NVIDIA Allegedly Launching Quadro K6000 GK110 GPU For Professionals
Subject: Graphics Cards | March 8, 2013 - 09:17 AM | Tim Verry
Tagged: quadro, nvidia, kepler, k6000, gk110
Earlier this week, NVIDIA updated its Quadro line of workstation cards with new GPUs with GK104 “Kepler” cores. The updated line introduced four new Kepler cards, but the Quadro 6000 successor was notably absent from the NVIDIA announcement. If rumors hold true, professionals may get access to a K6000 Quadro card after all, and one that is powered by GK110 as well.
According to rumors around the Internet, NVIDIA has reserved its top-end Quadro slot for a GK110-based graphics card. Dubbed the K6000 (and in line with the existing Kepler Quadro cards), the high-end workstation card will feature 13 SMX units, 2,496 CUDA cores, 192 Texture Manipulation Units, 40 Raster Operations Pipeline units, and a 320-bit memory bus. The K6000 card will likely have 5GB of GDDR5 memory, like its Tesla K20 counterpart. Interestingly, this Quadro K6000 graphics card has one less SMX unit than NVIDIA’s Tesla K20X and even NVIDIA’s consumer-grade GTX Titan GPU. A comparison between the rumored K6000 card, the Quadro K5000 (GK104), and other existing GK110 cards is available in the table below. Also, note that the (rumored) K6000 specs put it more in like with the Tesla K20 than the K20X, but as it is the flagship Quadro card I felt it was still fair to compare it to the flagship Telsa and GeForce cards.
| Quadro K6000 | Tesla K20X | GTX Titan | GK110 Full (Not available yet) | Quadro K5000 | |
| SMX Units | 13 | 14 | 14 | 15 | 8 |
| CUDA Cores | 2,496 | 2,688 | 2,688 | 2,880 | 1536 |
| TMUs | 192 | 224 | 224 | 256 | 128 |
| ROPs | 40 | 48 | 48 | 48 | 32 |
| Memory Bus | 320-bit | 384-bit | 384-bit | 384-bit | 256-bit |
| DP TFLOPS | ~1.17 TFLOPS | 1.31 TFLOPS | 1.31 TFLOPS | ~1.4 TFLOPS | .09 TFLOPS |
| Core | GK110 | GK110 | GK110 | GK110 | GK104 |
The Quadro cards are in an odd situation when it comes to double precision floating point performance. The Quadro K5000 which uses GK104 brings an abysmal 90 GFLOPS of double precision. The rumored GK110-powered Quadro K6000 brings double precision performance up to approximately 1 TFLOPS, which is quite the jump and shows that GK104 really was cut down to focus on gaming performance! Further, the card that the K6000 is replacing in name, the Quadro 6000 (no prefixed K), is based on NVIDIA’s previous-generation Fermi architecture and offers .5152 TFLOPS (515.2 GFLOPS) of double precision performance. On the plus side, users can expect around 3.5 TFLOPS of single precision horsepower, which is a substantial upgrade over Quadro 6000's 1.03 TFLOPS of single precision floating point. For comparison, the GK104-based Quadro K5000 offers 2.1 TFLOPS of single precision. Although it's no full GK110, it looks to be the Quadro card to beat for the intended usage.
Of course, Quadro is more about stable drivers, beefy memory, and single precision than double precision, but it would be nice to see the expensive Quadro workstation cards have the ability to pull double duty, as it were. NVIDIA’s Tesla line is where DP floating point is key. It is just a rather wide gap between the two lineups that the K6000 somewhat closes, fortunately. I would have really liked to see the K6000 have at least 14 SMX units, to match consumer Titan and the Tesla K20X, but rumors are not looking positive in that regard. Professionals should expect to see quite the premium with the K6000 versus the Titan, despite the hardware differences. It will likely be sold for around $3,000.
No word on availability, but the card will likely be released soon in order to complete the Kepler Quadro lineup update.
