AMD bulldozer has achieved insane 8.58Ghz using liquid nitrogen, hitting a world record. But 5.6Ghz is the best we’ve reached with Core i7. The work is done by professional overclocker Hicookie who overclocked his Core i7 3930K to 5.6GHz.

His setup was actually amazing, he used aforementioned Dippin’ Dots refrigerant. Hicookie used an Gigabyte X79 motherboard for making it possible. Gigabyte X79 is first such board to reach a multiplier of 57. Check out the video after a break:

don’t forget, we warned you about the poor video quality

We write latest and greatest in Tech Guides, Apple, iPhone, Tablets, Android,  Open Source, Latest in Tech, subscribe to us@geeknizeron Twitter OR on Facebook Fanpage, Google+:

The new 16-core processors from AMD are targeting enterprise servers for better performance with great power efficiency. AMD Opteron 6200 family of processors code-named Interlagos give enterprises as much as 84 percent better performance, 73 percent better memory bandwidth, and better power efficiency with half the power per core. They save about two-thirds on floor space and two-thirds on platform costs.

The five 6200 chips — 6262 HE, 6272, 6274, 6276 and 6282 SE — run at clock speeds between 1.6GHz and 2.6GHz, and are priced between US$523 and $1,019. The chips draw between 85 watts and 140 watts of power and will plug into existing server sockets to replace older 12-core chips.

This is a great deal for SMB companies that are getting their businesses into cloud computing with more agility and efficiency. The new Opteron chips use AMD’s Bulldozer computing cores.

The Bulldozer architecture mixes the CPU with integer units and a shared floating point unit so more operations can be executed per clock cycle while drawing lower power. Other chip improvements include Turbo Core technology, which can increase clock speed by up to 500MHz across all cores and up to 1GHz on some cores depending on the performance required.

AMD is also introducing the AMD Opteron 4200 series, formerly code-named Valencia, which will come with between six and eight cores. The chips operate at clock speeds between 1.6GHz and 3.0GHz, and are priced between $125 and $377. The 4200 processors are for dense server environments with low-power consumption. The chips draw between 35 watts and 95 watts of power, and as low as 4.3 watts per core

AMD is already workign the server OEMs like HP, Acer, dell to get these new 16-core chips to market, as early as possible.

We write latest and greatest in Tech Guides, Apple, iPhone, Tablets, Android,  Open Source, Latest in Tech, subscribe to us@geeknizer on Twitter OR on Facebook Fanpage:

“The idea is that at a fixed computing load, the amount of battery you need will fall by a factor of two every year and a half” which will shape the future of mobile computing in all forms.

Koomey’s law is more consumer centric, which says that Energy efficiency and thus, battery life is becoming more of a concern than the raw power of new devices thanks to the continuing rise of smartphones, tablets and notebooks. Till very recently, both Moore’s law and Koomey’s law had been valid, but Moore’s law had been invalidated according to several scientists.

Typically, performance improvement can be achieved by either overclocking the chipset ( by delivering more power to the transistors) thus generating more heat, or by simply adding more transistors to meet the new performance requirements. Both the problems of performance and energy efficiency have been answered thus far with a single solution: reducing the size of transistors. This allows for more of them to be placed on a chipset and reduces each transistor’s energy and heat mitigation requirements. e.g. a 45nm chip is more power hungry than a 22nm chip, and so on; Size difference is obvious.

Energy efficiency of transistors is a better concept and benchmark to measure improvements over years.

“This is a fundamental characteristic of information technology that uses electrons for switching… It’s not just a function of the components on a chip”. It stands to reason then, that future technologies will likely be based on this same premise, and thus conform to the theory.

Physicist Richard Feynman tells us Koomey’s theory would hold true for decades to come. In 1985, Richard analyzed the electrical requirements of computers and estimated that the technology could theoretically improve by a factor of one hundred billion (100,000,000,000) beforeit reaches the limit. So far,  we’ve only seen an improvement of around a factor of forty thousand (40,000). Whatever may happen, both Moore and Koomey believe that a technology that efficiently delivered boundless processing power would be magical indeed. Arthur C. Clarke’s third law “Any sufficiently advanced technology is indistinguishable from magic”.

