All | Editorial | General Tech | Graphics Cards | Networking | Motherboards | Cases and Cooling | Processors | Chipsets | Memory | Displays | Systems | Storage | Mobile | Shows and Expos
GTC 2013: Cortexica Vision Systems Talks About the Future of Image Recognition During the Emerging Companies Summit
Subject: General Tech, Graphics Cards | March 20, 2013 - 09:44 PM | Tim Verry
Tagged: video fingerprinting, image recognition, GTC 2013, gpgpu, cortexica, cloud computing
The Emerging Companies Summit is an series of sessions at NVIDIA's GPU Technology Conference (GTC) that gives the floor to CEOs from several up-and-coming technology startups. Earlier today, the CEO of Cortexica Vision Systems took the stage to talk briefly about the company's products and future direction, and to answer questions from a panel of industry experts.
If you tuned into NVIDIA's keynote presentation yesterday, you may have noticed the company showing off a new image recognition technology. That technology is being developed by a company called Cortexica Vision Systems. While it cannot perform facial recognition, it is capable of identifying everything else, according the company's CEO Ian McCready. Currently, Cortexica is employing a cluster of approximately 70 NVIDIA graphics cards, but it is capable of scaling beyond that. Mcready estimates that about 100 GPUs and a CPU would be required by a company like eBay, should they want to implement Cortexica's image recognition technology in-house.
The Cortexica technology uses images captured by a camera (such as the one in your smartphone), which is then sent to Cortexica's servers for processing. The GPUs in the Cortexica cluster handle the fingerprint creation task while the CPU does the actual lookup in the database of known fingerprints to either find an exact match, or return similar image results. According to Cortexica, the fingerprint creation takes only 100ms, though as more powerful GPUs make it into mobile devices, it may be possible to do the fingerprint creation on the device itself, reducing the time between taking a photo and getting relevant results back.
The image recognition technology is currently being used by Ebay Motors in the US, UK, and Germany. Cortexica hopes to find a home with many of the fashion companies that would use the technology to allow people to identify and ultimately purchase clothing they take photos of on television or in public. The technology can also perform 360-degree object recognition, identify logos that are as small as .4% of the screen, and identify videos. In the future Cortexica hopes to reduce latency, improve recognition accuracy, and add more search categories. Cortexica is also working on enabling an "always on" mobile device that will constantly be indentifying everything around it, which is both cool and a bit creepy. With mobile chips like Logan and Parker coming in the future, Cortexica hopes to be able to do on-device image recognition, which would greatly reduce latency and allow the use of the recognition technology while not connected to the internet.
The number of photos taken is growing rapidly, where as many as 10% of all photos stored "in the cloud" were taken last year alone. Even Facebook, with it's massive data centers is moving to a cold-storage approach to save money on electricity costs of storing and serving up those photos. And while some of these photos have relevant meta data, the majority of photos taken do not, and Cortexica claims that its technology can be used to get around that issue, but identifying photos as well as finding similar photos using its algorithms.
Stay tuned to PC Perspective for more GTC coverage!
Additional slides are available after the break:
CEO Jen-Hsun Huang Sells Windows RT... A Little Bit.
Subject: Editorial, General Tech, Processors, Shows and Expos | March 20, 2013 - 06:26 PM | Scott Michaud
Tagged: windows rt, nvidia, GTC 2013
NVIDIA develops processors, but without an x86 license they are only able to power ARM-based operating systems. When it comes to Windows, that means Windows Phone or Windows RT. The latter segment of the market has disappointing sales according to multiple OEMs, which Microsoft blames them for, but the jolly green GPU company is not crying doomsday.
NVIDIA just skimming the Surface RT, they hope.
As reported by The Verge, NVIDIA CEO Jen-Hsun Huang was optimistic that Microsoft would eventually let Windows RT blossom. He noted how Microsoft very often "gets it right" at some point when they push an initiative. And it is true, Microsoft has a history of turning around perceived disasters across a variety of devices.
They also have a history of, as they call it, "knifing the baby."
I think there is a very real fear for some that Microsoft could consider Intel's latest offerings as good enough to stop pursuing ARM. Of course, the more the pursue ARM, the more their business model will rely upon the-interface-formerly-known-as-Metro and likely all of its certification politics. As such, I think it is safe to say that I am watching the industry teeter on a fence with a bear on one side and a pack of rabid dogs on the other. On the one hand, Microsoft jumping back to Intel would allow them to perpetuate the desktop and all of the openness it provides. On the other hand, even if they stick with Intel they likely will just kill the desktop anyway, for the sake of user confusion and the security benefits of cert. We might just have less processor manufacturers when they do that.
So it could be that NVIDIA is confident that Microsoft will push Windows RT, or it could be that NVIDIA is pushing Microsoft to continue to develop Windows RT. Frankly, I do not know which would be better... or more accurately, worse.
Annealed Pyrolytic Graphite, your next exotic cooling solution
Subject: Cases and Cooling | March 20, 2013 - 04:02 PM | Jeremy Hellstrom
Tagged: annealed pyrolytic graphite, cooling, exotic materials, thermal paste
Efficient cooling has always and will always be a limiter on the power of processors, especially as the processes used shrink and transistor density increases. Over the years we have seen heatpipes become common and watercooling move into the mainstream with the advent of all-in-one coolers. Thermal interface material has not changed much, even though we have heard of many developments nothing has been released to market. Carbon black proved to be too long in development and might be replaced by nanotube forests though there is do it yourself thermal paste doped with diamonds that you can make right now.