TITAN up your ... you know
Subject: Graphics Cards | February 21, 2013 - 12:57 PM | Jeremy Hellstrom
Tagged: titan, nvidia, kepler, gtx titan, gk110, geforce
Before getting into the performance of the $1000 NVIDIA TITAN it is worth looking at the improvements NVIDIA has added to this GK110 beast. At 10.5" long it is a half inch longer than a 680 and a full 1.5" shorter than a 690, which allows it to fit in a wider variety of cases and the vastly improved thermals allow the usage of much smaller cases than other high end GPUs can manage without exotic cooling solutions. There is also a reduction in noise generated, to the point where SLI'd TITANs run quieter than some single card solutions, not to mention much faster. To take a look at just how much faster you can see [H]ard|OCP's results which you can compare to Ryan's results.
"NVIDIA is launching a TITAN today, literally, the new GeForce GTX TITAN video card is here, and we have a lot to talk about. We test single-GPU and 2-way SLI today, with more to follow later. We will find out if this TITAN of a video card really is worth it, and just who this video card is designed for. Be prepared to face the fastest single-GPU video card."
Here are some more Graphics Card articles from around the web:
- Nvidia's GeForce GTX Titan @ The Tech Report
- NVIDIA GTX TITAN @ Overclockers.com
- NVIDIA’s GeForce GTX Titan Review, Part 2: Titan's Performance Unveiled @ AnandTech
- NVIDIA GeForce GTX Titan Gaming Review @ OCC
- NVIDIA GeForce GTX TITAN 6GB Performance Review @ Hardware Canucks
- NVIDIA GeForce GTX TITAN 6 GB @ techPowerUp
- NVIDIA GeForce GTX TITAN SLI & Tri-SLI @ techPowerUp
- MSI GTX 670 Twin Frozr Power Edition OC 2GB @ Tweaktown
- Desktop Graphics Card Comparison Guide @ TechARP
- HIS Radeon HD 7850 iPower IceQ Turbo 4GB Crossfire @ Legion Hardware
TITAN is back for more!
Our NVIDIA GeForce GTX TITAN Coverage Schedule:
- Tuesday, February 19 @ 9am ET: GeForce GTX TITAN Features Preview
- Thursday, February 21 @ 9am ET: GeForce GTX TITAN Benchmarks and Review
- Thursday, February 21 @ 2pm ET: PC Perspective Live! GTX TITAN Stream
If you are reading this today, chances are you were here on Tuesday when we first launched our NVIDIA GeForce GTX TITAN features and preview story (accessible from the link above) and were hoping to find benchmarks then. You didn't, but you will now. I am here to show you that the TITAN is indeed the single fastest GPU on the market and MAY be the best graphics cards (single or dual GPU) on the market depending on what usage models you have. Some will argue, some will disagree, but we have an interesting argument to make about this $999 gaming beast.
A brief history of time...er, TITAN
In our previous article we talked all about TITAN's GK110-based GPU, the form factor, card design, GPU Boost 2.0 features and much more and I would highly press you all to read it before going forward. If you just want the cliff notes, I am going to copy and paste some of the most important details below.
From a pure specifications standpoint the GeForce GTX TITAN based on GK110 is a powerhouse. While the full GPU sports a total of 15 SMX units, TITAN will have 14 of them enabled for a total of 2688 shaders and 224 texture units. Clock speeds on TITAN are a bit lower than on GK104 with a base clock rate of 836 MHz and a Boost Clock of 876 MHz. As we will show you later in this article though the GPU Boost technology has been updated and changed quite a bit from what we first saw with the GTX 680.
The bump in the memory bus width is also key, being able to feed that many CUDA cores definitely required a boost from 256-bit to 384-bit, a 50% increase. Even better, the memory bus is still running at 6.0 GHz resulting in total memory bandwdith of 288.4 GB/s.
Speaking of memory - this card will ship with 6GB on-board. Yes, 6 GeeBees!! That is twice as much as AMD's Radeon HD 7970 and three times as much as NVIDIA's own GeForce GTX 680 card. This is without a doubt a nod to the super-computing capabilities of the GPU and the GPGPU functionality that NVIDIA is enabling with the double precision aspects of GK110.