We write latest and greatest in Tech Guides, Apple, iPhone, Tablets, Android,  Open Source, Latest in Tech, subscribe to us@geeknizer on Twitter OR on Facebook Fanpage:

Although with AI (Artificial Intelligence), computers can learn, they are not smart enough to make independent decisions, they don’t think beyond what they are told and even this artifical thinking can be slow at times when its a cpu intensive operation. For instance, Face recognition is something human brain can do much faster than a household computer, but, when compared to mathematical operations, computers beat humans collectively. Its a challenge when we try training a computer to behave like a human brain.

Researchers at IBM have made a key step towards Cognitive computing, a methodology that let computer think like humans. IBM has built two chips that process data more like how humans. Its a new CPU architecture, that surpasses the current Intels and AMD (von Neumann architecture).

These chips, like human brain, are extremely efficient, to prove the point, these chips run at 10Hz and still beat most modern computers. 10Hz is roughly the same as the frequency of human brain.

The chips represent a significant milestone in a six-year-long project that has involved 100 researchers and some $41 million in funding from the government’s Defense Advanced Research Projects Agency, or DARPA. IBM has also committed an undisclosed amount of money.

No Neurons or Bio-parts inside, yet
These are no biological chips but silicon chips inspired by human brain. They work as a human brain would. As IBM calls it, they are “neurobiology to make up what is referred to as a ‘neurosynaptic core’ with integrated memory (replicated synapses), computation (replicated neurons), and communication (replicated axons)”.

IBM demoed steering a simulated car through a maze, playing Pong using these chips. The chips’ ability to adapt to types of information that it wasn’t specifically programmed to expect is a key feature.

Dharmendra Modha, project leader for IBM Research, said the new chips have parts that behave like digital “neurons” and “synapses” that make them different than other chips. Each “core,” or processing engine, has computing, communication and memory functions.

“You have to throw out virtually everything we know about how these chips are designed. The key, key, key difference really is the memory and the processor are very closely brought together. There’s a massive, massive amount of parallelism.”

The project is part of the same research that led to IBM‘s announcement in 2009 that it had simulated a cat’s cerebral cortex, the thinking part of the brain, using a massive supercomputer. Using progressively bigger supercomputers, IBM had previously simulated 40 percent of a mouse’s brain in 2006, a rat’s full brain in 2007, and 1 percent of a human’s cerebral cortex in 2009. A computer with the power of the human brain is not yet near.

Also Read: Simulate Human Brain

We are still a decade away from a computer that would beat human brain, its just a good start that we see now, first step is taken.

We write latest and greatest in Tech Guides, Apple, iPhone, Tablets, Android,  Open Source, Latest in Tech, subscribe to us @geeknizer on Twitter OR on Facebook Fanpage:

As Intel calims:

With these upgrades, customers will enjoy:

• Better performance for photo, video, and music tasks.
• Better responsiveness for everyday PC activities.
• Better responsiveness for PC productivity at work or at home.

Wait a minute, how is that even possible?

Truth be told, the hardware was already capable of doing more but looks like it was not unlocked out of the box. Intel had disabled HyperThreading technology, more L3 cache for applications on some of the Core i3 processors, and Intel Pentiums, which will be unlocked via this software upgrade. Intel is selling these as $50 upgrade cards.

Pentium 2.8GHz G6951 is sold with 3MB of L3 cache and has HyperThreading disabled. By purchasing and activating the $50 upgrade card, a full 4MB of L3 cache is enabled along with HyperThreading.

