Subject: General Tech, Graphics Cards | March 20, 2013 - 01:47 PM | Tim Verry
Tagged: tesla, tegra 3, supercomputer, pedraforca, nvidia, GTC 2013, GTC, graphics cards, data centers
There is a lot of talk about heterogeneous computing at GTC, in the sense of adding graphics cards to servers. If you have HPC workloads that can benefit from GPU parallelism, adding GPUs gives you computing performance in less physical space, and using less power, than a CPU only cluster (for equivalent TFLOPS).
However, there was a session at GTC that actually took things to the opposite extreme. Instead of a CPU only cluster or a mixed cluster, Alex Ramirez (leader of Heterogeneous Architectures Group at Barcelona Supercomputing Center) is proposing a homogeneous GPU cluster called Pedraforca.
Pedraforca V2 combines NVIDIA Tesla GPUs with low power ARM processors. Each node is comprised of the following components:
- 1 x Mini-ITX carrier board
1 x Q7 module (which hosts the ARM SoC and memory)
- Current config is one Tegra 3 @ 1.3GHz and 2GB DDR2
- 1 x NVIDIA Tesla K20 accelerator card (1170 GFLOPS)
- 1 x InfiniBand 40Gb/s card (via Mellanox ConnectX-3 slot)
- 1 x 2.5" SSD (SATA 3 MLC, 250GB)
The ARM processor is used solely for booting the system and facilitating GPU communication between nodes. It is not intended to be used for computing. According to Dr. Ramirez, in situations where running code on a CPU would be faster, it would be best to have a small number of Intel Xeon powered nodes to do the CPU-favorable computing, and then offload the parallel workloads to the GPU cluster over the InfiniBand connection (though this is less than ideal, Pedraforca would be most-efficient with data-sets that can be processed solely on the Tesla cards).
While Pedraforca is not necessarily locked to NVIDIA's Tegra hardware, it is currently the only SoC that meets their needs. The system requires the ARM chip to have PCI-E support. The Tegra 3 SoC has four PCI-E lanes, so the carrier board is using two PLX chips to allow the Tesla and InfiniBand cards to both be connected.
The researcher stated that he is also looking forward to using NVIDIA's upcoming Logan processor in the Pedraforca cluster. It will reportedly be possible to upgrade existing Pedraforca clusters with the new chips by replacing the existing (Tegra 3) Q7 module with one that has the Logan SoC when it is released.
Pedraforca V2 has an initial cluster size of 64 nodes. While the speaker was reluctant to provide TFLOPS performance numbers, as it would depend on the workload, with 64 Telsa K20 cards, it should provide respectable performance. The intent of the cluster is to save power costs by using a low power CPU. If your sever kernel and applications can run on GPUs alone, there are noticeable power savings to be had by switching from a ~100W Intel Xeon chip to a lower-power (approximately 2-3W) Tegra 3 processor. If you have a kernel that needs to run on a CPU, it is recommended to run the OS on an Intel server and transfer just the GPU work to the Pedraforca cluster. Each Pedraforca node is reportedly under 300W, with the Tesla card being the majority of that figure. Despite the limitations, and niche nature of the workloads and software necessary to get the full power-saving benefits, Pedraforca is certainly an interesting take on a homogeneous server cluster!
In another session relating to the path to exascale computing, power use in data centers was listed as one of the biggest hurdles to getting to Exaflop-levels of performance, and while Pedraforca is not the answer to Exascale, it should at least be a useful learning experience at wringing the most parallelism out of code and pushing GPGPU to the limits. And that research will help other clusters use the GPUs more efficiently as researchers explore the future of computing.
The Pedraforca project built upon research conducted on Tibidabo, a multi-core ARM CPU cluster, and CARMA (CUDA on ARM development kit) which is a Tegra SoC paired with an NVIDIA Quadro card. The two slides below show CARMA benchmarks and a Tibidabo cluster (click on image for larger version).
Stay tuned to PC Perspective for more GTC 2013 coverage!
