Home
Nvidia

Colorful Shows Off Massive Passively Cooled NVIDIA GTX 680

Subject: Graphics Cards | July 2, 2012 - 06:53 PM |
Tagged: passive cooling, nvidia, kepler, gtx 680, gpu

Chinese graphics card manufacturer Colorful recently showed off a massive NVIDIA GTX 680 GPU. Massive may even be an understatement, as this card uses not one, but two heatsinks – and more heatpipes that Josh can shake a GPU at – to passively cool the fastest single GPU graphics card that NVIDIA has.

Colorful-680-1.jpg

While there is no word on pricing, availability, or clock speeds, the iGAME NVIDIA GTX 680 is a silent GPU that is going to need a seriously large case. One heatsink attaches as you would expect, right over the GPU, GDDR5 memory, and VRMs. It uses 140 aluminum fins and seven heatpipes traveling the length of the PCB to distribute heat.

Colorful-680-6.jpg

From there, six copper heatpipes transfer heat to a second heatsink with another 140 fins and seven heatpipes(!). This second heatsink appears to float over the top of the card, supported by the six heatpipes. The heatsink and PCB are black, with a blue piece covering the two heatsinks that features the iGame and NVIDIA GTX 680 logos. The back of the card features a single DVI port, a DisplayPort, and a full-size HDMI port.

Colorful-680-4.jpg

For the PC gamer that values silent performance with the least compromises possible, this card is looking like the perfect solution – assuming it comes to market, of course. If you are interested in seeing more photos of this passively cooled GTX 680 graphics card, check out the EXPReview story.

Source: EXPReview

Podcast #208 - AMD Radeon HD 7970 GHZ Edition, Intel Core i5-3470, our Blindfolded APU build and more!

Subject: General Tech | June 28, 2012 - 05:18 PM |
Tagged: Vertex 4, thunderbolt, ssd, podcast, nvidia, i5-3470, hd7970, blindfolded, APU, 7970 ghz edition

PC Perspective Podcast #208 - 06/28/2012

Join us this week as we talk about the AMD Radeon HD 7970 GHZ Edition, Intel Core i5-3470, our Blindfolded APU build and more!

You can subscribe to us through iTunes and you can still access it directly through the RSS page HERE.

The URL for the podcast is: http://pcper.com/podcast - Share with your friends!

  • iTunes - Subscribe to the podcast directly through the iTunes Store
  • RSS - Subscribe through your regular RSS reader
  • MP3 - Direct download link to the MP3 file

Hosts: Ryan Shrout, Jeremy Hellstrom, Josh Walrath and Allyn Malvantano

This Podcast is brought to you by MSI!

Program length: 1:05:24

Program Schedule:

  1. Introduction
  2. 1-888-38-PCPER or podcast@pcper.com
  3. http://pcper.com/podcast
  4. http://twitter.com/ryanshrout and http://twitter.com/pcper
  5. 0:01:42 AMD Radeon HD 7970 GHz Edition
  6. 0:09:10 Live Review Recap: AMD Radeon HD 7970 GHz Edition
  7. 0:10:30 Silverstone Crown Series CW02 case review
  8. 0:13:50 Intel Core i5-3470 IVB Review
  9. 0:21:11 This Podcast is brought to you by MSI!
  10. 0:22:05 Live Video Recap: AMD Llano APU Blindfolded Build
  11. 0:25:50 ASUS ROG Matrix HD 7970 coming soon
  12. 0:30:00 Sandia Cooler Prototype
  13. 0:39:50 Dell Ubuntu Notebooks
  14. 0:43:40 Can a 12-core ARM cluster hit critical mass?
  15. 0:48:20 Google announces Nexus 7 tablet powered by Tegra 3
  16. 0:55:55 Hardware / Software Pick of the Week
    1. Ryan: Thunderbolt on Windows Article coming tomorrow!!
    2. Jeremy: Core i7 3770K is a compute per watt monster
    3. Josh: Good PS for general use and excellent price
    4. Allyn: OCZ Vertex 4 FW 1.4.1.3
  17. 1-888-38-PCPER or podcast@pcper.com
  18. http://pcper.com/podcast
  19. http://twitter.com/ryanshrout and http://twitter.com/pcper
  20. Closing