Compatible processors:

Intel® Core™ i3-2102 Processor
Intel® Pentium® G622 Processor
Intel® Core™ i3-2312M Processor
Intel® Pentium® G6951 Processor

As with all forms of DRM and software unlocks, it’s only a matter of time before modders/hackers find a way to circumvent Intel’s $50 upgrade card.

We write latest and greatest in Tech Guides, Apple, iPhone, Tablets, Android,  Open Source, Latest in Tech, subscribe to us@geeknizer on Twitter OR on Facebook Fanpage:

Qualcomm is claiming that its next generation of Snapdragon chips would beat current generation of processors used in gaming consoles like PS3. That’s a big claim, but noting the facts laid out by Sony PS Vita, these look real.

S4 codenamed ‘Krait’ devices would launched by end of the year. S4 would be first 28nm quad core processors and run Adreno 225 GPU – Quad core cpu + Adreno 225 aim to blow away the fluidity of PS3 graphics.

Qualcomm S

There are four new tiers of processor, named S1 to S4. That “S” stands for “System”, with the number referring to how powerful the chip is.

S1 includes standard handsets such as the HTC Droid Incredible and Sony Ericsson X10i, S2 is featured in more powerful phones like the HTC Thunderbolt and LG Revolution, and S3 powers uberphones and tablets such as the HTC Sensation and HP TouchPad.

Portable Gaming & Future

Portable gaming is going to pave the way to future. Already Android and iPhone has together eaten the major percentage of mobile market and they would start interfering with consoles next year. Imagine this – plug your mobile to a TV and use it like a console or wirelessly stream video. If not in a year, you would see this in practice 2 years from now.

2012 is the year of Quad cores. Nvidia Tegra 3, Snapdragon S4, and Intel is jumping in too. Apple isn’t holding back either, iPad 3 (or iPad 4) and iPhone 4 are going to be A6 quad core too.

We write latest and greatest in Tech Guides, Apple, iPhone, Tablets, Android,  Open Source, Latest in Tech, subscribe to us@geeknizeron Twitter OR on Facebook Fanpage:

The company believes that Intel’s x86 architecture is built to work for generic applications that are mostly limited to single cores and few threads, they cannot scale well beyond to levels where Intel cannot. Tilera Gx family targets high-throughput applications.

Tile Gx family has 3 flavors 36-core Gx3036, the 64-core GX3064 and the 100-core Gx3100. All of them target high performance multi-core computing designed for high-end web servers & applicatons including vast databases and heavy frameworks.

If the company Tilera is to be believed, the Gx family is at least 10 times power efficient, per-watt. With 100 cores on a single die, the processor consumes less than 48 watts, which is way lower than Sandybridge. Each core rated at less than 0.5 watt is the among the most efficeient processors ever designed for servers.

Tile Gx Family Specs:

• An array of 16 to 100 general-purpose processor cores (tiles)
• 64-bit VLIW processors with a 64-bit instruction bundle
• Three-way pipeline with up to three instructions per cycle
• 32K L1i cache, 32K L1d cache, 256K L2 cache per tile
• Up to 750 billion operations per second (BOPS)
• Up to 200 Tbps of on-chip mesh interconnect
• Over 500 Gbps memory bandwidth with four 64-bit DDR3 controllers

Sandy bridge consumes upto 95W, and Xeon goes upto 130W.

Tilera goes further in criticizing Intel’s upcoming architecture “Knights Ferry n 2012”. They argue that

“an x86 is an x86, whether it’s Atom cores, Pentium cores — the overhead that you’re carrying is the same. You need to carry the overhead to be binary compatible,” Bishara said. “What [Intel] do, even with Atom, is lower the frequency to get lower power and to get more cores in the same chip.”

Tilera’s Gx3036 would become available around July, followed by Gx3064 and Gx3100 in Q1 2012 and stratton 28nm chip in 2012 going upto 200 cores. With the big plans on its line, its already in talks with big cloud players like Amazon, Google, Microsoft.