Subject: Processors | February 20, 2013 - 09:35 PM | Josh Walrath
Tagged: Tegra 4i, tegra 4, tegra 3, Tegra 2, tegra, phoenix, nvidia, icera, i500
The NVIDIA Tegra 4 and Shield project were announced at this year’s CES, but there were other products in the pipeline that were just not quite ready to see the light of day at that time. While Tegra 4 is an impressive looking part for mobile applications, it is not entirely appropriate for the majority of smart phones out there. Sure, the nebulous “Superphone” category will utilize Tegra 4, but that is not a large part of the smartphone market. The two basic issues with Tegra 4 is that it pulls a bit more power at the rated clockspeeds than some manufacturers like, and it does not contain a built-in modem for communication needs.
The die shot of the Tegra 4i. A lot going on in this little guy.
NVIDIA bought up UK modem designer Icera to help create true all-in-one SOCs. Icera has a unique method with building their modems that they say is not only more flexible than what others are offering, but also much more powerful. These modems skip a lot of fixed function units that most modems are made of and rely on high speed general purpose compute units and an interesting software stack to create smaller modems with greater flexibility when it comes to wireless standards. At CES NVIDIA showed off the first product of this acquisition, the i500. This is a standalone chip and is set to be offered with the Tegra 4 SOC.
Yesterday NVIDIA introduced the Tegra 4i, formerly codenamed “Grey”. This is a combined Tegra SOC with the Icera i500 modem. This is not exactly what we were expecting, but the results are actually quite exciting. Before I get too out of hand about the possibilities of the chip, I must make one thing perfectly clear. The chip itself will not be available until Q4 2013. It will be released in limited products with greater availability in Q1 2014. While NVIDIA is announcing this chip, end users will not get to use it until much later this year. I believe this issue is not so much that NVIDIA cannot produce the chips, but rather the design cycles of new and complex cell phones do not allow for rapid product development.
Tegra 4i really should not be confused for the slightly earlier Tegra 4. The 4i actually uses the 4th revision of the Cortex A9 processor rather than the Cortex A15 in the Tegra 4. The A9 has been a mainstay of modern cell phone processors for some years now and offers a great deal of performance when considering die size and power consumption. The 4th revision improves IPC of the A9 in a variety of ways (memory management, prefetch, buffers, etc.), so it will perform better than previous Cortex A9 solutions. Performance will not approach that provided by the much larger and complex A15 cores, but it is a nice little boost from what we have previously seen.
The Tegra 4 features a 72 core GPU (though NVIDIA has still declined to detail the specifics of their new mobile graphics technology- these ain’t Kepler though), while the 4i features a nearly identical unit featuring 60 cores. There is no word so far as to what speed these will be running at or how performance really compares to the latest graphics products from ARM, Imagination, or Qualcomm.
The chip is made on TSMC’s 28 nm HPM process and features core speeds up to 2.3 GHz. We again have no information on if that will be all four cores at that speed or turbo functionality with one core. The design adopts the previous 4+1 core setup with four high speed cores and one power saving core. Considering how small each core is (Cortex A9 or A15) it is not a waste of silicon as compared to the potential power savings. The HPM process is the high power version rather than the LPM (low power) used for Tegra 4. My guess here is that the A9 cores are not going to pull all that much power anyway due to their simpler design as compared to A15. Hitting 2.3 GHz is also a factor in the process decision. Also consider that +1 core that is fabricated slightly differently than the other four to allow for slower transistor switching speed with much lower leakage.
The die size looks to be in the 60 to 65 mm squared range. This is not a whole lot larger than the original Tegra 2 which was around 50 mm squared. Consider that the Tegra 4i has three more cores, a larger and more able GPU portion, and the integrated Icera i500 modem. The modem is a full Cat 3 LTE capable unit (100 mbps), so bandwidth should not be an issue for this phone. The chip has all of the features of the larger Tegra 4, such as the Computational Photography Architecture, Image Signal Processor, video engine, and the “optimized memory interface”. All of those neat things that NVIDIA showed off at CES will be included. The only other major feature that is not present is the ability to output 3200x2000 resolutions. This particular chip is limited to 1920x1200. Not a horrific tradeoff considering this will be a smartphone SOC with a max of 1080P resolution for the near future.
We expect to see Tegra 4 out in late Q2 in some devices, but not a lot. While Tegra 4 is certainly impressive, I would argue that Tegra 4i is the more marketable product with a larger chance of success. If it were available today, I would expect its market impact to be similar to what we saw with the original 28nm Krait SOCs from Qualcomm last year. There is simply a lot of good technology in this core. It is small, it has a built-in modem, and performance per mm squared looks to be pretty tremendous. Power consumption will be appropriate for handhelds, and perhaps might turn out to be better than most current solutions built on 28 nm and 32 nm processes.