From there we saw a project doping thermal paste with graphene, which could provide conductivity of up to 600 W/mK once it becomes available, hopefully in sheet form for easy installation. Increasing the thermal conductivity of your TIM is a good thing, assuming that the heatsink absorbing the heat can keep up with the transfer which is what makes the news out of FrostyTech so interesting. Researchers are sandwiching a material they call K-Core Annealed Pyrolytic Graphite in between layers of aluminium and other metals to create a heatsink with a thermal conductivity of up to 1092W/mK in certain situations. It is not as simple as doping a heatsink with this new material though, it is only efficient at moving heat horizontally. Read on to find out more at FrostyTech.
"When the thermal conductivity of copper and aluminum heat spreaders just won't cut it, the future revolves around a material called Annealed Pyrolytic Graphite. Let's consider the numbers: where a solid aluminum heat spreader has a thermal conductivity of 126W/mK, the same heatspreader with an Annealed Pyrolytic Graphite core would see thermal conductivity on the order of 1092 W/mK. That's not a typo."
Here are some more Cases & Cooling reviews from around the web:
- Zalman FX100 CPU Cooler Review @ Hardware Secrets
- Noctua NH-L9i Review @ HCW
- Thermalright Silver Arrow SB-E Special Edition @ Kitguru
- Prolimatech Megahalems Red Series CPU Cooler Review @ Hardware Secrets
- Noctua NH-L12 @ techPowerUp
- DeepCool IceBlade Pro V2.0 Heatsink Review @ Frostytech
-
Scythe Kabuto II CPU Cooler Review @ Hardware Secrets
- Enermax ELC 240 Liquid CPU Cooler @ eTeknix
- Corsair Hydro Series H110 Liquid CPU Cooler @ eTeknix
- Corsair Hydro Series H110 Review @ OCC
- Corsair Hydro Series H110 AIO CPU Cooler @ Tweaktown
- Corsair Hydro H110 280mm AiO CPU Cooler Review @ Pro-Clockers
-
Compact Liquid Cooling Systems Roundup. Part I: Water on a Budget @ X-bit Labs
- NZXT Phantom 630 Computer Case @ Benchmark Reviews
- Zalman Z11 Plus @ Hardware.info
- IN WIN GT1 Mid-Tower ATX @ [H]ard|OCP
- Anidees AI-06W Midi Tower Review @ NikKTech
- Cooltek Coolcube Black @ techPowerUp
- Sharkoon REX8 Value Chassis @ eTeknix
- CM Storm Scout II Advanced Chassis @ eTeknix
- Nanoxia Deep Silence 2 Mid-Tower @ Tweaktown
- In Win D-Frame @ techPowerUp
- Coolermaster Centurion 6 @ Rbmods
LogicBuy Deals of the Day For 3/20 - HP Wireless Audio $54.99
Subject: General Tech | March 20, 2013 - 02:28 PM | Jeremy Hellstrom
Tagged: deals
Top deal
HP Wireless Audio for $54.99 with Free Shipping (normally $100 - use $150 Coupon Code: 15LOGICBUY).
Laptops
15.4" Apple MacBook Pro Retina Display Core i7 Notebook w/256GB SSD + Parallels Desktop 8 for $1,899.99 with free shipping (normally $2,100).
15.6" Dell Inspiron 15R Special Edition Core i5 + 2GB Radeon HD 7730M Laptop w/Backlit Keyboard, 8GB RAM for $550 with free shipping (normally $650 - use coupon code: 2Q?XNXR2DXQ13G).
Entertainment
60" Sharp LC-60E69U 1080p 120Hz LCD HDTV for $698.00 with free shipping (normally $1,100).
47" LG 47LM8600 1080p 240Hz 3D Dual Core LED HDTV for $1,079 with free shipping (normally $1,200).
Components
20" HP Pavilion 20xi 1600 x 900 IPS LED-backlit LCD Monitor for $105 with free shipping (normally $130 - use coupon code: 15LOGICBUY).
24" Dell UltraSharp U2413 1920 x 1200 IPS Monitor w/USB 3.0 Hub, 3-year warranty for $500 with free shipping (normally $600).
HP bd335i Blu-ray Burner (Retail) for $105.00 with free shipping (normally $130- use coupon code: 15LOGICBUY).
GTC 2013: Pedraforca Is A Power Efficient ARM + GPU Cluster For Homogeneous (GPU) Workloads
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!
Hair Quality is now a graphics setting
Subject: General Tech | March 20, 2013 - 01:21 PM | Jeremy Hellstrom
Tagged: tomb raider, tressfx, gaming
Tomb Raider is as divisive a game as Halo, either you love the series or can't understand why people are interested in it at all. As is usual, [H]ard|OCP put the gaming considerations aside to take a look at the technology showcased in the game as well as finding the settings which provide the best gaming experience on several different single and dual GPU systems. Those who want to experience AMD's new TressFX feature will be glad to hear that you can enable that setting even on a GTX 660Ti. As far as general performance, high end card owners will be able to use Super Sample AA while others will have to content themselves with FXAA, for resolutions over 1080p you are going to want a pair of GPUs as single GPU solutions struggled to meet even 1080p with high or ultimate settings. Read on to see how your system will perform and discover which side of the fence [H] is on when it comes to Lara Croft.