Source: PC Perspective

GeForce 302.82 Driver for Win8

Subject: Graphics Cards | June 27, 2012 - 03:52 PM |
Tagged: win8, whql, nvidia, geforce, driver

If you are running Windows 8 and an NVIDIA graphics card on a desktop machine then you should head on over to NVIDIA to grab the WHQL certified GeForce 302.82 for 32-bit and 64-bit versions of the pre-release OS.  If you are on a laptop then NVIDIA suggests you should continue to use the 302.80 drivers for the moment. 

twimtbp.png

You will see a new NVIDIA Control Panel page that allows you to set up stereoscopic 3D for 3D Vision.  The drawbacks are few, the driver will request a reboot in order to finish the installation, which you should do whether you are asked or not, and there is an issue for users of the GT520 who enable FXAA via the NVIDIA control panel but other than those two addendum, NVIDIA posted no other known issues.  As it is a WHQL version, you can expect it to be stable and to be around for a bit as the release date of Win8 slowly approaches. 

Source: NVIDIA

Podcast #207 - Western Digital N900 HD Router, NVIDIA GT 640, Falling SSD prices, and more!

Subject: General Tech | June 21, 2012 - 04:03 PM |
Tagged: western digital, podcast, nvidia, N900, kepler, Intel, gt640, gpu, cpu, amd

PC Perspective Podcast #207 - 06/21/2012

Join us this week as we talk about the Western Digital N900 HD Router, NVIDIA GT 640, Falling SSD prices, and more!

You can subscribe to us through iTunes and you can still access it directly through the RSS page HERE.

The URL for the podcast is: http://pcper.com/podcast - Share with your friends!

  • iTunes - Subscribe to the podcast directly through the iTunes Store
  • RSS - Subscribe through your regular RSS reader
  • MP3 - Direct download link to the MP3 file

Hosts: Ryan Shrout, Jeremy Hellstrom, Josh Walrath and Allyn Malvantano

This Podcast is brought to you by MSI!

Program length: 1:17:19

Program Schedule:

  1. 0:00:58 Introduction
  2. 1-888-38-PCPER or podcast@pcper.com
  3. http://pcper.com/podcast
  4. http://twitter.com/ryanshrout and http://twitter.com/pcper
  5. 0:01:58 Join us for some cool live events this week! - http://pcper.com/live
  6. 0:05:15 Western Digital My Net N900 HD Router Review
  7. 0:19:00 Low-End Laptop Graphics Solution Comparison: Five Options Go Head-To-Head
  8. 0:22:03 Galaxy GeForce GT 640 GC 1GB DDR3 Review - GK107 is no GK104
  9. 0:30:17 This Podcast is brought to you by MSI!
  10. 0:31:00 Modest announcements at the last day of the AFDS
  11. 0:34:20 Western Digital and Seagate doomed to be marked as bad sectors?
  12. 0:37:45 How did we suddenly move past the $1/GB on SSDs?
  13. 0:40:25 SK Hynix to acquire Link_a_Media Devices for $248 million
  14. 0:44:30 Microsoft Surface announced, tablet to compete with iPad
  15. 0:52:40 Intel renames Larrabee to Xeon Phi
  16. 1:01:00 Hardware / Software Pick of the Week
    1. Ryan: Pegasus R4 Thunderbolt Unit - pushing 660 MB/s with RAID-0
    2. Jeremy: I change my mind … This is what I was promised!!
    3. Josh: I love the price drop!
    4. Allyn: Jawbone HD + The Nerd
  17. 1-888-38-PCPER or podcast@pcper.com
  18. http://pcper.com/podcast
  19. http://twitter.com/ryanshrout and http://twitter.com/pcper
  20. Closing

Source: PC Perspective

NVIDIA Responds to Linus Torvalds’ Rant

Subject: General Tech | June 21, 2012 - 01:35 PM |
Tagged: rant, optimus, open source, nvidia, linux, linus, drivers

Last week, the founder of Linux – Linus Torvalds – gave a speech at the Aalto Center for Entrepreneurship. The aspect that most people picked up on was a certain disparaging statement towards NVIDIA. Since then, the video has spread rapidly around the Internet with critics for and against the statement. Linus does not believe that NVIDIA is easy to work with regarding Linux support, in short. NVIDIA PR recently responded to his statement in stating that the company is in fact heavily involved with Linux development, albeit mobile kernels.

nvidia-2.jpg

NVIDIA stated in its PR release that supporting Linux is important to the company and they understand how important a positive Linux experience using NVIDIA hardware is. I don’t think anyone is surprised by that statement, but that was not all they said. The company stated that they are big supporters of the ARM Linux kernel with a claimed second most total lines changed and fourth highest number of changesets in the kernel.

