The Kepler Architecture
Join us today at 12pm EST / 9am CST as PC Perspective hosts a Live Review on the new GeForce GTX 680 graphics card. We will discuss the new GPU technology, important features like GPU Boost, talk about performance compared to AMD's lineup and we will also have NVIDIA's own Tom Petersen on hand to run some demos and answer questions from viewers. You can find it all at http://pcper.com/live!!
NVIDIA fans have been eagerly waiting for the new Kepler architecture ever since CEO Jen-Hsun Huang first mentioned it in September 2010. In the interim, we have seen the birth of a complete lineup of AMD graphics cards based on its Southern Islands architecture including the Radeon HD 7970, HD 7950, HD 7800s and HD 7700s. To the gamer looking for an upgrade it would appear that NVIDIA had fallen behind; but the company is hoping that today's release of the GeForce GTX 680 will put them back in the driver's seat.
This new $499 graphics card will directly compete against the Radeon HD 7970, and it brings quite a few "firsts" to NVIDIA's lineup. This NVIDIA card is the first desktop 28nm GPU, the first to offer a clock speed over 1 GHz, the first to support triple-panel gaming on a single card, and the first to offer "boost" clocks that vary from game to game. Interested yet? Let's get to the good stuff.
The Kepler Architecture
In many ways, the new 28nm Kepler architecture is just an update to the Fermi design that was first introduced in the GF100 chip. NVIDIA's Jonah Alben summed things up pretty nicely for us in a discussion stating that "there are lots of tiny things changing (in Kepler) rather than a few large things which makes it difficult to tell a story."
GTX 680 Block Diagram
Subject: General Tech | March 20, 2012 - 01:12 PM | Jeremy Hellstrom
Tagged: TSMC, nvidia, amd, southern islands, kepler, 28nm, maxwell, llano
TSMC's 28nm process has been in the news for a long time, sometimes this was a good thing but more often it was not. Back in May of 2009 the first announcements of TSMC's brand new 28nm process hit the news with major production slated to start in early 2010. That didn't happen on time, much to several companies dismay as Josh unhappily discussed towards the end of 2010. This set a trend for TSMC's 28nm process for a while, for instance AMD did not quite meet their promise of readily available 28nm GPUs in 2011, though a late December launch for the HD7970 did meet the spirit of the agreement. The delays and issues on TSMC's 28nm lines had a variety of causes, perhaps one of the worst being TSMC's overly optimistic attitude about their production capabilities especially when AMD had a surprise for them. Add to that the long line of woes during the development and production of NVIDIA's 28nm Kepler GPU as well as the recent shutdown of the production line, and you can see why TSMC's 28nm process has spent a lot of time being maligned in the news. It almost makes you forget about the 40nm process woes, but that is ancient news.
All that effort is not going to waste as DigiTimes reports that TSMC is planning on expanding their 28nm capacity this year and expects that process to account for 10% of their 2012 revenue. The next question on most peoples minds is the progress on TSMC's 22nm process which in 2010 they announced would be ready by Q3 2012, something which NVIDIA's Maxwell team is probably anticipating with great anxiety.
"With current capacity for 28nm processes filled up, Taiwan Semiconductor Manufacturing Company (TSMC) is likely to expand the leading-edge process capacity later in 2012, according to industry sources.
TSMC reportedly is running at full capacity at its 12-inch fabs due to strong orders for 28nm as well as 40nm and 65nm designs. In order to avoid orders to rivals such as United Microelectronics (UMC) and Samsung Electronics, TSMC will have to speed up the pace of its leading-edge capacity expansion in particular its 28nm capacity, the sources said."
Here is some more Tech News from around the web:
- AMD releases single-processor AM3+ Opteron 3200-series chips @ The Inquirer
- D-Wave Announces Commercially Available Quantum Computer @ Slashdot
- Intel launches over 100 Xeon E5-2600 motherboard and chassis SKUs @ The Inquirer
- ARM's ultra-low-power fridge-puter chips: Just what the CIA ordered @ The Register
- Windows 8 to debut on both x86 and ARM devices in October, report says @ Ars Technica
- Interview with XFX Sales VP Cy Brown @ Kitguru
- Windows 8 tablet freezes in Microsoft keynote demo @ The Register
- Samsung shows 14nm and 20nm wafers @ SemiAccurate
- ASUS Masters of Overclocking Competition 2012 UK with HardwareHeaven
Subject: General Tech | March 15, 2012 - 01:28 PM | Ryan Shrout
Tagged: podcast, nvidia, kepler, Ivy Bridge, Intel, amd
PC Perspective Podcast #193 - 03/15/2012
Join us this week as we talk about our Kepler Mobile preview, GTX 680 Rumors, Zenbook talk and more!