NVIDIA also developed the Phoenix Reference Phone which features the Tegra 4i. This is a rather robust looking unit with a 5” screen and 1080P resolution. It has front and rear facing cameras, USB and HDMI ports, and is only 8 mm thin. Just as with the original Tegra 3 it features the DirectTouch functionality which uses the +1 core to handle all touch inputs. This makes it more accurate and sensitive as compared to other solutions on the market.
Overall I am impressed with this product. It is a very nice balance of performance, features, and power consumption. As mentioned before, it will not be out until Q4 2013. This will obviously give the competition some time to hone their own products and perhaps release something that will not only compete well with Tegra 4i in its price range, but exceed it in most ways. I am not entirely certain of this, but it is a potential danger. The potential is low though, as the design cycles for complex and feature packed cell phones are longer than 6 to 7 months. While NVIDIA has had some success in the SOC market, they have not had a true homerun yet. Tegra 2 and Tegra 3 had their fair share of design wins, but did not ship in numbers that came anywhere approaching Qualcomm or Samsung. Perhaps Tegra 4i will be that breakthrough part for NVIDIA? Hard to say, but when we consider how aggressive this company is, how deep their developer relations, and how feature packed these products seem to be, then I think that NVIDIA will continue to gain traction and marketshare in the SOC market.
Subject: Mobile | January 9, 2013 - 11:18 AM | Ryan Shrout
Tagged: video, tegra 3, qualcomm, power, nvidia, krait, Intel, clovertrail, ces 2013, CES
One of the more interesting demonstrations from CES thus far has come from Intel in the form of power consumption comparisons between three of the current tablet SoC solutions. Intel pits the Clovertrail SoC against NVIDIA's Tegra 3 and Qualcomm's Krait in a battle of power efficiency during video playback. What you'll see is that Intel's test shows the Clovertrail processor able to not only run near but surpass the power efficiency of the ARM-based processors shown.
This is an incredibly powerful collection of tools that Intel has presented and we are hoping to be able to dive into a similar level of detail in the future. By utilizing direct monitoring of power VRMs on the processor we could even see the power consumption of the CPU cores in comparison to the GPU cores and even against the L2 cache in some instances.
Intel is on a mission to prove that they are not only competitive today in the tablet SoC market but that they are a leader in the market. More to follow!!
PC Perspective's CES 2013 coverage is sponsored by AMD.
Follow all of our coverage of the show at http://pcper.com/ces!
Subject: Mobile | January 7, 2013 - 10:43 AM | Tim Verry
Tagged: vizio, tegra 3, tablet, ces 2013, CES
In addition to the AMD-powered tablet running Windows 8 that Vizio showed off earlier this week, the company is showing off two new ARM-based tablets running Android at CES. Vizio has reportedly listened to feedback from users as well as completed internal testing to arrive at a new tablet form factor that is lighter and thinner. In contrast to the previous-generation design, the two new Vizio tablets will be 7-inches and 10.1-inches respectively.
Both tablets feature an IPS display, rounded corners, and a back panel that is covered with a soft-to-the-touch material. Also, both tablets have a similar color scheme and logo placement.
While the exterior design is similar between the two devices, the internal specifications differ significantly. The 7-inch tablet is much smaller and has been optimized for portrait viewing. According to Vizio, the tablet is light enough to hold in one hand comfortably. Along the edges, it offers micro USB, a headphone jack, and volume controls. It has a front-facing 1.2MP webcam and an IPS display (non-laminated) with a resolution of 1280 x 800. A Vizio logo and speaker bar adorn the underside of the device.
Internal specifications include a NVIDIA Tegra 3 SoC, 16GB of storage, Wi-Fi, Bluetooth, microphone, and the Android 4.2 operating system. There is no word yet on the amount of RAM or how much the tablet weighs.