GK110 Makes Its Way to Gamers
Our NVIDIA GeForce GTX TITAN Coverage Schedule:
- Tuesday, February 19 @ 9am ET: GeForce GTX TITAN Features Preview
- Thursday, February 21 @ 9am ET: GeForce GTX TITAN Benchmarks and Review
- Thursday, February 21 @ 2pm ET: PC Perspective Live! GTX TITAN Stream
Back in May of 2012 NVIDIA released information on GK110, a new GPU that the company was targeting towards HPC (high performance computing) and the GPGPU markets that are eager for more processing power. Almost immediately the questions began on when we might see the GK110 part make its way to consumers and gamers in addition to finding a home in supercomputers like Cray's Titan system capable of 17.59 Petaflops/s.
Watch this same video on our YouTube channel
Nine months later we finally have an answer - the GeForce GTX TITAN is a consumer graphics card built around the GK110 GPU. Comprised of 2,688 CUDA cores, 7.1 billion transistors and with a die size of 551 mm^2, the GTX TITAN is a big step forward (both in performance and physical size).
From a pure specifications standpoint the GeForce GTX TITAN based on GK110 is a powerhouse. While the full GPU sports a total of 15 SMX units, TITAN will have 14 of them enabled for a total of 2688 shaders and 224 texture units. Clock speeds on TITAN are a bit lower than on GK104 with a base clock rate of 836 MHz and a Boost Clock of 876 MHz. As we will show you later in this article though the GPU Boost technology has been updated and changed quite a bit from what we first saw with the GTX 680.
The bump in the memory bus width is also key, being able to feed that many CUDA cores definitely required a boost from 256-bit to 384-bit, a 50% increase. Even better, the memory bus is still running at 6.0 GHz resulting in total memory bandwdith of 288.4 GB/s.
Continue reading our preview of the brand new NVIDIA GeForce GTX TITAN graphics card!!
Podcast #235 - AMD Hardware in the PS4, a GK110 NVIDIA product, Corsair 200R case and more!
Subject: General Tech | January 24, 2013 - 03:31 PM | Ken Addison
Tagged: video, titan, ps4, podcast, nvidia, kavari, Kabini, H80i, gk110, GCN, corsair, APU, amd, 200r
PC Perspective Podcast #235 - 01/24/2013
Join us this week as we discuss potential AMD Hardware in the PS4, a GK110 NVIDIA product, Corsair 200R case 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 Malventano
This Podcast is brought to you by MSI!
Program length: 1:16:39
Podcast topics of discussion:
- Week in Reviews:
- 0:13:35 This Podcast is brought to you by MSI!
-
News items of interest:
- 0:15:15 Corsair Launches 140mm and 280mm coolers
- 0:17:50 Catalyst 13.1 drivers released
- 0:19:30 SimCity Beta Weekend
- 0:25:00 NVIDIA GK110 Titan Rumored for February
- 0:30:50 Intel to exit motherboard business after Haswell
- 0:38:00 But ASUS says its okay...
- 0:41:30 PS4 Hardware discussion
-
Closing:
-
Hardware / Software Pick of the Week
- Ryan: Pegasus R4 with Thunderbolt
- Jeremy: Not since the Sumosac has there been something more sure to get you the ladies!
- Josh: Just built a machine with one of these
- Allyn: Zip Snip ($20 at Lowes)
-
Hardware / Software Pick of the Week
- 1-888-38-PCPER or podcast@pcper.com
- http://pcper.com/podcast
- http://twitter.com/ryanshrout and http://twitter.com/pcper
- Closing/outro
Be sure to subscribe to the PC Perspective YouTube channel!!
Rumor: NVIDIA GK110 based GeForce GPU 'Titan' to be released late February
Subject: Graphics Cards | January 22, 2013 - 02:44 PM | Ryan Shrout
Tagged: nvidia, geforce, gk110, titan, rumor
A combination of rumors and news pieces found online and in some recent conversations with partners indicates that February will see the release of a new super-high-end graphics card from NVIDIA based on the GK110 GPU. Apparently using the name "Titan" based on a report from Sweclockers.com, this new single GPU card will feature 2688 CUDA cores, compared to the 1536 in the GeForce GTX 680.
If true, the name Titan likely refers to the Cray super computer of the same name built using GK110 Kepler Tesla cards. Sweclockers.com's sources are quoted with the clocks of this new super-GPU as well: 732 MHz core clock and 5.2 GHz GDDR5 memory clock. While those numbers are low compared to the 1000+ MHz speeds of the GK104 parts out today, this GPU would have 75% more compute units and presumably additional memory capacity as well. The memory bus width of 384-bits is a 50% increase as well which would indicate another big jump in performance over current cards. The CUDA core count of 2688 is actually indicative of a GK110 GPU with a single SMX disabled as well.