"Tomb Raider is the first game to sport AMD's new TressFX feature. This DX11 effect creates a new sense of realism in-game with each strand of Lara's hair reacting to her movement and environmental features like wind and rain. Crystal Dynamics has worked hard to advance our expectations as gamers and enthusiasts alike!"
Here is some more Tech News from around the web:
- Waaagh-Face: Slitherine Announce Turn-Based 40K Game @ Rock, Paper, SHOTGUN
- StarCraft II Heart Of The Swarm @ Kitguru
- 150 Mods at Once (And a $1,500 PC) Give Skyrim a Next-Gen Makeover @ Wired
- Firaxis Talk Us Through Civilization V’s Brave New World @ Rock, Paper, SHOTGUN
- Crysis 3 @ eTeknix
- SimCity Tested, Benchmarked @ Techspot
- Battlefield 4 unveiling teased for 27th March @ HEXUS
- Duke Is Out: Duke Nukem 3D: Megaton Edition @ Rock, Paper, SHOTGUN
- Gears of War: Judgement @ The Inquirer
DRAM makers emulate the HDD business by devouring the competition
Subject: General Tech | March 20, 2013 - 01:02 PM | Jeremy Hellstrom
Tagged: DRAM, micron, ssd, Samsung, Hynix
It is perhaps not obvious to many because of the huge number of DRAM resellers but there are only three major manufacturers of DRAM left at this point. Apart from Micron, who claim top spot in this article on The Register, Samsung and Hynix are the only other big players left supplying DRAM. Considering the instability of memory and SSD pricing it seems odd that it is a component with only three possible sources, the instability could be coming from the fact that many of the mergers are still rather recent or in the case of Elpida, not quite complete yet. One very interesting comment from Kipp Bedard, Micron's investor relations VP, might also explain the volatilty of flash, "there simply isn't enough NAND fab capacity to store even 20 per cent of the data people are generating." If demand outstrips supply by that order of magnitude you can dictate almost any price you wish.
"When I first started at Micron, there were about 40 to 50 DRAM companies in the space," said Bedard. "And we spent most of the '80s with the Japanese deciding they wanted to own the DRAM space which they went from 10 per cent market share to about 90 per cent, [and] took all of the US companies out except for two, us and Texas Instruments."
Here is some more Tech News from around the web:
- Fusion-io gobbles Brit Linux SCSI gurus ID7 @ The Register
- Report: BlackBerry BYOD-ware doesn't pass UK.gov security test @ The Register
- Netatmo review: weather station with app @ Hardware.info
Noctua Offers Free LGA 1150 Haswell Mounting Kit Upgrade for Older Heatsinks
Subject: General Tech | March 20, 2013 - 12:05 AM | Tim Verry
Tagged: noctua, lga 1150, hsf, heatsink, haswell, cpu cooler
Noctua has recently announced that the company is providing free mounting kits to owners of existing coolers to make them compatible with Intel's latest LGA 1150 (Haswell) motherboards. The new NM-i115x mounting kit will allow enthusiasts to recycle their older Noctua coolers with the new platform without issue. The kit includes a new back plate with fixed struts and the necessary connectors (screws, springs, et al) to make alignment and mounting easier than previous setups.
Because the LGA 1150 socket keeps the same mounting hole spacing as the current LGA 1156 and LGA 1155 sockets, many newer Noctua cooler will not need the mounting kit upgrade, and can simply be installed into the Haswell machine as is. In other words, if the heatsink worked with your Lynnfield, Sandy Bridge, or Ivy Bridge-based system, it will work in a Haswell system as well. According to Noctua, the following coolers are already compatible with Haswell:
NH-C14, NH-D14, NH-C12P SE14, NH-L12, NH-L9i, NH-U12P SE2, NH-U9B SE2
If your cooler was released prior to LGA 1156, you will need to grab the NM-i115x mounting kit upgrade by filling out this form. Noctua will make the kit available on its website as well as in retail stores (for a minimal charge, though the company did not provide specific pricing). You will need to provide proof of purchase for your existing cooler by sending Noctua a scan or screenshot of your invoice or receipt.
For more information on the NM-i115x, head over to the Noctua product page.
It is nice to see Noctua standing behind its products like this, even if it only affects a small number of users that will be making the jump for LGA 775/ect to LGA 1150.
GTC 2013: TYAN Launches New HPC Servers Powered by Kepler-based Tesla Cards
Subject: General Tech, Graphics Cards | March 19, 2013 - 06:52 PM | Tim Verry
Tagged: GTC 2013, tyan, HPC, servers, tesla, kepler, nvidia
Server platform manufacturer TYAN is showing off several of its latest servers aimed at the high performance computing (HPC) market. The new servers range in size from 2U to 4U chassis and hold up to 8 Kepler-based Tesla accelerator cards. The new product lineup consists of two motherboards and three bare-bones systems. The S7055 and S7056 are the motherboards while the FT77-B7059, TA77-B7061, and FT48-B7055.
The TA77-B7061 is the smallest system, with support for two Intel Xeon E5-2600 processors and four Kepler-based Tesla accelerator cards. The FT48-B7055 has si7056 specifications but is housed in a 4U chassis. Finally, the FT77-B7059 is a 4U system with support for two Intel Xeon E5-2600 processors, and up to eight Tesla accelerator cards. The S7055 supports a maximum of 4 GPUs while the S7056 can support two Tesla cards, though these are bare boards so you will have to supply your own cards, processors, and RAM (of course).