The company uses proprietary drivers, but it does support GeForce, Quadro, and Tesla graphics cards under the Linux operating system. By using a common, proprietary driver, NVIDIA claims same-day support for new graphics cards and OpenGL versions for both Windows and Linux operating systems.

Linus’ rant started when an audience member asked about Optimus support under Linux. On that front, NVIDIA did not have a direct answer – only that when it launched laptops with Optimus, it was only supported on Windows 7. Allegedly, the company is working to make interaction between its drivers and the Bumblebee Open Source Project. The Bumblebee project is working to make Optimus-powered laptops work with Linux operating systems.

What do you think of the two statements by Linus and NVIDIA? Should NVIDIA be held accountable for Optimus support under Linux? Is the company doing enough to support the OS? Or is Linus wrong? Let us know in the comments below!

Personally, as much as I like Linux, I don’t think NVIDIA should have to go out of its way to support Optimus on Linux. At least, not until the Linux OS is the operating system that comes pre-installed on an Optimus notebook. At that point, it would be on NVIDIA to provide support. Until then, they don’t have to support it on aftermarket / third part operating systems. With that said, better Linux support couldn't hurt PR-wise. As far as Linux and NVIDIA working together in a more general sense, I think that the company could certainly do more for Linux on the desktop, especially being a Linux Foundation member, but I don't think they will until it is more financially viable to do so.

The full PR statement is available after the break.

Source: Phoronix

Graphics Card (GPU) Stock Check - June 20th, 2012

Subject: Graphics Cards | June 20, 2012 - 07:27 PM |
Tagged: stock check, radeon, nvidia, HD 7970, hd 7950, hd 7870, hd 7850, hd 7770, hd 7750, GTX 690, gtx 680, gtx 670, geforce, amd

Due to popular request, I am going to try to keep our readers up to date on the current availability of graphics cards and pricing on the market.  With the recent price drops from AMD, the frequent out-of-stock status of the GTX 680 cards and the release of the GTX 670, I thought this would be a great summary of the current situation.

stockcheck20120620.png

AMD's Radeon HD 7970 3GB

We will try to post new updates weekly or maybe more frequently as we see fit.  Newegg is our partner of choice for this today, so let's see what we have.

AMD Radeon HD 7000 Series

Radeon HD 7970 3GB - In Stock
Starting at $449

Radeon HD 7950 3GB - In Stock
Starting at $369

Radeon HD 7870 2GB - In Stock
Starting at $319

Radeon HD 7850 2GB - In Stock
Starting at $239

Radeon HD 7770 1GB - In Stock
Starting at $129

Radeon HD 7750 1GB - In Stock
Starting at $109

NVIDIA GeForce GTX 600 Series

GeForce GTX 690 4GB - In Stock
Starting at $1049

GeForce GTX 680 2GB - In Stock
Starting at $499

GeForce GTX 670 2GB - In Stock
Starting at $399

I think it is official, the GeForce GTX 680 has been in stock for more than two weeks in a row and we believe that this is a trend we see continuing through the summer.  Hell, we even found a single GTX 690 in stock from ASUS!

AMD is still doing great on availability with the Radeon HD 7970 and HD 7950 widely available for the price of $449 / $369 with a set of three free games including DiRT Showdown and Dues Ex: Human Revolution and yet another $10 price drop.  The fact that the Radeon HD 7970 is now down to $449 and is $50 less than the GTX 680 makes it a compelling solution for gamers yet again.

