Subject: Graphics Cards | January 7, 2015 - 03:51 PM | Sebastian Peak
Tagged: nvidia, notebook, mobile graphics, mobile gpu, GeForce 965M
With zero fanfare NVIDIA has released a new mobile graphics chip today, the GeForce GTX 965M.
Based on the 28nm Maxwell GM204 core and positioned just below the existing GTX 970M, the new GTX 965M has 1024 CUDA cores (compared to the 970M's 1280) and the new 965M has a lower 128-bit memory interface (vs 192-bit with the 970M). The base clock is slightly faster at 944 MHz (plus unspecified Boost headroom).
Compared with the flagship GTX 980M which boasts 1536 CUDA cores and 256-bit GDDR5 this new GTX 965M will be a significantly lower performer, but NVIDIA is marketing it towards 1080p mobile gaming. At a lower cost to OEMs the 965M should help create some less expensive 1080p gaming notebooks as the new GPU is adopted.
The chip features proprietary NVIDIA Optimus and Battery Boost support, and is GameStream, ShadowPlay, and GameWorks ready.
Specs from NVIDIA:
- CUDA Cores: 1024
- Base Clock: 944 MHz + Boost
- Memory Clock: 2500 MHz
- Memory Interface: GDDR5
- Memory Interface Width: 128-bit
- Memory Bandwidth: 80 GB/sec
- DirectX API: 12
- OpenGL: 4.4
- OpenCL: 1.1
- Display Resolution: Up to 3840x2160
More information on this new mobile GPU can be found via the source link.
Subject: General Tech | September 24, 2014 - 04:56 PM | Jeremy Hellstrom
Tagged: amd, nvidia, hp, dell, asus, acer, toshibe, mobile gpu
The growing market of low cost $200 to $400 10" to 15" laptops is expected to cut into the sales of AMD and NVIDIA's mobile GPUs as they are forced to focus more on higher end models. That is a much smaller market and the margins generally favour the laptop vendor as opposed to the company providing the mobile GPU. This will be felt more strongly by NVIDIA as AMD's APU lineup will appear in the smaller and less expensive notebooks but will still have an effect on AMD's bottom line over the coming quarters. DigiTimes also mentioned that AMD's R9 390X is due out in the first half of 2015 and that both companies are currently reducing the price of their GPUs in the hopes of increasing their sales volumes on the desktop.
"Notebook vendors including Hewlett-Packard (HP), Dell, Lenovo, Asustek Computer, Acer and Toshiba, will launch low-cost models with CPUs with integrated graphics in the fourth quarter of 2014 and therefore AMD and Nvidia are expected to see demand for their discrete mobile GPUs decrease, according to Taiwan-based supply chain makers."
Here is some more Tech News from around the web:
- The TR Podcast 162: Apple's biggest and Nvidia's fastest
- Adobe swallows Aviary, hopes to stuff Creative Cloud into mobes @ The Register
- Blackberry Passport arrives, claims to outperform the iPhone 6 and Galaxy S5 @ The Inquirer
- ARM gives Internet of Things a PIECE of its MIND – the Cortex-M7 @ The Register
- Why the Convergent Desktop is So Important to Linux @ Linux.com
- Le whoops! Microsoft France boss blows lid off 'Windows 9' event @ The Register
- Microsoft to cut Windows 7 OEM supply on 31 October @ The Inquirer
Subject: Mobile | September 9, 2014 - 07:45 PM | Sebastian Peak
Tagged: mobile gpu, mobile cpu, mobile, iphone 6 plus, iphone 6, iphone, apple, 5.5, 4.7
Today Apple finally catches up with the current smartphone industry as they announce not just a new iPhone, but two new phones - both with much larger screens.
Image credit: Apple, Inc.
In 2007 Steve Jobs proclaimed that the just-announced iPhone was five years ahead of the competition. In many ways, he was correct - though by 2012 the market had more than caught up. In fact, Apple was behind when they announced the 4-inch iPhone 5, which managed to tick the larger-screen checkbox by simply increasing the vertical resolution by 100 pixels or so. In the area of the "phablet" the iterative refresh that followed in 2013 was hardly news, and Samsung, LG, and HTC busied themselves with larger, higher-resolution offerings that made the iPhone look tiny in comparison.
Image credit: The Verge
The new iPhone 6 features a smooth (and widely leaked) design with a thin profile and rounded corners, and the expected 4.7-inch screen. However this screen is a disappointing (and very odd) 1334x750 resolution. Contrast the Nexus 5’s 4.95-inch 1080p screen, which represents what has simply become an industry standard for smartphones in the 5-inch range.
But the bigger news here (literally) is the announcement of the iPhone 6 Plus. This 5.5-inch phone has a full 1920x1080 resolution, and there are UI tweaks to iOS 8 that are only enabled on this larger version, such as an expanded landscape keyboard and horizontal home screen. The Plus also features a better camera than its 4.7-inch sibling, with optical image stabilization (OIS) implemented along with the same new image sensor.