Meanwhile, the 10.1-inch Vizio tablet is matched to compete with Google’s Nexus 10. The Vizio tablet features a laminated IPS display with a resolution of 2560 x 1600, front and rear-facing cameras, speakers, and micro USB, HDMI, and headphone connectors. Internally, the 10.1-inch tablet uses NVIDIA’s latest Tegra 4 System on a Chip (SoC), which should push it above the performance of the Nexus 10 -- and (hopefully) provide the computing power necessary to smoothly push all the pixels on the high resolution display. Other hardware specs that Vizio has shared includes 32GB of internal storage, Wi-Fi, and Bluetooth 4.0 support. The tablet will ship with Android 4.2 as well.
Notably, Vizio has opted to provide a completely stock Android 4.2 operating system with its new tablets sans any skins or bloat-ware. Both tablets are expected sometime this year, with The Verge claiming the 7-inch model’s release date being within the first half of 2013. Allegedly, the tablets are noticeably lighter than the current (and, granted, older) crop of competing tablets such as the Kindle Fire HD and Nexus 7 and Nexus 10 tablets. It will be interesting to see how well the Tegra 4 chip handles the 2560 x 1600 display with the Android UI, movies, and 3D games.
For comparison, the Kindle Fire HD 7” is running a dual core OMAP 4460 SoC at 1.2GHz and the Nexus 10 is running a dual core Samsung Exynos 5250 chip at 1.7GHz. It is somewhat of a tossup with the 7” Vizio tablet and Tegra 3 as it will depend on the task and how well multi-core/multithreading is handled in the particular piece of software. The comparison between the Exynos 5250 and Tegra 4 will be interesting though, as it reminds me of the early Intel Core days where debates would be waged over the faster clocked E6600 versus the slower Q6600 and the merits of dual vs quad core on the OSes and games of the time. I’m interested to see some independent benchmarks of Tegra 4 versus Tegra 3 and A6X-powered devices in particular though (to see if it lives up to NVIDIA's claims).
Besides the unknown Tegra 4 improvements, current unknowns on the two tablets include pricing, availability, battery life, amount of RAM, and the SoC clockspeeds.
What do you think of the redesigned Vizio tablets from what we know so far? Did the company get it right this time around with its re-engineered stock devices?
PC Perspective's CES 2013 coverage is sponsored by AMD.
Follow all of our coverage of the show at http://pcper.com/ces!
Subject: Systems | January 4, 2013 - 07:59 PM | Jeremy Hellstrom
Tagged: arm, Intel, krayt, atom, qualcomm, cortex a15, tegra 3
AnandTech managed to get their hands on an Samsung designed ARM Cortex A15 processor powered tablet, which they compared to several competitors such as Intel's Atom, Qualcomm's Krait and NVIDIA's Tegra 3. The test names may seem unfamiliar with Sunspider, Kraken and RIABench providing performance comparisons though the power consumption tests will be familiar to all. Read on to see how the next generation of chips from the main contenders for your mobile device spending compare.
"The previous article focused on an admittedly not too interesting comparison: Intel's Atom Z2760 (Clover Trail) versus NVIDIA's Tegra 3. After much pleading, Intel returned with two more tablets: a Dell XPS 10 using Qualcomm's APQ8060A SoC (dual-core 28nm Krait) and a Nexus 10 using Samsung's Exynos 5 Dual (dual-core 32nm Cortex A15). What was a walk in the park for Atom all of the sudden became much more challenging. Both of these SoCs are built on very modern, low power manufacturing processes and Intel no longer has a performance advantage compared to Exynos 5."
Here are some more Systems articles from around the web:
- iBUYPOWER Chimera 4SE Desktop Gaming PC @ Tweaktown
- Improving the PC as a gaming platform: the hardware @ The Tech Report
- Cyberpower Gaming Battalion 502 Windows 8 PC Review (FX 4170 / Radeon 7770) @ Kitguru
- HP Envy 23-d060qd TouchSmart Review @ TechReviewSource
- E3iO Snack Series SK02 Desktop PC Review @ Ninjalane
- Antec ISK110 VESA Mini-ITX Desktop @ techPowerUp
Subject: Mobile | November 13, 2012 - 06:55 PM | Jeremy Hellstrom
Tagged: asus, vivo tab rt, tegra 3, winRT
Hopefully the rounded corners on the VivoTab will not catch the attention of Cupertino but until it does this convertible tablet/notebook will be popular. The tablet portion has a 10.1" 1366 x 768 SuperIPS+ display, aka 155 PPI, powered by a Tegra 3 T30 @ 1.3GHz. It has an 8MP camera at the rear and a 2MP camera which faces you for video conferencing and while it does have the ability to provide a USB connection it does so with an adapter and the docking port, so USB is unavailable when you are docked. Overall The Tech Report mostly liked the device, it might load some WinRT apps slowly but once they are running they perform admirably; lack of support for x86 programs was disappointing and in some ways they preferred the previous Android versions. See why that is so in the full article.