According to TYAN, the new Kepler-based HPC systems will be available in Q2 2013, though there is no word on pricing yet.
Stay tuned to PC Perspective for further GTC 2013 Coverage!
Bungie jump for your mouse from ROCCAT
Subject: General Tech | March 19, 2013 - 06:25 PM | Jeremy Hellstrom
Tagged: input, roccat, apuri hybrid, gadget
The Apuri Hybrid USB Hub & Mouse Bungie looks a little familiar, though it does have more functionality that the Cooler Master version as it is also a 4 port powered USB 2.0 hub with an LED. Not only will your mouse tail look snazzy hanging from a scorpion like device but you can also keep a variety of USB devices close to hand. Neoseeker was a little disappointed at the $40 price tag, rather high for a non-USB 3.0 hub, but if you are looking to get your cords out of the way the added functionality is a nice feature.
"If you have a very particular need for a USB hub that also serves to reduce mouse cable clutter and keep your work area in order, ROCCAT just might have you covered with the Apuri. This unique peripheral is both mouse cable bungie and 4-port USB 2.0 hub in one scorpion-shaped package, so hit our review to see whether the Apuri delivers good value for its proposed convenience."
Here is some more Tech News from around the web:
- Razer DeathAdder 2013 (4G) Gaming Mouse Review @ Custom PC Review
- FUNC MS-3 Laser Gaming Mouse @ Tweaktown
- AZiO Levetron GM533U Gaming Mouse @ Benchmark Reviews
- Razer Naga Hex, Goliathus League of Legends Gaming Peripherals Review @ Custom PC Review
- AZiO Levetron GM533U Gaming Mouse Review @ OCC
- Genius Gila GX Gaming Mouse @ Benchmark Reviews
- Razer Ouroboros Wireless Gaming Mouse @ eTeknix
- ROCCAT Sense Chrome Blue Gaming Mouse Pad Review @ Neoseeker
- Cooler Master CM Storm Power-RX Mouse Pad Review @ Ninjalane
- Roccat ISKU FX Gaming Keyboard @ eTeknix
- Razer Blackwidow Ultimate gaming keyboard @ Rbmods
- Enermax Aurora Micro Wireless Keyboard @ Kitguru
ASUS VivoBook comes close to the original spirit of the Ultrabook
Subject: Mobile | March 19, 2013 - 03:21 PM | Jeremy Hellstrom
Tagged: asus, VivoBook S500, ultrabook, win8
The ASUS VivoBook is under $1000, lightweight with a touchscreen for Win8 and it does have an SSD, a small 24GB cache SSD but enough to trim down on boot times and resume from sleep all of which come close to the original specs for an Ultrabook. Legit Reviews tried out the 1366x768 Core i5-3317 powered Ultrabook, configured with 4GB RAM and a SanDisk cache drive. It lasted a reasonable 2 hours and 21 minutes in Futuremark Powermark, simulating heavy usage but when it came to the storage subsystem it really lagged behind the competition. Overall ASUS did make compromises to keept the price low, but if you are looking for an ultramobile touch device and don't need fast storage it is a decent choice.
"Are you looking for an affordable Intel Ultrabook that features Windows 8 with Touch? The ASUS VivoBook S500 just launched this week and is an entry level 15.4" Intel Ultrabook that is loaded with features and costs under $700 shipped. Read on to see how the ASUS VivoBook S500 Ultrabook performs with an Intel Core i5-3317U processor, 6GB DDR3 memory, 500GB 5400RPM hard drive and 24GB SSD for caching purposes."
Here are some more Mobile articles from around the web:
- Acer Aspire S7 13″ (S7-391) Ultrabook @ XSReviews
- Dell Inspiron 17-3721 Review @ TechReviewSource
- HP ENVY 4 TouchSmart (ENVY 4-1102xx) Ultrabook Review @ Custom PC Review
- Microsoft Surface RT review: the first Microsoft tablet @ Hardware.info
- Acer Iconia W510 Hybrid Tablet @ TechSpot
- Nextbook Premium7SE Tablet Review @ TechwareLabs
- DeepCool N9 Aluminum Notebook Cooler @ Benchmark Reviews
- Logitech T651 Rechargeable Trackpad for Mac Review @ Legit Reviews
- Antec PowerUp 6000 and Go Charger Mobile Accessory Review @ Hi Tech Legion
- Benchmarking Ubuntu Linux On The Google Nexus 7 @ Phoronix
- Sony Xperia Z @ The Inquirer
- Sony Xperia Z review: Sony's flagship Full HD phone @ Hardware.info
- Mid-range smartphone round-up @ Hardware.info
- HTC One review: there can be only One @ Hardware.info
- Cygnett Aviator iPhone 4/4S Case Review @ Madshrimps
- Poetic Palette Nexus 4 @ LanOC Reviews
GTC 2013: Jen-Hsun Huang Takes the Stage to Discuss NVIDIA's Future, New Hardware
Subject: General Tech, Graphics Cards | March 19, 2013 - 02:55 PM | Tim Verry
Tagged: unified virtual memory, ray tracing, nvidia, GTC 2013, grid vca, grid, graphics cards
Today, NVIDIA's CEO Jen-Hsun Huang stepped on stage to present the GTC keynote. In the presentation (which was live streamed on the GTC website and archived here.), NVIDIA discussed five major points, looking back over 2013 and into the future of its mobile and professional products. In addition to the product roadmap, NVIDIA discussed the state of computer graphics and GPGPU software. Remote graphics and GPU virtualization was also on tap. Finally, towards the end of the Keynote, the company revealed its first appliance with the NVIDIA GRID VCA. The culmination of NVIDIA's GRID and GPU virtualization technology, the VCA is a device that hosts up to 16 virtual machines which each can tap into one of 16 Kepler-based graphics processors (8 cards, 16 GPUs per card) to fully hardware accelerate software running of the VCA. Three new mobile Tegra parts and two new desktop graphics processors were also hinted at, with improvements to power efficiency and performance.