Tilera is non-x86, but Dev Toolchain would be available

Gx chips are compatible with 2.6.36 kernel release of Linux showing love for CentOS. The applications can be written in any of the popular languages: C and C++, Java, PHP, Perl and Python, which are implemented via a GCC compiler that has been ported to Tilera’s architecture.

Tilera’s Architecture – The secret recipe

The DNA of the multicore super-performance is the way it communicated among multiple-cores. Gx chips pass information between cores via a mesh network, which distributes the cache throughout the processor and allows for multiple connections between individual cores. Applications can access the on-chip network, and can fully use it to communicate between cores, the result is a superior throughput in the IO among the chips, and better cache management as compared to sandybridge.

We do believe that Tilera is bringing some breakthrough improvements in the CPU architecture especially on the server sides. The ultimate question that still remains unanswered is “Will the customers (big cloud players) port apps to a new architecture?, would it be easy enough?”

We write latest and greatest in Tech Guides, Apple, iPhone, Tablets, Android,  Open Source, Latest in Tech, subscribe to us@geeknizeron Twitter OR on Facebook Fanpage:

United States is now owns the fastest SuperComputer, pushing China to the second place, of course leaving Google Plex aside. Very recently, China had pushed Cray XT5 Jaguar to the Rank 2. Although, you can Build yourself Supercomputers, it does cost millions when its built as a nation’s pride.

The Tianhe-1A, meaning Milky Way, was designed by the National University of Defense Technology (NUDT) in China. It is the work of 200 scientists, that makes groundbreaking performance record of 2.507 petaflops, or quatrillion calculations per second, making it the fastest system in the world today. Ordinarily the computer runs at 563.1 teraflops, or trillion calculations per second.

Lets welcome Blue Gene/Q, aka “Mira”,  IBM’s latest and greatest supercomputer boasting a ten-petaflops of raw power. Mira is capable of running programs at ten quadrillion calculations a second.

To give you an idea of how powerful this supercomputer is IBM’s statement tries to explain it:

“If every man, woman and child in the United States performed one calculation each second, it would take them almost a year to do as many calculations as Mira will do in one second.”

Where would the Most Powerful SuperComputer be used?

Mira would be employed with US Department of Energy’s Argonne National Laboratory, where it’ll be used to tackle 16 projects in particular that were drawn from a pool of proposals to gain access to her capabilities. We’re told that these include a range of initiatives — from reducing energy inefficiencies in transportation and developing advanced engine designs to spurring advances in energy technologies — and in time, it could lead to exascale-class computers “that will be faster than petascale-class computers by a factor of a thousand.”

Here are notes from IBM’s press release:

WASHINGTON – 08 Feb 2011: IBM (NYSE: IBM) today announced that the U.S. Department of Energy’s (DOE) Argonne National Laboratory will use IBM’s next-generation Blue Gene supercomputer to enable significant advances in areas such as designing ultra-efficient electric car batteries, understanding global climate change and exploring the evolution of our universe.

The 10-petaflop IBM Blue Gene/Q supercomputer, named “Mira”, will be operational in 2012 and made available to scientists from industry, academia and government research facilities around the world.

“Computation and supercomputing are critical to solving some of our greatest scientific challenges, like advancing clean energy and understanding the Earth’s climate,” said Rick Stevens, associate laboratory director for computing, environment and life sciences at Argonne National Laboratory. “Argonne’s new IBM supercomputer will help address the critical demand for complex modeling and simulation capabilities, which are essential to improving our economic prosperity and global competitiveness.”

Argonne to use IBM Blue Gene/Q

Argonne National Laboratory will use IBM’s next-generation Blue Gene/Q supercomputer to stoke economic growth and improve U.S. competitiveness for such challenges as designing electric car batteries, understanding climate change and exploring the evolution of the universe. The 10 petaflop system, named “Mira”, will be twice as fast as today’s fastest supercomputer, providing a strong science and technology engine that will fuel national innovation. Argonne is one of the U.S. Department of Energy’s oldest and largest labs for science and engineering research, located some 20 minutes outside Chicago, IL (Feature Photo Service).