Speaking of the image sensor, which is “all-new” according to Apple, the next-gen 8 MP iSight camera has same 1.5(micron) pixel size as before, f/2.2 aperture. True Tone flash returns, and the new camera also boasts faster “phase detection” autofocus. The image signal processor in the A8 chip is also custom designed by Apple. Another change is video slo-mo support, with up to 240fps capture.
Image credit: The Verge
The A8 itself is a second generation 64-bit chip, with 2 billion transistors on a 20nm process. This is 13% smaller than the A7, and Apple claims a 20% faster CPU, 50% faster graphics than its predecessor. Apple is also placing emphasis on sustained performance with this new chip, showcasing graphs with maintained speed within their thermal envelope during extended use. This is accompanied by the new M8 motion coprocessor, which adds new functionality for motion applications (just in time for iOS 8).
Image credit: The Verge
The screen is ion-strengthened glass (no sapphire here) with an “improved polarizer", and photo-aligned IPS LCD technology. Whatever that is. If you're interested, Sharp previously published a paper with technical details on this technology here (PDF).
Image credit: Apple, Inc.
The phones are thin, too. The iPhone 6 is 6.9mm thick, and the 6 Plus is only slightly thicker at 7.1mm.
As far as wireless communication goes, these new iPhones feature 20 bands of LTE as well as VoLTE support, and 802.11ac Wi-Fi. And Apple users can get ready to start waving their phone wildly at checkout as NFC payments come to the iPhone via “Apple Pay”. Some 22,000 retailers will work with it (it seems to be using conventional wireless credit card infrastructure).
The battery life should be improved with both phones compared to the current iPhone 5S, and particularly so with the larger iPhone 6 Plus. Apple is claiming up to 24 hours of 3G talk time and 12 hours of LTE browsing on the 5.5-inch phone, along with a 16 day standby.
The iPhone 6 and iPhone 6 Plus will be available September 19, with the 16GB versions starting at $199 and $299 respectively with a 2-year contract. Of note, while the entry-level capacity remains at just 16GB, the next model for both phones jumps to 64GB for an additional $100 each.
Subject: General Tech, Graphics Cards, Mobile | July 19, 2014 - 07:29 AM | Scott Michaud
Tagged: nvidia, geforce, maxwell, mobile gpu, mobile graphics
Apparently, some hardware sites got their hands on an NVIDIA driver listing with several new product codes. They claim thirteen N16(P/E) chips are listed (although I count twelve (??)). While I do not have much knowledge of NVIDIA's internal product structure, the GeForce GTX 880M, based on Kepler, is apparently listed as N15E.
Things have changed a lot since this presentation.
These new parts will allegedly be based on the second-generation Maxwell architecture. Also, the source believes that these new GPUs will in the GeForce GTX 800-series, possibly with the MX suffix that was last seen in October 2012 with the GeForce GTX 680MX. Of course, being a long-time PC gamer, the MX suffix does not exactly ring positive with my memory. It used to be the Ti-line that you wanted, and the MX-line that you could afford. But who am I kidding? None of that is relevant these days. Get off my lawn.
Subject: General Tech | January 16, 2014 - 04:56 AM | Tim Verry
Tagged: r9 m290x, r7 m265, r5 m230, mobile gpu, GCN, amd
AMD recently took the wraps off of its latest mobile GPU series in the form of the R5 M200, R7 M200, and R9 M200 series. Currently, there is one GPU in each respective Rx M200 series including the AMD Radeon R5 M230, R7 M265, and R9 M290X. Do not get too excited, however. All of the new mobile GPUs are based on desktop versions of Volcanic Islands and not AMD's new Hawaii GPUs. As such, the Rx M200 series are essentially rebrands of the Radeon HD 8000M series (which was in turn OEM rebrands of the HD 7000M series) based around AMD's Graphics Core Next 1.0 architecture and specifically the Pitcairn GPU implementation.
All of the Rx M200 series support DirectX 11.2 Tier 1, up to 4GB GDDR5 memory, and at least 320 GCN shader cores. Informatin on the mid-range R7 M265 is scarce, but AMD has released information on the low and high end chips. Further, Computer Base has managed to put together specifications for the R5 M230 and R9 M290X. In short, the R5 M230 is a rebranded HD 8570 with higher clockspeeds and support for more memory while the R9 M290X is a rebranded HD 8970M with official support for DirectX 11.2 Tier 1 (the HD8970M technically supports it as well). A more detailed breakdown is as follows.
The R9 M290X features 1280 shaders clocked at 850MHz/900MHz (base/boost), 80 texture units, and 32 ROPs. OEMs can pair the GPU with up to 4GB of GDDR5 memory clocked at 1,200 MHz on a 256-bit bus.
The R5 M230 has 320 shaders clocked at 855MHz, 20 texture units, and 4 ROPs. This GPU can support up to 4GB of GDDR5 memory at 1,000MHz over a 64-bit bus.
