as there will be very few reference cards released, all manufacturers will be putting there own spins on the design of these cards, which brings the price in line with the GTX680. Performance wise these cards outpace the two current single GPU flagship cards, not by enough to make it worth upgrading from a 7970 or 680 but certainly enough to attract owners of previous generation cards. [H]ard|OCP reviewed MSI's Lightning model, with dual fans, an overclock of 104MHz on the base clock and 117MHz boost, plus a completely unlocked BIOS for even more tweaking choices.
If you want to see how well it fares on our new Frame Rating metric you will have to read Ryan's full review here.
"NVIDIA debuts the "new" GeForce GTX 770 today. The GeForce GTX 770 is poised to provide refreshed performance, for a surprising price. We evaluate a retail MSI GeForce GTX 770 Lightning flagship video card from MSI with specifications that will make any enthusiast smile. The $399 price point just got a kick in the pants."
Here are some more Graphics Card articles from around the web:
- NVIDIA GeForce GTX 770 Review @ Neoseeker
- NVIDIA GeForce GTX 770 Review: The $400 Fight @ AnandTech
- The NVIDIA GeForce GTX 770 Tech Report @ TechARP
- EVGA GTX 770 ACX @ LanOC Reviews
- Nvidia GTX 770 @ LanOC Reviews
- MSI GeForce GTX 770 Gaming and ASUS GeForce GTX 770 DirectCU II Review @ Legit Reviews
- ASUS GTX 770 DirectCU II OC 2 GB @ techPowerUp
- Palit GTX 770 JetStream 2 GB @ techPowerUp
- NVIDIA GeForce GTX 770 Video Card @ Benchmark Reviews
- Gigabyte GTX 770 WindForce OC 2 GB @ techPowerUp
- Nvidia GeForce GTX 770 review incl. 3-way SLI and frametimes @ Hardware.info
- Gigabyte GeForce GTX 770 OC 2GB Video Card Review @HiTech Legion
- Move Aside, GTX 680: NVIDIA GeForce GTX 770 Review @ Techgage
- GeForce GTX 770 Review: Adding Value to High-End GFX @ Techspot
- NVIDIA GeForce GTX 770 2GB Video Card Review @Hi Tech Legion
- MSI Twin Frozr GTX770 OC @ Kitguru
- GTX770 video with Asus @ Kitguru
- NVIDIA GeForce GTX 770 Review @ Hardware Canucks
- NVIDIA GeForce GTX 770 2 GB @ techPowerUp
- MSI GTX 770 Gaming Review @ OCC
- Gainward GeForce GTX 770 Phantom @ Legion Hardware
- NVIDIA GeForce GTX 780 Review @ Neoseeker
- NVIDIA GeForce GTX 780 Video Card Review @ Legit Reviews
- EVGA GeForce GTX 780 3GB SuperClocked Video Cards in SLI Overclocked @ Tweaktown
- EVGA GeForce GTX 780 3GB SuperClocked Video Cards in SLI @ Tweaktown
- PowerColor HD 7850 SCS3 passive 1 GB @ techPowerUp
- HIS 7850 IceQ Turbo 2GB GDDR5 Video Card Review @ Madshrimps
- PowerColor Radeon HD 7870 Myst Edition Crossfire Review @ OCC
- PowerColor HD Radeon 7850 SCS3 Passive Graphics Card @ eTeknix
GK104 gets cheaper and faster
A week ago today we posted our review of the GeForce GTX 780, NVIDIA's attempt to split the difference between the GTX 680 and the GTX Titan graphics cards in terms of performance and pricing. Today NVIDIA launches the GeForce GTX 770 that, even though it has a fancy new name, is a card and a GPU that you are very familiar with.
The NVIDIA GK104 GPU Diagram
Based on GK104, the same GPU that powers the GTX 680 (released in March 2012), GTX 670 and the GTX 690 (though in a pair), the new GeForce GTX 770 has very few changes from the previous models that are really worth noting. NVIDIA has updated the GPU Boost technology to 2.0 (more granular, better controls in software) but the real changes come in the clocks speeds.
The GTX 770 is still built around 4 GPCs and 8 SMXs for a grand total of 1536 CUDA cores, 128 texture units and 32 ROPs. The clock speeds have increased from 1006 MHz base clock and 1058 MHz Boost up to 1046 MHz base and 1085 MHz Boost. That is a pretty minor speed bump in reality, an increase of just 4% or so over the previous clock speeds.
NVIDIA did bump up the GDDR5 memory speed considerably though, going from 6.0 Gbps to 7.0 Gbps, or 1750 MHz. The memory bus width remains 256-bits wide but the total memory bandwidth has jumped up to 224.3 GB/s.
Maybe the best change for PC gamers is the new starting MSRP for the GeForce GTX 770 at $399 - a full $50-60 less than the GTX 680 was selling for as of yesterday. If you happened to pick up a GTX 680 recently, you are going to want to look into your return options as this will surely annoying the crap out of you.
If you want more information on the architecture design of the GK104 GPU, check out our initial article on the chips release from last year. Otherwise, with those few specification changes out of the way, let's move on to some interesting information.
The NVIDIA GeForce GTX 770 2GB Reference Card
Tired of this design yet? If so, you'll want to look into some of the non-reference options I'll show you on the next page from other vendors, but I for one am still taken with the design of these cards. You will find a handful of vendors offering up re-branded GTX 770 options at the outset of release but most will have their own SKUs to showcase.