Mira will offer an opportunity for scientists to become more familiar with the capabilities an exascale machine will offer and the programming changes it will require. For example, scientists will have to scale their current computer codes to more than 750,000 individual computing cores, providing them preliminary experience on how scalability might be achieved on an exascale-class system with 100s of millions of cores.

Once Mira is online, the DOE’s Innovative and Novel Computational Impact on Theory and Experiment (INCITE) and the ASCR Leadership Computing Challenge (ALCC) programs will award blocks of computing time via a peer-reviewed, competitive process to researchers who are working on scientific challenges that are best addressed by the capabilities of high-performance supercomputers.

Blue Gene is one of 100 Icons of Progress in IBM’s 100 year history because it is a radical departure from the supercomputers of its time, consuming only a fraction of the energy and floor space. The system is part of a collaboration between Argonne, IBM and Lawrence Livermore National Laboratory. Blue Gene’s speed and expandability have enabled industry and the scientific community to address a wide range of complex problems and make more informed decisions.

We write about Latest in tech, Google, Green Tech, Gadgets, Open Source, Programming. Grab them all@taranfx on Twitter or below:

Just that you are aware, Texas Instruments’ OMAP3 processor powers Motorola Droid Pro, Droid 2, Palm Pre 2, etc. and OMAP4 powers the BlackBerry Playbook. Now the future is held by Texas Instruments while they raise curtain on OMAP5, with 2Ghz Quad core.

The 28 nanometer OMAP 5 applications processors carry on the OMAP family tradition of delivering significant increases in performance and functionality, while lowering power consumption compared to their predecessors. Specifically, they offer up to 3x processing performance and five-fold 3D graphics improvement, yet provide a nearly 60 percent average power reduction compared to a sample user experience on the OMAP 4 platform. Additionally, the OMAP 5 platform’s software is designed for maximum reuse to ease migration from the OMAP 4 platform.

OMAP5 Specs & facts:

• Core Clock speeds up to 2Ghz Quad core — 2 ARM Cortex-A15 cores capable of speeds up to 2 Ghz, and 2 Cortex-M4 cores
• Lower Power consumption: TI promises processing performance 3x that of OMAP4, all while decreasing average power consumption by 60%.
• TI claims it can support 3 QSXGA displays running at the same time. QSXGA is a resolution of 2560×2048.
• Multiple simultaneous cameras – Ideal for 3D video
• Delivery 2011: mid 2011 production, hits the market around the mid-point of 2012.

via TI

For latest Google, Open Source, iPhone, Android, Tech news @taranfx on Twitter or subscribe below:

Nvidia has plans of leaping the current gen smartphone processors Tegra 2. Within few months, the graphics giant will launch Tegra 2 3D, a 3D version of Tegra 2 with high performance 1.2Ghz dual core processor and 3D display.

At CES 2011 we learned that existing Tegra 2 chips will power flagship Android devices like the LG Optimus 2X and Motorola Atrix 4G smartphones, as well as Motorola’s Xoom tablet.

That’s just a taste of things to come in the near future. Think new breed of portable devices incorporating glass-less 3D displays, Blu-ray support and enhanced graphics, paving the way for stereoscopic 3D gaming, exciting user interfaces and other perks.

Going further, there will be Tegra 3 Quad core Cortex A9 1.5 Ghz CPU with 3x faster graphics, BluRay video, 1900×1200 display. Something of that config is a true desktop replacement.

The ULP designation on this listing stands for Ultra Low Power in NVIDIA parlance, which would indicate an aggressively tuned power management system — the only way we can envision a quad-core anything operating within a tablet. Fall 2011 is when we should know for sure.