On the desktop side of things, NVIDIA's roadmap included two new GPUs. Following Kepler, NVIDIA will introduce Maxwell and Volta. Maxwell will feature a new virtualized memory technology called Unified Virtual Memory. This tech will allow both the CPU and GPU to read from a single (virtual) memory store. Much as with the promise of AMD's Kaveri APU, the Unified Virtual Meory will result in speed improvements in heterogeneous applications because data will not have to be copied to/from the GPU and CPU in order for the data to be processed. Server applications will really benefit from the shared memory tech. NVIDIA did not provide details, but from the sound of it, the CPU and GPU both continue to write to their own physical memory, but their is a layer of virtualized memory on top of that, that will allow the two (or more) different processors to read from each other's memory store.
Following Maxwell, Volta will be a physically smaller chip with more transistors (likely a smaller process node). In addition to the power efficiency improvements over Maxwell, it steps up the memory bandwidth significantly. NVIDIA will use TSV (through silicon via) technology to physically mount the graphics DRAM chips over the GPU (attached to the same silicon substrate electrically). According to NVIDIA, this new TSV-mounted memory will achieve up to 1 Terabytes/second of memory bandwidth, which is a notable increase over existing GPUs.
NVIDIA continues to pursue the mobile market with its line of Tegra chips that pair an ARM CPU, NVIDIA GPU, and SDR modem. Two new mobile chips called Logan and Parker will follow Tegra 4. Both new chips will support the full CUDA 5 stack and OpenGL 4.3 out of the box. Logan will feature a Kepler-based graphics porcessor on the chip that can “everything a modern computer ought to do” according to NVIDIA. Parker will have a yet-to-be-revealed graphics processor (Kepler successor). This mobile chip will utilize 3D FinFET transistors. It will have a greater number of transistors in a smaller package than previous Tegra parts (it will be about the size of a dime), and NVIDIA also plans to ramp up the frequency to wrangle more performance out of the mobile chip. NVIDIA has stated that Logan silicon should be completed towards the end of 2013, with the mobile chips entering production in 2014.
Interestingly, Logan has a sister chip that NVIDIA is calling Kayla. This mobile chip is capable of running ray tracing applications and features OpenGL geometric shaders. It can support GPGPU code and will be compatible with Linux.
NVIDIA has been pushing CUDA for several years, now. The company has seen some respectable adoption rates, by growing from 1 Tesla supercomputer in 2008 to its graphics cards being used in 50 supercomputers, with 500 million CUDA processors on the market. There are now allegedly 640 universities working with CUDA and 37,000 academic papers on CUDA.
Finally, NVIDIA's hinted-at new product announcement was the NVIDIA VCA, which is a GPU virtualization appliance that hooks into the network and can deliver up to 16 virtual machines running independant applications. These GPU accelerated workspaces can be presneted to thin clinets over the netowrk by installing the GRID client software on users' workstations. The specifications of the GRID VCA is rather impressive, as well.
The GRID VCA features:
- 2 x Intel Xeon processors with 16 threads each (32 total threads)
- 192GB to 384GB of system memory
- 8 Kepler-based graphics cards, with two GPUs each (16 total GPUs)
- 16 x GPU-accelerated virtual machines
The GRID VCA fits into a 4U case. It can deliver remote graphics to workstations, and is allegedly fast enough to deliver gpu accelerated software that is equivalent to having it run on the local machine (at least over LAN). The GRID Visual Computing Appliance will come in two flavors at different price points. The first will have 8 Kepler GPUs with 4GB of memory each, 16 CPU threads, and 192GB of system memory for $24,900. The other version will cost $34,900 and features 16 Kepler GPUs (4GB memory), 32 CPU threads, and 384GB system memory. On top of the hardware cost, NVIDIA is also charging licensing fees. While both GRID VCA devices can support unlimited devices, the licenses cost $2,400 and $4,800 per year respectively.
Overall, it was an interesting keynote, and the proposed graphics cards look to be offering up some unique and necessary features that should help hasten the day of ubiquitous general purpose GPU computing. The Unified Virtual Memory was something I was not expecting, and it will be interesting to see how AMD responds. AMD is already promising shared memory in its Kaveri APU, but I am interested to see the details of how NVIDIA and AMD will accomplish shared memory with dedicated grapahics cards (and whether CrossFire/SLI setups will all have a single shared memory pool)..
Stay tuned to PC Perspective for more GTC 2013 Coverage!