"Asus' Transformer approach to convertible tablets has finally come to Windows. We take a closer look at the new VivoTab RT."
Here are some more Mobile articles from around the web:
- Microsoft Surface Tablet (64GB / Windows RT) Review @ HardwareHeaven
- HP Envy TouchSmart Ultrabook 4 Review @ TechReviewSource
- Asus Zenbook Prime UX31A Ultrabook Windows 7 and 8 Testing Review @ TechwareLabs
- Asus S56CA-DH51 Review @ TechReviewSource
- Maingear Vybe 15 Gaming Laptop @ Tweaktown
- Schenker XMG P722 Gaming Laptop @ HardwareHeaven
- Dell Inspiron 14z: Ultrabook with DVD and SSD @ Hardware.info
- Lenovo Thinkpad X1 Carbon @ Hardware.info
- 13-inch Retina MacBook Pro @ AnandTech
- Apple 13-inch MacBook Pro Retina @ Hardware.info
- ASUS Eee Pad Transformer Prime @ Tweaktown
- Samsung Galaxy Note 2 (16GB, Sprint) Review @ TechReviewSource
- Samsung Galaxy Xcover review: robust smartphone
- Samsung Galaxy Note II 16GB Smartphone Review @ Legit Reviews
- Google Nexus 4 and Nexus 10 Performance Preview @ AnandTech
- Apple iPad Mini Review @ HardwareHeaven
- Apple iPad Mini (Wi-Fi) Review @ TechReviewSource
- Acer Iconia W700 Windows 8 Tablet @ XSReviews
- Amazon Kindle Fire HD 7in Review @ HardwareHeaven
- Nook Simple Touch Glowlight @ The Inquirer
- Apple Ipad Mini @ The Inquirer
Subject: Mobile | October 23, 2012 - 02:54 PM | Ryan Shrout
Tagged: windows rt, vivotab rt, tegra 3, asus
Let the onslaught of new Windows devices continue, this time with the announcement of the ASUS VivoTab RT, a Windows RT-based tablet powered by NVIDIA's Tegra 3 SoC. We have seen the VivoTab RT leaks and pictures for several months including a price listing just last month, all of which seem to have been spot on.
One of the flagship Windows RT devices, the ASUS tablet utilizes an NVIDIA Tegra 3 SoC running at up to 1.3 GHz in either dual or quad-core mode. You can see more background information on the processor itself in our story from September of last year when the product was first announced.
The tablet has a sleek design with a 8.3mm profile (0.32 in), 525g weight (1.15 lb) and 10.1-in Super IPS+ screen with a 1366x768 resolution behind scratch-resistant Corning Fit Glass. It will be available with either 32GB or 64GB of internal storage and will start at $599 with an included keyboard dock.
As we saw with ASUS Transformer series of tablets, the VivoTab RT will have an optional keyboard dock that includes a trackpad and nearly doubles the battery life of the machine. Below is the full spec sheet as provided by ASUS:
When docked, ASUS is claiming a total of 16 hours of usable battery life and with the inclusion of the Office Home and Student version of Microsoft Office 2013 RT, you should actually be able to use this tablet for content creation and business purposes - something we haven't been fond of claiming on Android or iOS based tablets.
If you are curious to learn more about the VivoTab RT we'll be doing a live streaming run through on the device on our PC Perspective Live! page at 4pm EDT / 1pm PDT, so be sure to join us!!
Missed the live stream? Here is a replay so you can enjoy seeing our experiences for a solid hour of usage including SmartGlass! Also, make sure you pay attention to the first few minutes as we explain the pricing.