For latest Google, Open Source, iPhone, Android, Tech news @taranfxon Twitter or subscribe to us below:

The new Core i3, i5, and i7 processors, will come in 29 new flavors with Integrated graphics options. The new Core processor range is an upgrade from existing Westmere 32nm processor, essentially falling into Intel’s “Tock” development phase in which they improve the performance, features, efficiency on the existing Chip fabrication technique i.e. 32nm.

Whats New in Core 2011 Processors

The new family of processors are all based on Intel’s 32nm microarchitecture and are the first to put the processor, memory controller, and graphics on the same die. This means you will have a smaller package and parts get to take advantage of each other better, e.g. by dynamically clocking both the CPU cores and graphics to match whatever workload you throw at it, and giving them up to 1MB of shared cache. Speaking of those graphics, while they may still not be on par with a discrete video card, they’re more powerful than ever before. According to Intel, the new HD 2000 and 3000 processor graphics provide 2x the performance of Capella-based systems.

Intel has improved its Turbo Boost and Hyper-threading technologies such that the new chips enable higher levels of CPU performance as well — up to a 60 percent improvement with quad-core mobile CPUs.

The performance is not at the cost of efficiency. The new integrated chips reduce power consumption by using a smaller integrated package and can actually switch off components its not using , to improve battery life.

The processor details

Intel is this time looking to satisfy Overclockers with a set of specially-marked overclockable ‘K’ series processors which lets them individually set the clockspeed ratios for each individual core, provided they run on a premium P67 Express motherboard.

New Features in Core 2011 Processors:

Geek part aside, these are the few features every user can understand:

• Intel Quick Sync Video -  Intel’s promising way faster video transcoding with it’s new integrated Quick Sync feature, which does encoding in hardware — it says it will be 17x faster than older generations of integrated graphics. Intel’s partnered with media software companies like CyberLink, Corel, and ArcSoft to enable this hardware-accelerated H.264 and MPEG-2 video conversion.

• Intel InTru 3D / Clear Video HD – 3D Blu-ray playback over HDMI 1.4? Not a problem for Intel’s Core 2011 platform. This doesn’t mean Intel’s providing the 3D technology for laptops or desktops, but it’s promising that you can play stereoscopic 3D and HD content on your TV using HDMI.

• WiDi 2.0 – Our biggest complaints about the original WiDi was the lack of support for 1080p. Well, Intel’s finally enabled streaming of full HD with its latest processors. There’s still lag and you will need to pick up a new TV receiver, most likely a new one from Netgear, to take advantage of the new full HD abilities. We’ve got more details on this and Intel’s new Insider video content service here.

Additional Details:

Related: BIOS death Nears with Sandybridge, UEFI is the Future

We write on Hardware, Open Source, Programming, Tech news, gadgets,  Get them @taranfx on Twitter or Subscribe to us below:

LG Star would be the first android phone with Nvidia Tegra2 dual core processor clocked at 1Ghz x 2. The UI on this phone is much like the Samsung Galaxy S, but the most interesting part of this phone is its dual-core processor.

GSM Israel has got the first handson video for the LGP990 (aka the Star) compared side-by-side with an iPhone 4.

The handset is powered by a 4-inch display and 8MP camera, as well as a front-facing counterpart and an HDMI port. At this time its running on a non-optimized Android Froyo, and is expected to improve speeds with Android 2.3 Gingerbread, which would be optimized for dual core Tegra2 processors.

Nvidia Tegra 2 offers full support for real-time run Full HD 1080p encoding, In terms of build quality, its sturdy,   combines elements of plastics and metal.

The screen is very bright and very high quality and even though it (apparently) is not a Super AMOLED or SLCD.

Despite running non-optimized Froyo 2.2, it is still very fast relative to all other Android device we’ve seen and iPhone 4 at everything. It performs equally well vs. iPhone 4 even when Flash is turned ON. Now that’s a big thing. With Gingerbread, native support for Dual core Tegra2 will be embedded into the kernel, and hence make the dual core phones perform much faster than iPhone 4 or any other device in the market.