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
- 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
- 1-888-38-PCPER or firstname.lastname@example.org
- http://twitter.com/ryanshrout and http://twitter.com/pcper
- NCAA 2012: PC Perspective Bracket Competition!!
- HP dm4t Beats Edition Notebook Review: Branding Gone Wild
- Nvidia GeForce GT 640M Review: Kepler Arrives For Mobile
- Unreal Engine Samaritan Demo Running On Single NVIDIA Kepler GPU
- Alleged NVIDIA GK104 Kepler GTX 670 Ti Photo Leaked
- GTX 680, Turbo Cores, and Cuda Cores!
- A possible GTX 680 specs leak?
- Asus Updating Zenbook Line With UX31A and UX21A Ultrabooks
- Lian Li Releases Official Photos of PC-QO5 Case
- The new MAINGEAR Solo all-in-one PC series
- ARM Cortex-MO+ Lowest Power Processor Yet At 9µA/MHz
- Give me a Marauder MAD-5M with original armour and I am good to go
- Hardware / Software Pick of the Week
- 1-888-38-PCPER or email@example.com
- http://twitter.com/ryanshrout and http://twitter.com/pcper
Introduction, GT 640M Basics
About two months ago I wrote an less than enthusiastic editorial about ultrabooks that pointed out several weaknesses in the format. One particular weakness in all of the products we’ve seen to date is graphics performance. Ultrabooks so far have lacked the headroom for a discrete graphics component and have instead been saddled with a low-performance version of the already so-so Intel HD 3000 IGP.
This is a problem. Ultrabooks are expensive, yet they so far are less capable of displaying rich 3D graphics than your typical smartphone or tablet. Casual gamers will notice this and take their gaming time and dollars in that direction. Early leaked information about Ivy Bridge indicates that there has been a substantial increase in graphics capability, but the information available so far is centered on the desktop. The version that will be found in ultrabooks is unlikely to be as quick.
Today we’re looking at a potential solution - the Acer Aspire Timeline Ultra M3 equipped with Nvidia’s new GT 640M GPU. This is the first laptop to launch with a Kepler based GPU. It is also an ultrabook, albeit it one with a 15.6” display. Otherwise, it isn’t much different from other products on the market, as you can see below.
This is likely to be the only Kepler based laptop on the market for a month or two. The reason for this is Ivy Bridge - most of the manufacturers are waiting for Intel’s processor update before they go to the trouble of designing new products.
Subject: Editorial | March 9, 2012 - 11:45 AM | Josh Walrath
Tagged: TSMC, tahiti, process node, nvidia, kepler, amd, 28 nm
Charlie over at Semiaccurate is reporting that TSMC has closed down their entire 28 nm line. Shut down. Not running wafers. This obviously cannot be good.
Apparently TSMC stopped the entire line about three weeks ago and have not restarted it. This type of thing does not happen very often, and when it does, things are really out of whack. Going back we have heard mixed reviews of TSMC’s 28 nm process. NVIDIA was quoted as saying that yields still were not very good, but at least were better than what they experienced with their first 40 nm part (GTX 400 series). Now, part of NVIDIA’s problem was that the design was as much of an issue as the 40 nm process was. AMD at the time was churning out HD 5000 series parts at a pretty good rate, and they said their yields were within expectations.
AMD so far is one of the first customers out of the gate with a large volume of 28 nm parts. The HD 7900 series has been out since the second week of January, the HD 7700 series since mid-February, and the recently released HD 7800 series will reach market in about 2 weeks. Charlie has done some more digging and has found out that AMD has enough product in terms of finished boards and packaged chips that they will be able to handle the shutdown from TSMC. Things will get tight at the end, but apparently the wafers in the middle of being processed have not been thrown out or destroyed. So once production starts again, AMD and the other customers will not have to wait 16 to 20 weeks before getting finished product.
NVIDIA will likely not fare nearly as well. The bulk of the stoppage occurred during the real “meat and potatoes” manufacturing cycle for the company. NVIDIA expects to launch the first round of Kepler based products this month, but if production has been stopped for the past three weeks then we can bet that there are a lot of NVIDIA wafers just sitting in the middle of production. Charlie also claims that the NVIDIA launch will not be a hard one, and NVIDIA expects retail products to be available several weeks after the introduction.