If you are looking for our latest graphics reviews to judge the performance of the above cards, here you go:

Source: PC Perspective

Galaxy GeForce GT 640 GC 1GB DDR3 Review - GK107 is no GK104

Author:
Date: June 20, 2012
Subject: Graphics Cards
Manufacturer: Galaxy
Tagged: nvidia, kepler, gt 640, GK107, geforce, galaxy

The GK107 GPU

With the release of the Kepler architecture in March of this year, NVIDIA has once again seemed to take back the hearts of PC gamers with a GPU that is both powerful and power efficient. The GK104 has seen a product implementation as the GTX 680, the dual-GPU GTX 690 and most recently as the GTX 670. With a price tag of $399 though, there is still a very large portion of the graphics card market that Kepler hasn’t touched but is being addressed firmly by AMD’s Radeon 7000 series.
 
01.jpg
 
Today we are going to be taking a look at NVIDIA’s latest offering, the sub-$100 card known as the GeForce GT 640 based on a completely new chip, the GK107. Specifically, we have the Galaxy GeForce GT 640 GC factory overclocked card.
 
NVIDIA’s GK107
 
Compared to the GK104 part, GK107 is a much smaller chip and the GT 640 implementation of it contains two SMX units and 384 CUDA cores. That is a significant drop off compared to the GTX 680 (1536 cores) and the GTX 670 (1344 cores) but it should really come as no surprise to those of you that follow the NVIDIA GPU families of the past.  The chip will have 32 texture units and 16 ROPs. 
 

NVIDIA's Tesla K10 offers serious single-precision performance

Subject: General Tech | June 19, 2012 - 03:04 PM |
Tagged: nvidia, tesla, K10, GK104, HPC

One of NVIDIA 's line of Tesla HPC cards, the Tesla K10 has actually been seen in the wild.  the new Tesla series is split between the GK104 based K10 model specifically designed for single-precision tasks and the GK110 based Tesla K20 and it is optimized for double-precision tasks.  The K10 is capable of 4.58 teraflops thanks to a pair of GK104s with 8GB of GDDR5, whereas the K20 should in theory double Intel's Xeon Phi at 2 teraflops of double-precision performance but that has yet to be demonstrated.  The K10 that was demonstrated also showed off another of the benefits of NVIDIA's new architecture, even with two GPUs the card remains within a 225W thermal envelop, something that is incredibly important if you are building a cluster.  The Register has gathered together some of the benchmarks and slides from NVIDIA's release, which you can see here.

elreg_nvidia_isc_tesla_k10_benchmarks.jpg

"The Top 500 supercomputer ranking is based on the performance of machines running the Linpack Fortran matrix math benchmark using double-precision floating point math, but a lot of applications will do just fine with single-precision math. And it is for these workloads, graphics chip maker and supercomputing upstart Nvidia says, that it designed the new Tesla K10 server coprocessors."

Here is some more Tech News from around the web:

Tech Talk

 

Source: The Register

Intel Introduces Xeon Phi: Larrabee Unleashed

Subject: Processors | June 19, 2012 - 11:46 AM |
Tagged: Xeon Phi, xeon e5, nvidia, larrabee, knights corner, Intel, HPC, gpgpu, amd

Intel does not respond well when asked about Larabee.  Though Intel has received a lot of bad press from the gaming community about what they were trying to do, that does not necessarily mean that Intel was wrong about how they set up the architecture.  The problem with Larrabee was that it was being considered as a consumer level product with an eye for breaking into the HPC/GPGPU market.  For the consumer level, Larrabee would have been a disaster.  Intel simply would not have been able to compete with AMD and NVIDIA for gamers’ hearts.
 
The problem with Larrabee and the consumer space was a matter of focus, process decisions, and die size.  Larrabee is unique in that it is almost fully programmable and features really only one fixed function unit.  In this case, that fixed function unit was all about texturing.    Everything else relied upon the large array of x86 processors and their attached vector units.  This turns out to be very inefficient when it comes to rendering games, which is the majority of work for the consumer market in graphics cards.  While no outlet was able to get a hold of a Larrabee sample and run benchmarks on it, the general feeling was that Intel would easily be a generation behind in performance.  When considering how large the die size would have to be to even get to that point, it was simply not economical for Intel to produce these cards.
 
phi_01.jpg
 
Xeon Phi is essentially an advanced part based on the original Larrabee architecture.
 