For more iPhone, iPhone apps, Tips n Tricks, Android, Gaming, Tech News, catch us @taranfx on Twitter.

Flash Player 10.2 is available for Windows, Mac, and Linux in adobe labs.

Stage Video API — full hardware acceleration for videos

Stage Video API delivers best-in-class, high performance video playback across platforms. Flash Player 10.1 had support for hardware decoding of H.264 content, arguably the most taxing part of playing back video.
The new API uses the GPU rather than the CPU for even more stages (hence the name) of the video rendering pipeline, including color conversion, scaling and blitting. So how much CPU will it use now for playing 1080p HD videos? NIL. Yes, for most cases, when available is fairly good, you will have almost no processing on CPU.

However, to take the full advantage of the Stage API, Content providers have to update their video players. Just because Adobe has good partnership with Google, expect them to be rolling out soon on Youtube and Android. From what we’ve heard it is already available on Google TVs and under test with Youtube.

IE9 hardware acceleration support and multi-monitor support
The new beta also includes Internet Explorer 9 hardware acceleration support , enhanced text rendering, a native custom mouse cursors API and support for full screen playback with multiple monitors.
Flash Player will also use the GPU to render other graphic elements leading to a performance boost of up to 35 percent in some cases. Apart from that, users will be able to watch a full-screen flash content on multiple monitors.

Native custom mouse cursors

Flash developers looking to add more personality to their apps, or just to annoy their users, can now create native custom mouse cursors. This means that they’ll be able to create custom mouse themes which will then be handled natively by the operating system, a much better and faster way to the alternative, rendering a custom cursor inside Flash.

Sub-pixel Text Rendering:

S-pixel text rendering enhances the Font type faces, making them better looking regardless of the fonts or local scripts used. It makes the typography beautiful on just any device.

Flash Player 10.2 Beta for Windows, Linux, Mac is available for download here.

For latest Google, Open Source, iPhone, Android, Tech news @taranfx on Twitter or subscribe to us below:

Although you can Build yourself Supercomputers, it does cost millions when its built as a nation’s pride.

The Tianhe-1A, meaning Milky Way, was designed by the National University of Defense Technology (NUDT) in China. It is the work of 200 scientists,  that makes groundbreaking performance  record of 2.507 petaflops, or quatrillion calculations per second, making it the fastest system in the world today. Ordinarily the computer runs at 563.1 teraflops, or trillion calculations per second.

This giant comfortably costed over $88 million.

Compare this: as of June 2010, the 500 fastest supercomputers in the world combine for 32.4 petaflops of computing power and Chinese new supercomputer does 2.5 petaflops alone.

The whole system weighs 155-ton and is cooled by 103 refrigerator-like cabinets lined up on an area of about 1,000 square meters. The Tianhe-1A will be employed in calculations of seismic data for oil exploration, conduct bio-medical computing and help design aerospace vehicles.

Tianhe-1A is powered by 7,168 Nvidia Tesla M2050 GPUs and 14,336 Intel Xeon CPUs. But the design is intuitive enough to beat 50,000 CPUs & half the floor space.

The second best, Cray XT5 Jaguar system has more than 19000 computers and 224,000 CPUs based on AMDs.

The performance scale was definitely not possible without GPUs. GPUs are redefining high performance computing. With the Tianhe-1A, GPUs now power two of the top three fastest computers in the world today. These GPU supercomputers are essential tools for scientists looking to turbocharge their rate of discovery.

Power Consumption:

Its not worlds Greenest Supercomputer, but Tianhe-1A is energy efficient, saving enough power to provide electricity to over 5,000 homes for a year, Tianhe-1A consumes only 4.04 megawatts, making it 3 times more power efficient compared to a 2.507 petaflop system built entirely with CPUs that would consume more than 12 megawatts. However, affording its yearly bill still means $2.7 million hole.

The battle to build the fastest supercomputer has become a point of national pride as these high performance computers are used in a areas like defense, energy, finance, science. They are also used for drug discovery, hurricane and tsunami modeling, cancer research, car design, and studying the formation of galaxies.