Users will be able to get the new Rx M200 series graphics cards in mobile systems from Alienware, Clevo, Lenovo, and MSI. Other manufactures should pick up the new GPUs soon as well. The new series is not terribly exciting being nearly identical to the existing HD 8000M counterparts, but it does update the lineup to AMD's new naming and branding scheme. Notably, should AMD release a Hawaii-based mobile GPU, it has not left itself much room as far as naming goes (R9 M295X?).
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.
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: Mobile | February 25, 2012 - 02:31 PM | Tim Verry
Tagged: ti, qualcomm, nvidia, mobile gpu, jpr, apple
The researchers over at Jon Peddie Research pushed out their results yesterday for shipments of mobile GPUs in SoC (system on a chip) platforms, and they found some interesting results. The article covers the number of shipments by the major players in the mobile device GPU space and uses those numbers to estimate the amount of market share each of the companies has using an average of all the four quarter shipment numbers. Further, they found that from Q1 2011 to Q4 2011, the number of mobile device GPUs shipped by all manufacturers had a CAGR (compound annual growth rate) of 18%. That's a fairly impressive growth rate that shows the smartphone and tablet hardware market is continuing to steadily grow.
In terms of market share, at the end of 2011 Qualcomm was leading the pack with 31.4%, and the only other manufacturer to come close to that number was Apple with 22.7%. The little Adreno GPU by Qualcomm was obviously a popular choice last year!
To make things even more interesting, they note that although Qualcomm has the highest shipment rates, it was Samsung who enjoyed the highest CAGR with a 39% growth rate (bringing them up from 9.2% in Q1 to 14.9% in Q4). Apple then followed behind Samsung's numbers with 26% CAGR. Finally, Qualcomm had the lowest percentage growth rate but maintained the highest number of shipments.
The table below shows off the relative market share for the major SoC mobile device manufacturers, as provided by Jon Peddie Research.
They further state that the mobile GPU war is really heating up, especially between Samsung, Apple, and Qualcomm, and I tend to agree. This area of the technology market is seeing some very impressive growth and is really booming as mobile GPU SoCs are continuously released and they are getting more powerful each iteration. It is an area that has a lot of competition and is growing rapidly, much like desktop computers did 10 to 20 years ago when personal computers really started to be affordable and powerful enough to take over the world (well, market share wise).
Another interesting point about the marketshare results in that of NVIDIA's shipments. With all the marketing behind the Tegra SoC and its popularity in high end smartphones and tablets, I was under the impression that they had a lot more marketshare than they do such that when I first saw the JPR chart, I did a double take and had to be sure I read them correctly! It will be interesting to see how they do this year and whether they will start to see increased growth.
It will be interesting to see if Samsung can catch up to Qualcomm and whether or nor Qualcomm will still be the heavyweight champion by 2012. Nvidia is still just breaking into this market but they have a very powerful GPU, so it will be interesting to see just how much they manage to grow this year. What are your thoughts on these numbers? How do you think things will unfold this year? Let us know in the comments below!
Subject: General Tech | December 7, 2011 - 05:25 PM | Jeremy Hellstrom
Tagged: amd, mobile gpu, 7400M, 7500M, 7600M, nvidia, GT635M, GT630M, 610M, turks, Caicos, GF106, GF108, GF119
Before you start to get too excited when you read about the AMD Radeon 7000M announcement today; realize this is a rebranding of Turks and Caicos, not the arrival of Southern Islands. While AMD might disappoint, at least the performance of the chips has been increased; NVIDIA went for a straight rebadge. Even if you squint, the stats for the GT630M are the same as the GT540M and same with the 610M and 520MX. There looks to be a slight difference in memory bandwidth between the 635M and 555M but AnandTech is doubtful that it is truly the case.
While we still don't know the exact frequencies that the so called 7000M chips will have in the end, they will be higher than the parts that they replace and will come in two flavours. The less expensive part will be DDR3, with a DDR5 alternative for those who want a bit more performance. Read on for all the gritty details or just look at the tables below.
"We just covered the AMD side of things, but yesterday NVIDIA quietly refreshed their entry-level and midrange mobile GPUs in a similar manner. We weren’t briefed on the updates, most likely because there’s not much to say. Like AMD there are three "new" 600M parts. Here’s the overview of what NVIDIA is offering, with the previous generation equivalents listed for reference."
Here is some more Tech News from around the web:
- AMD Launches the HD 7000M; Mobile Market Déjà Vu? @ Hardware Canucks
- Windows 8 beta coming in February, too late for a final release in 2012? @ ExtremeTech
- Physical computing just got a lot easier @ Hack a Day
- Intel, Micron double single-chip flash capacity @ The Register
- US military pays SETI to check Kepler-22b for aliens @ The Register
- Military contractor warns of new Adobe Reader exploit @ The Register
- Sunwayman V20C T6 Tactical Flashlight @ 3DVelocity
- SteelSeries Desmo Digital Eyewear @ Benchmark Reviews
- Ars Technica's 2011 holiday gift guide extravaganza