This is not to say that Larrabee does not have a place in the industry.  The actual design lends itself very nicely towards HPC applications.  With each chip hosting many x86 processors with powerful vector units attached, these products can provide tremendous performance in HPC applications which can leverage these particular units.  Because Intel utilized x86 processors instead of the more homogenous designs that AMD and NVIDIA use (lots of stream units doing vector and scalar, but no x86 units or a more traditional networking fabric to connect them).  This does give Intel a leg up on the competition when it comes to programming.  While GPGPU applications are working with products like OpenCL, C++ AMP, and NVIDIA’s CUDA, Intel is able to rely on many current programming languages which can utilize x86.  With the addition of wide vector units on each x86 core, it is relatively simple to make adjustments to utilize these new features as compared to porting something over to OpenCL.
 
So this leads us to the Intel Xeon Phi.  This is the first commercially available product based on an updated version of the Larrabee technology.  The exact code name is Knights Corner.  This is a new MIC (many integrated cores) product based on Intel’s latest 22 nm Tri-Gate process technology.  The details are scarce on how many cores this product actually contains, but it looks to be more than 50 of a very basic “Pentium” style core;  essentially low die space, in-order, and all connected by a robust networking fabric that allows fast data transfer between the memory interface, PCI-E interface, and the cores.
 
intelphi.jpg
 
Each Xeon Phi promises more than 1 TFLOP of performance (as measured by Linpack).  When combined with the new Xeon E5 series of processors, these products can provide a huge amount of computing power.  Furthermore, with the addition of the Cray interconnect technology that Intel acquired this year, clusters of these systems could provide for some of the fastest supercomputers on the market.  While it will take until the end of this year at least to integrate these products into a massive cluster, it will happen and Intel expects these products to be at the forefront of driving performance from the Petascale to the Exascale.
 
phi_02.jpg
 
These are the building blocks that Intel hopes to utilize to corner the HPC market.  Providing powerful CPUs and dozens if not hundreds of MIC units per cluster, the potential computer power should bring us to the Exascale that much sooner.
 
Time will of course tell if Intel will be successful with Xeon Phi and Knights Corner.  The idea behind this product seems sound, and the addition of powerful vector units being attached to simple x86 cores should make the software migration to massively parallel computing just a wee bit easier than what we are seeing now with GPU based products from AMD and NVIDIA.  The areas that those other manufacturers have advantages over Intel are that of many years of work with educational institutions (research), software developers (gaming, GPGPU, and HPC), and industry standards groups (Khronos).  Xeon Phi has a ways to go before being fully embraced by these other organizations, and its future is certainly not set in stone.  We have yet to see 3rd party groups get a hold of these products and put them to the test.  While Intel CPUs are certainly class leading, we still do not know of the full potential of these MIC products as compared to what is currently available in the market.
 

The one positive thing for Intel’s competitors is that it seems their enthusiasm for massively parallel computing is justified.  Intel just entered that ring with a unique architecture that will certainly help push high performance computing more towards true heterogeneous computing. 

Source: Intel

New NVIDIA GeForce 304.48 Beta driver available

Subject: Graphics Cards | June 18, 2012 - 04:37 PM |
Tagged: nvidia, graphics drivers

If you want to see your performance in Batman: Arkham City jump by 17.6% and your Dragon Age 2 and S.T.A.L.K.E.R. Call of Pripyat increase about 10% then you want to upgrade to the newest beta driver from NVIDIA.  There is more to it than that however, they have completely redesigned the interface of the Control Panel, now offering far more control over MSAA in a variety of games.  There are new SLI profiles as well as updated 3D Vision profiles for those of you with the requisite components, which will enhance your experience in a number of games.

geforce-304-48-beta-diablo-iii-nvcpl-650.png

As usual there are also bug fixes, ranging from a fix for factory overclocked cards which occasionally downclock and refuse to come back, boot issues caused by Display Port adapters and a variety of game specific fixes.  Head over to GeForce.com for your update.

Source: NVIDIA

PC Perspective
Upcoming Events
  • 5/29 @ 7:00pm PDT / 10:00pm EDT
    PC Perspective Podcast
  • 5/30 @ 6:00pm PDT / 9:00pm EDT
    This Week in Computer Hardware