Subject: Editorial, General Tech, Mobile | October 22, 2012 - 06:22 PM | Ryan Shrout
Tagged: asus, vivo tab rt, tegra 3, nvidia, video, live
If you happen to be free tomorrow afternoon and would like to be one of the first to see the upcoming ASUS Vivo Tab RT based on the Windows RT operating system and the NVIDIA Tegra 3 SoC, you should set your calendar for 12pm PDT / 3pm EDT and join me on the PC Perspective Live! page.
While we won't have any insight on our long term experiences with the device at that time tomorrow, you can see our initial impressions and anything/everything that occurrs with our intial setup and usage!
If you have questions or thoughts on the device that you want addressed during the live stream, you can leave them here in our comments or hang around in our chat room during the event as well. We want this to be interactive so your input is requested!
Again, that is 12pm PDT / 3pm EDT at the PC Perspective Live! page.
Subject: Mobile | October 10, 2012 - 10:26 PM | Tim Verry
Tagged: yoga 11, windows rt, tegra 3, tablet, nvidia, notebook, microsoft, Lenovo
At an event in New York earlier this week Lenovo announced a new Windows RT tablet called the Yoga 11. It will be joining the company’s lineup alongside the larger x86-powered Yoga 13.
The Lenovo Yoga 11 follows in the footsteps of the Yoga 13 but steps down the hardware specifications. The 11.6” tablet is 15.6mm thick and 2.8 pounds. On a simple level, the Yoga 11 is a notebook that doubles as a tablet thanks to the five point multitouch screen that can swivel 360 degrees to lay flat like a tablet.
The notebook will come pre-loaded with Microsoft’s upcoming Windows RT operating system as well as Office 2013 RT. It is powered by a NVIDIA Tegra 3 ARM System on a Chip (SoC) and 64GB of internal storage. What we don’t know yet is the amount of RAM, radio support (Wi-Fi, Bluetooth, LTE, et al) if any, and the specific display resolution and panel type. Lenovo has announced that the Yoga 11 will be able to get up to 13 hours of usage on a single charge.
The Yoga 11 is a traditional notebook at first glance, and it even includes a full Qwerty keyboard and trackpad. Where the Yoga differentiates itself is in the screen hinge. The hinge allows you to swing the display all the way around to lie flat against the bottom of the computer, which amounts to tablet mode, and every position in between. One use for this feature would be to show off presentation to a small group or prop it up on an airplane to watch a movie. It is essentially a convertible tablet without the center-mounted swivel hinge.
It certainly looks like an interesting device, and the Tegra 3 should provide enough GPU horsepower to allow you to watch HD videos with ease. Unfortunately, pricing and availability are still unknown, which makes this a hard product to place or predict the success of.
Read more about Windows RT tablets at PC Perspective.
Subject: Mobile | August 29, 2012 - 03:45 PM | Matt Smith
Tagged: unreal engine, tegra 3, tablet, nvidia, gaming
One of the reasons why I have hope for Windows RT is its gaming potential. Microsoft has been hit-or-miss with its gaming projects, but when it succeeds, it really knocks it out of the park – see DirectX, the Xbox 360 and Microsoft’s digital distribution via its console. Bringing Windows to tablets could make life easier for game developers in that space and offer a wider selection of mature titles rather than mobile-focused games, which often (in my opinion) feel watered down and look underwhelming.
NVIDIA showcased this potential at IFA 2012 by demonstrating a Windows RT tablet (with Tegra 3 hardware, of course) running Unreal Engine 3. The tablet is shown playing the NVIDIA “Epic Citiadel” demo which we saw at the editor’s day conference used to debut the GTX 680 earlier this year. Quality details are probably reduced compared to the version that ran on the GTX 680 (it’s hard to tell in the video) but it still looks excellent and runs smoothly.
The demonstration highlighted the fact this isn’t some one-off or stripped-down version of the engine designed only for mobile devices. It’s a port of the existing Unreal Engine 3 engine used to make Windows PC games, which means developers shipping games that use UE3 should have minimal trouble porting their game to a Windows 8 RT tablet. Mark Rein, president of Epic Games, stated that Windows 8 RT code is now available to UE3 licenesees. It’ll be interesting to see which game developer is first to jump on board.
The tablet in the video is an ASUS Vivo Tab RT, an upcoming Windows 8 RT tablet with an 11.6” IPS display with 1366x768 resolution and a Tegra 3 SoC. A tablet like this could be a compelling mobile gaming device if the games become available. I’ve got my fingers crossed.