ASRock's Formula for success
Subject: Motherboards | March 19, 2013 - 01:36 PM | Jeremy Hellstrom
Tagged: asrock, Z77 OC Formula, Intel Z77X
If you are shopping for a Z77 motherboard you have a lot of choice in make and model as well as price, they range from sub-$100 models to high end boards like the $225 ASRock Z77 OC Formula. For that extra price you get a motherboard built with 12+4 phase power, premium alloy chokes, dual-stack MOSFETs and 8 layers of copper. It is not just high end components, you also get a pair of PCIe 16x slots, a single PCIe 4x slot and a pair of 1x slots for add-in cards as well as four SATA 6Gbps ports and two SATA 3G ports, 10 USB 2.0 ports and 8 USB 3.0 ports along with onboard audio from Realtec's ALC898. [H]ard|OCP did some testing to see if this board lives up to the OC in its name, which it did rather handily.
"Generally speaking our ASRock experiences have been positive save for one or two minor complaints. We’ve looked inexpensive but very popular ASRock model motherboards. Today we are taking a look at a higher end more expensive ASRock offering. The Z77 OC Formula caught our eye and will hopefully perform as good as it looks."
Here are some more Motherboard articles from around the web:
- ASRock Z77 Pro4-M @ [H]ard|OCP
- Gigabyte Z77X-UD4H @ Funky Kit
- Gigabyte GA-H77N-WiFi Motherboard Review @ Hi Tech Legion
- ASUS P8Z77-V LK Motherboard @ Hardware Secrets
- GIGABYTE Z77N-WiFi @ Tweaktown
- MSI's Z77IA-E53 Mini-ITX @ The Tech Report
- BIOS Option Of The Week - SDRAM Tras Timing Value @ TechARP
- Biostar Hi-Fi A85W @ Kitguru
- ECS A85F2-A GOLDEN @ Tweaktown
- ECS A970M-A Deluxe Motherboard Review @ OCC
Intel's inventory undergoes some shrinkage
Subject: Motherboards | March 19, 2013 - 12:55 PM | Jeremy Hellstrom
Tagged: Intel, qualcomm
The slowdown of PC sales has finally even impacted Intel's supply chain as they reduce the number of chips stocked in inventory. Even after these years of domination over AMD on the desktop Intel has not been reducing their supplies of chips as they were still selling them at a brisk pace. It is obvious that has changed over the past year as the lowering sales of PCs and laptops finally lead to Intel reducing the number of chips they have on hand. They were not the only ones to make this move, with AMD and others also reducing their stocks somewhat. One area The Register did not report on is GPUs, with the short lifespan of a GPU the stocks of new silicon are also goign to be quite reduced and you should see more discounts on lower end GPUs as resellers try to offload them. As we have seen before people are still buying electronics, just smaller, more portable devices; Qualcomm's available stock has had to increase by 24% over the same time period.
"Bean counter iSuppli reckons the major manufacturers acted swiftly to prevent expensive backlogs of baked silicon forming: the average number of days between producing inventory and selling it declined five per cent. The value of the inventory piles also fell five per cent, or $600m, from Q3 to Q4 of 2012, we're told."
Here is some more Tech News from around the web:
- How Fusion-io redlined its PCIe flash motor to hit 9.6 MEEELION IOPS @ The Register
- EA Origin vuln puts players at risk @ The Register
- Oracle Virtual Box Virtual Machine Tips @ PCSTATS
- Win an Asus GeForce GTX 650 Ti TOP Graphics Card @ eTeknix
GTC 2013: Prepare for Graphics Overload
Subject: General Tech, Graphics Cards, Mobile, Shows and Expos | March 18, 2013 - 09:10 PM | Scott Michaud
Tagged: GTC 2013, nvidia
We just received word from Tim Verry, our GTC correspondent and news troll, about his first kick at the conference. This... is his story.
Graphics card manufacturer, NVIDIA, is hosting its annual GPU Technology Conference (GTC 2013) in San Jose, California this week. PC Perspective will be roaming the exhibit floor and covering sessions as NVIDIA and its partners discuss upcoming graphics technologies, GPGPU, programming, and a number of other low level computing topics.
The future... is tomorrow!
A number of tech companies will be on site and delivering presentations to show off their latest Kepler-based systems. NVIDIA will deliver its keynote presentation tomorrow for the press, financial and industry analysts, and business partners to provide a glimpse at the green team's roadmap throughout 2013 - and maybe beyond.
We cannot say for certain what NVIDIA will reveal during its keynote; but, since we have not been briefed ahead of time, we are completely free to speculate! I think one certainty is the official launch of the Kepler-based K6000 workstation card; for example. While I do not expect to see Maxwell, we could possibly see a planned refresh of the Kepler-based components with some incremental improvements: I predict power efficiency over performance. Perhaps we will receive a cheaper Titan-like consumer card towards the end of 2013? Wishful thinking on my part? A refresh of its GK104 architecture would be nice to see as well, even if actual hardware will not show up until next year. I expect that NVIDIA will react to whatever plans AMD has to decide whether it is in their interest to match them or not.
I do expect to see more information on GRID and Project SHIELD, however. NVIDIA has reportedly broadened the scope of this year's conference to include mobile sessions: expect Tegra programming and mobile GPGPU goodness to be on tap.
It should be an interesting week of GPU news. Stay tuned to PC Perspective for more coverage as the conference gets underway.
What are you hoping to see from NVIDIA at GTC 2013?