The NVIDIA Titan card will apparently be the replacement for the GeForce GTX 690, a dual-GK104 card launched in May of last year. The performance estimate for the Titan is approximately 85% of that GTX 690 and if the rumors are right it would see an $899 price tag.
Based on other conversations I have had recently you should only expect those same partners that were able to sell the GTX 690 to stock this new GK110-based part. There won't be any modifications and you will see very little differentiation between vendors branding on it. If dates are to be believed, we are hearing that a Feb 25th (or at least that week) launch is the current target.
NVIDIA Launches Maximus 2.0, Combining Kepler and Tesla
Subject: General Tech, Graphics Cards | August 10, 2012 - 05:34 AM | Tim Verry
Tagged: tesla, quadro, nvidia, maximus, kepler, gk110
At SIGGRAPH 2012 NVIDIA announced a refresh of its Maximus workstation platform technology. Maximus is a technology aimed at professionals that work with simulations or content creation and editing. The updated platform features a Tesla K20 accelerator card as well as a Kepler-based NVIDIA Quadro K5000 graphics card. The K5000 in particular has 4GB of GDDR5 memory on a 256-bit bus and 1536 CUDA cores. NVIDIA states that the Quadro graphics card has 2.1 Teraflops of single precision compute power and draws 122 watts.
The K20 on the other hand features a GK110 Kepler GPU with Dynamic Parallelism and Hyper Q features that reportedly enable more than 1 Teraflop of peak double precision performance. Unfortunately, we do not know much more than that on the new K20 Tesla card as the exact specifications are still listed as “to be announced.” It is slated for a Q4 2012 release.
The Quadro K5000 workstation GPU
Beyond the hardware itself, the company’s Maximus platform has received software support from several high-profile software companies and system integrators. Some of the companies that certify and support Maximus are Adobe, Autodesk, Mathworks, and Paradigm among others. Dell, Fujitsu, HP, Lenovo, and Supermicro are OEMs that support the hardware and manufacture Maximus-powered workstations.
The Tesla K20 accelerator card.
The second-generation Maximus technology will be available in desktop workstations as early as December 2012. Further, the NVIDIA Quadro K5000 will be available for purchase as a separate discrete card in October 2012 for $2,249 (MSRP). The Tesla K20 will (for now) only be available integrated in a workstation, but NVIDIA lists the MSRP at $3,199.
More information on the NVIDIA Maximus refresh can be found in the company’s press release.
NVIDIA's big chip, the GK110
Subject: General Tech | May 25, 2012 - 11:28 AM | Jeremy Hellstrom
Tagged: nvidia, kepler, GTC 2012, gk110
We at PC Perspective were not the only ones who became a wee bit excited when we had the news from NVIDIA about what the GK110 Kepler chip is going to be capable of. The chip will be powering professional HPC systems with the Telsa K20 board which will deliver over a teraflop of double precision processing power. That precision is not so important to the proper rendering of fluid dynamics in the underground water of Crysis 2 but for scientists trying to model the real world it is double what they say from the previous generation of Fermi based Tesla boards. Check out The Tech Report as they delve into how NVIDIA tweaked their new architecture to deal with new choke points and the compute enhancements they've added.
"At its 2012 GPU Technology Conference, Nvidia revealed plenty of details about the biggest GPU of its Kepler generation. Here's what you need to know."
Here is some more Tech News from around the web:
- Grab your iron and add GameCube back to the Wii @ Hack a Day
- Have Internet, will travel @ The Tech Report
- GeIL Taipei Factory Tour - We almost broke an IC Testing Machine @ Tweaktown
- MSI GT70 Ivy Bridge Gaming Notebook Giveaway @ AnandTech
Podcast #202 - GTX 670, NVIDIA's GK110 Tesla card, our AMD Trinity Mobile review and more!
Subject: General Tech | May 17, 2012 - 03:16 PM | Ken Addison
Tagged: trinity, tesla, podcast, nvidia, kepler, gtx670, GTC 2012, gk110, GK104, dv nation, a10
PC Perspective Podcast #202 - 05/17/2012
Join us this week as we talk about the GTX 670, NVIDIA's GK110 Tesla card, our AMD Trinity Mobile review and more!