The potential reasons for this could be legion. Was there some kind of toxic spill that resulted in a massive cleanup that required the entire line to be shut down? Was there some kind of contamination that was present while installing the line, but was not discovered until well after production started? Or was something glossed over during installation that ballooned into a bigger problem that just needed to be rectified (a stitch in time saves nine)?
Subject: Graphics Cards | March 8, 2012 - 06:59 PM | Josh Walrath
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.
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.
Subject: Graphics Cards | March 8, 2012 - 03:41 PM | Tim Verry
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.
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?
Quarter Down but Year Up
Yesterday NVIDIA released their latest financial results for Q4 2012 and FY2012. There was some good and bad mixed in the results, but overall it was a very successful year for NVIDIA.
Q4 saw gross revenue top $953.2 million US with a net income of $116 million US. This is about $53 million less in gross revenue and $62 million down in net income as compared to last quarter. There are several reasons as to why this happened, but the majority of it appears to be due to the hard drive shortage affecting add-in sales. Simply put, the increase in hard drive prices caused most OEMs to take a good look at the price points of the entire system, and oftentimes would cut out the add-in graphics and just use integrated.
Tegra 3 promises a 50% increase in revenue for NVIDIA this coming year.
Two other reasons for the lower than expected quarter were start of the transition to 28 nm products based on Kepler. They are ramping up production on 28 nm and slowing down 40 nm. Yields on 28 nm are not where they expected them to be, and there is also a shortage of wafer starts for that line. This had a pretty minimal affect overall on Q4, but it will be one of the prime reasons why revenue looks like it will be down in Q1 2013.
Subject: General Tech | February 16, 2012 - 12:45 PM | Jeremy Hellstrom
Tagged: nvidia, 28nm, TSMC, kepler, tegra, tegra 3
If you caught the podcast last night you would have heard Josh discussing NVIDIA's year end financial conference call, otherwise you will have to wait until the 'cast is posted later this week. Until then you can read SemiAccurate's take on the call here. There is a lot of news about NVIDIA and none of it is good, from wafer yields to chip demand nothing seems to have gone right for them. Attempting to move off of their cursed 40nm line and switching to 28nm, NVIDIA has run into big yield problems as in entire wafers having issues as opposed to just some dies being bad.
Tegra is not doing so well either, with sales of Tegra 2 dropping as we approach the release of Tegra 3, which is getting a lot of bad press. SemiAccurate refers to the chip as bloated in size as well as being downright expensive to make. Combine that with the fact that NVIDIA is lagging on A15 adoption and Samsung and Apple turning their backs on Tegra and it doesn't look good for NVIDIA's mobile plans. The one ray of sunshine is that even combined Samsung and Apple do not account for even half of smartphones on the market, so there is still room for NVIDIA and Tegra to grow.
"Nvidia seems to be so far ahead of the curve that they are experiencing problems that are unique in the industry. In their recent year end financial conference call, there was enough said to draw some very grim conclusions.
Today’s conference call was a near complete validation of all the things SemiAccurate has been saying about Nvidia. Remember when we asked if Nvidia could supply Apple? Anyone notice the part about dumping early 28nm capacity, and the disappearance of 28nm Fermi shrinks? Remember how 28nm was not an issue for Nvidia, even if their product roadmap slips said otherwise. How well does this mesh with the quotes from Jen-Hsun himself on the topic?"
Here is some more Tech News from around the web:
- Danish researchers invent 2nm components @ SemiAccurate
- Space; it’s a junkyard until the Swiss get their way @ Hack a Day
- From encryption to darknets: As governments snoop, activists fight back @ Ars Technica
- Intel to postpone mass shipments of Ivy Bridge processors @ DigiTimes
- Acer expects double ultrabook shipments in 2Q12, improving gross margin each quarter @ DigiTimes
- High Orbits and Slowlorises: understanding the Anonymous attack tools @ Ars Technica
- Samsung SCX-4728FD Multifunctional Printer @ Overclockers Online
- Norton 360 Version 6.0 Review @ TechReviewSource
- CoolerMaster MASSIVE Giveaway @ eTeknix
Subject: Graphics Cards | February 6, 2012 - 06:23 PM | Tim Verry
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|
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?
Get notified when we go live!