Need high volume SSD storage and can afford the price? Solidata has 2TB drives
Subject: Storage | March 18, 2013 - 04:23 PM | Jeremy Hellstrom
Tagged: Solidata, K8 1920E 2TB, ssd, sf-1222, LSI, sandforce, Micron JMB393
We have seen some high capacity PCIe based SSDs but in the 2.5" form factor they have been few and far between. This will soon change as Solidata will be releasing a 2 Terabyte SSD called the K8 1920E which will be somewhere in the neighbourhood of $5000 when it becomes available. Each one of the flash storage chips you can see below is a 64GB chip and with 16 on each side you get a full 2048GB of storage. It uses four of the LSI Sandforce SF-1222 controllers and a Micron JMB393 SATA II RAID-5 controller which is configured to act as a 4 port hub, treating each of the controllers as a separate 512GB SSD. Once the SSD Review had formatted the drive for use there was a total of 1788GB available for storage which did not support TRIM as it is technically behind a RAID card. The performance was on par with expectations, keeping in mind the difficulties that SandForce controllers have with incompressible data. This drive will be very expensive but it seems it will be the first product of its type available to be purchased.
"Ever since SSDs were introduced to the retail market back in 07, one of the main complaints has always been capacity. After all, the first SSD releases were only 32 and 64GB. The hopes of one day seeing the performance of an SSD coupled with the capacity of a hard drive has grown and, too many, we think our analysis of the new Solidata K8-1920E 2TB SSD might be welcome news."
Here are some more Storage reviews from around the web:
- SuperSSpeed S301 Hyper Gold 128GB SLC SSD @ [H]ard|OCP
- Intel 335 Series 180GB SSD Review @ Techgage
- MyDigitalSSD BP4 Slim 7 Solid State Drive @ Benchmark Reviews
- OCZ Vertex 3.20 20nm @ SSD Review
- Micron RealSSD P400m Enterprise SSD @ SSD Review
- Kingston SSDNow V300 120GB @ Tweaktown
- OCZ Vector 256GB SSD Review @ Hi Tech Legion
- Samsung 840 Pro 512GB @ Tweaktown
- Toshiba MK01GRRB/R 2.5-inch 6Gb/s SAS 15K RPM Enterprise RAID Report @ Tweaktown
- Patriot Gauntlet Node Wireless Enclosure Review @ NikKTech
- Adata DashDrive Air AE400 review: wireless card reader for mobile devices @ Hardware.info
- PQI Tiffany USB 3.0 32 GB @ techPowerUp
- Transcend RDF8 USB 3.0 Memory Card Reader Review @ Legit Reviews
- SuperTalent RC4 USB 3.0 Flash Drive With MS Windows To Go @ SSD Review
- Patriot Supersonic Magnum 256GB USB 3.0 Flash Drive Review @ Legit Reviews
- Patriot Supersonic Magnum 256GB USB 3.0 Flash Drive Review @ Hi Tech Legion
- CalDigit AV Pro USB 3.0 HDD / SSD Enclosure @ Tweaktown
- Thecus N7510 7-Bay Affordable Tower NAS @ Tweaktown
- QNAP TS-469L High-performance 4-bay NAS Server for Home & SOHO Review @ Madshrimps
- StarTech 2.5-Inch to USB 3.0 Encrypted Hard Drive Enclosure Review @ Legit Reviews
- QNAP TurboNAS TS-469U-RP NAS Server Review @ NikKTech
- Icy Dock FlexCage MB973SP-2B 5.25-inch HDD Bay Adapter @ Tweaktown
ASUS HD 7970 DirectCU II versus a dual linked Dell 3007WFP
Subject: Graphics Cards | March 18, 2013 - 03:17 PM | Jeremy Hellstrom
Tagged: 2560x1600, amd, hd7970 direct cu 2, asus, dell, 3007WFP
[H]ard|OCP has wanted to publish their review of the ASUS HD 7970 DirectCU II for a while but ran into a compatibility issue during their testing and ended up being a perfect example of what sometimes happens to review sites and enthusiasts on the bleeding edge. [H] uses a Dell 3007WFP with a resolution of 2560x1600 which necessitates the use of a dual link DVI connection, which cause the issue you can see below. No other setup seemed to reproduce this problem, even the same monitor on a single link DVI at 1920x1080 or at the higher resolution on Display Port would not display the issue. So what began as a review of an HD 7970 with some nice extra features from ASUS became a long session of troubleshooting. Take a read through the review as these cards should be back in stock over the next few months, very likely with a solution to this problem already incorporated.
"Today we have the ASUS HD 7970 DirectCU II strapped to our test bench for your reading pleasure. We will compare it to the AMD Radeon HD 7970 GHz Edition and to the NVIDIA GeForce GTX 680 to determine whether the custom VRMs and DirectCU II cooling solution are the droids you are looking for in your next graphics card purchase."
Here are some more Graphics Card articles from around the web:
- PowerColor PCS+ HD7870 GHz Edition 2GB GDDR5 @ LanOC Reviews
- HIS Radeon HD 7850 iPower IceQ Turbo 4GB @ Tweaktown
- ASUS Radeon HD 7850 DirectCU On Ubuntu @ Phoronix
- AMD Radeon HD 7870 GHz Edition vs. Nvidia GeForce GTX 660: frametimes @ Hardware.info
- Powercolor HD 7870 Myst Edition @ Bjorn3D
- AMD vs Nvidia: Radeon 7870 vs GeForce 660 Using Frame Times @ HCW
- Prolimatech MK-26 GPU Cooler Review @ Pro-Clockers
- GELID Icy Vision Rev. 2 VGA Cooler Review @ Hi Tech Legion
- Matrox DS1 review: a practical Thunderbolt dock @ Hardware.info
- Nvidia GeForce GTX TITAN 6 GB @ X-bit Labs
- Nvidia GeForce GTX Titan @ Techspot
- Gigabyte GeForce GTX Titan @ Legion Hardware
- EVGA GeForce GTX 670 FTW 2GB @ Hardware.info
- NVIDIA GTX TITAN vs. SLI & Crossfire @ Hardware Canucks
Turn half your GTX 690 into a Quadro or Tesla?