If you want even more PC Perspective this, check out our "aftershow" event as well. Event might be an over-statement though...
You can subscribe to us through iTunes and you can still
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: Jeremy Hellstrom, Josh Walrath, and Allyn Malvantano
Program Schedule:
- 0:00:21 Introduction
- 1-888-38-PCPER or podcast@pcper.com
- http://pcper.com/podcast
- http://twitter.com/ryanshrout and http://twitter.com/pcper
- 0:01:15 NVIDIA GeForce GTX 670 2GB Graphics Card Review - Kepler for $399
- 0:11:20 Graphics Card (GPU) Stock Check - May 10th, 2012
- 0:14:25 NVIDIA Reveals GK110 GPU - Kepler at 7.1B Transistors, 15 SMX Units
- 0:20:20 Lenovo IdeaCentre Q180: Atom's Wake
- 0:24:30 AMD A10-4600M Trinity For Mobile Review: Trying To Cut The Ivy
- 0:33:40 Just Delivered: DV Nation RAMRod PC - Sandy Bridge-E, 64GB DDR3, 480GB RevoDrive 3 X2
- 0:35:42 Plug and Pray PCIe SSD that you can upgrade; OWC's Mercury Accelsior
- 0:40:40 GTC 2012: NVIDIA Announces GeForce GRID Cloud Gaming Platform
- 0:53:00 ZOTAC announces ZOTAC GeForce GT 630, GT 620 and GT 610 series
- 0:55:00 Hardware / Software Pick of the Week
- Jeremy: Only to be used for evil
- Josh: Since NV doesn't have an answer yet at this price range...
- Allyn: If you need your files secure - without the destruction
- 1-888-38-PCPER or podcast@pcper.com
- http://pcper.com/podcast
- http://twitter.com/ryanshrout and http://twitter.com/pcper
- Closing
GK110 Specifications
When the Fermi architecture was first discussed in September of 2009 at the NVIDIA GPU Technology Conference it marked an interesting turn for the company. Not only was NVIDIA releasing details about a GPU that wasn’t going to be available to consumers for another six months, but also that NVIDIA was building GPUs not strictly for gaming anymore – HPC and GPGPU were a defining target of all the company’s resources going forward.
Kepler on the other hand seemed to go back in the other direction with a consumer graphics release in March of this year without discussion of the Tesla / Quadro side of the picture. While the company liked to tout that Kepler was built for gamers I think you’ll find that with the information NVIDIA released today, Kepler was still very much designed to be an HPC powerhouse. More than likely NVIDIA’s release schedules were altered by the very successful launch of AMD’s Tahiti graphics cards under the HD 7900 brand. As a result, gamers got access to GK104 before NVIDIA’s flagship professional conference and the announcement of GK110 – a 7.1 billion transistor GPU aimed squarely at parallel computing workloads.
Kepler GK110
With the Fermi design NVIDIA took a gamble and changed directions with its GPU design betting that it could develop a microprocessor that was primarily intended for the professional markets while still appealing to the gaming markets that have sustained it for the majority of the company’s existence. While the GTX 480 flagship consumer card and the GTX 580 to some degree had overheating and efficiency drawbacks for gaming workloads compared to AMD GPUs, the GTX 680 based on Kepler GK104 has improved on them greatly. NVIDIA has still designed Kepler for high-performance computing though with a focus this time on power efficiency as well as performance though we haven’t seen the true king of this product line until today.
GK110 Die Shot
Built on the 28nm process technology from TSMC, GK110 is an absolutely MASSIVE chip built on 7.1 billion transistors and though NVIDIA hasn’t given us a die size, it is likely coming close the reticle limit of 550 square millimeters. NVIDIA is proud to call this chip the most ‘architecturally complex’ microprocessor ever built and while impressive, it means there is potential for some issues when it comes to producing a chip of this size. This GPU will be able to offer more than 1 TFlop of double precision computing power with greater than 80% efficiency and 3x the performance per watt of Fermi designs.
Continue reading our overview of the newly announced NVIDIA Kepler GK110 GPU!
PC Perspective Upcoming Events
|