Subject: General Tech | March 18, 2013 - 02:23 PM | Jeremy Hellstrom
Tagged: nvidia, hack, GTX 690, K5000, K10, quadro, tesla, linux
It will take a bit of work with a soldering iron but Hack a Day has posted an article covering how to mod one of the GPUs on a GTX690 into thinking it is either a Quadro K5000 or Tesla K10. More people will need to apply this mod and test it to confirm that the performance of the GPU actually does match or at least compare to the professional level graphics but the ID string is definitely changed to match one of those two much more expensive GPUs. They also believe that a similar mod could be applied to the new TITAN graphics card as it is electronically similar to the GTX690. Of course, if things go bad during the modification you could kill a $1000 card so do be careful.
"If hardware manufacturers want to keep their firmware crippling a secret, perhaps they shouldn’t mess with Linux users? We figure if you’re using Linux you’re quite a bit more likely than the average Windows user to crack something open and see what’s hidden inside. And so we get to the story of how [Gnif] figured out that the NVIDIA GTX690 can be hacked to perform like the Quadro K5000. The thing is, the latter costs nearly $800 more than the former!"
Here is some more Tech News from around the web:
- The TR Podcast 130: A series of grunts about convertible tablets
- Microsoft updates its Kinect for Windows SDK @ The Inquirer
- Asustek to launch new Intel-based smartphone in June @ DigiTimes
- The 2013 Top 7 Best Linux Distributions for You @ Linux.com
- Watch out, office bods: A backdoor daemon lurks in HP LaserJets @ The Register
Western Digital 3TB Red 3.5" SATA Internal Hard Drive (WD30EFRX) $145.95
Subject: General Tech, Storage | March 18, 2013 - 12:51 PM | Jeremy Hellstrom
Tagged: deals
Top deal
Western Digital 3TB Red 3.5" SATA Internal Hard Drive (WD30EFRX) for $145.95 with Free Shipping (normally $170).
Laptops
15.6" Dell Inspiron 15R Special Edition Core i5 Laptop w/2GB Radeon HD 7730M, Backlit Keyboard, 6GB RAM for $549.99 with free shipping (normally $799.99 - use $150 Coupon Code: 2Q?XNXR2DXQ13G).
23.6" HP Spectre ONE 23-e010se Core i5 Slim All-in-One PC w/TrackPad for $974.99 with free shipping (normally $1,299.99 - use coupon code: DT2617).
Entertainment
90" Sharp AQUOS LC-90LE745U 3D 1080p 120Hz LED HDTV + Free Wall Mount for $7,390 with free shipping (normally $10,000 - use coupon code: FREEMOUNT).
Components
Two (2) Dual UltraSharp U2412M IPS LCD Monitors with Dual Monitor Stand for $594.99 with free shipping (normally $699.99 - use coupon code: 6DBNK$ZJLR$L4J).
128GB OCZ Vertex 4 SATA III Solid State Drive for $116.99 with free shipping (normally $129.99 - use coupon code: VZQG7WPT?PJ4C4).
Netgear Universal WN3000RP Wi-Fi Range Extender for $69.00 with free shipping (normally $90).
Gadgets
Boombotix BB2 Bluetooth Speaker Limited Edition for $69.95 with free shipping (normally $79.99).
Waterfi iPod Shuffle Waterproof Swim Set (5th ten) for $154.95 with free shipping (normally $179.99).
Audio-Technica Portable Stainless Steel Headphones for $109 with free shipping (normally $249.99 - use coupon code: VMESAVESU20).
New Beta NVIDIA GeForce Drivers for Tomb Raider
Subject: General Tech | March 16, 2013 - 11:36 PM | Scott Michaud
Tagged: nvidia, tomb raider
The last month has been good to PC gamers: from Starcraft, to SimCity, to Tomb Raider, all with the promise of Bioshock Infinite just around the corner. We are being dog piled by one bulky release after another... most of which we are theoretically able to play.
Of course this is a call to action for GPU driver engineers. The software required to make your video card run is extremely complex with graphics instructions being compiled and interpreted at runtime for routinely shifting architectures. Performance increases are often measured in the double digit percentages albeit for some set "X" of components in some set "Y" of games.
GeForce 314.14 beta drivers launched early in the month with decent performance increases particularly for setups with SLi-paired 680s. Tomb Raider fans found themselves quite a bit left out with the reboot of the franchise doing everything but rebooting their PCs with NVIDIA and Intel hardware.
Now, two weeks later, NVIDIA has released yet another beta driver, dubbed 314.21, aimed squarely at Tomb Raider. Performance increases are claimed to be an average 45% higher than previous versions with some configurations seeing upwards of 60% increases in performance. The delay was allegedly caused by the hardware developer not receiving the game code with enough time before launch to create the updates.
If you are a Tomb Raider, check out the drivers at NVIDIA's website.




