Of the world’s fastest 500 supercomputers, the United States has 291, while Europe has 145 and Asia 49.

UPDATE: World’s Fastest Supercomputer – IBM’s Mira US owns the crown, again.

We write about Latest in tech, Google, Green Tech, Gadgets, Open Source, Programming. Grab them all@taranfx on Twitter or below:

Recently, Snapdragon announced 1.5Ghz DualCore Processor for Smartphones, targeted for the year-end. Looks like the future continues to creep toward us, Marvell announced the first tri-core low-power CPU for mobile phones and tablets.The Processor is capable of encoding and decoding FullHD 1080p video.

Marvell has designed it using ARM v7 MP compatible system-on-a-chip (SoC) which promises better battery life. To save battery, it employs 3 cores –  two 1.5GHz cores for processing power, and a third core optimized for ultra-low power consumption that deals with routine tasks, but can wakeup Dualcores in split seconds, when needed.

The integrated Graphics engine is also powerful enough for most 3D  gaming. The GPU engine can render 200 million triangles per second, and supports all the popular standards — DirectX, Open GL ES 2.0, and Open VG 1.1.

The SoC is powerful that it can drive upto 4 simultaneous displays at up to 2k resolution.

As the company claims:

The new ARMADA 628 tri-core processor incorporates a number of advanced processing and power management features. The tri-core design integrates two high performance symmetric multiprocessing cores and a third core optimized for ultra low-power. The third core is designed to support routine user tasks and acts as a system management processor to monitor and dynamically scale power and performance. The tri-core architecture provides superior performance and lower power over dual-core designs while maintaining industry compatibility and leadership — ensuring a richer, faster and smoother experience than any other ARM-based processor available today.

Up to 1.5 GHz for the two main cores and 624 MHz for the third low power core
“Heterogeneous multiprocessing” with “hardware-based Cache Coherence”
1 MB System Level 2 Cache
Platform leading multimedia capabilities, including support for both WMMX2 and NEON acceleration; and a highly optimized pipelined VFPv3 floating point engine
Member of the ARMADA family of processors for easy software porting
1080p dual stream 3D video applications (30 FPS, multi-format)
Ultimate 3D graphics performance with quad unified shaders for 200 million triangles per second (MT/s)
High performance, integrated image signal processor (ISP)
Ability to project images on multiple simultaneous displays
2 LCDs
1 HDMI
1 advanced EPD controller
Peripherals support: USB 3.0 Superspeed Client, MIPI CSI, MIPI DSI, HDMI with integrated PHY, UniPro, Slimbus, SPMI

So you might be thinking, alright, what’s the deal – Which all Smartphones, Tablets will get it?

Since it uses the industry standard ARM architecture, it would support most of the portable devices int eh market — Android, Blackberry OS, Linux, Windows Mobile (Windows Phone 7) and may be the NextGen iPhone, iPad too.

Today AMD announced speed bumps to nearly every processor in its desktop lineup. Everything from the dual-core Athlon II to the six-core Phenom II gets a new family member today. And they’re all very attractively priced.

Most of these new Phenom II  (6 core, quad core) and Athlon II don’t come with any major changes and hence we can expect the same performance from them, if not more.

New AMD Phenom II X6 1090T (6 cores) is clocked at 3.2GHz with 9MB of cache and can be boosted with TurboCore to 3.7GHz. This chip will have thermal design power rating of 125W and would be available at for $245.

Quad-core Phenom II lineup gets new 970 Black Edition processor that is clocked at 3.5GHz and is priced for $185 . While the dual-core Phenom II X2 560 clocked at 3.30GHz with 7MB cache is price at $105.

On the other hand, Athlon II family of chips gets quad-core Athlon II X4 645 clocked 3.1GHz with 2MB cache and 95W TDP rating. This Athlon II family quad-core chip will cost $122 which is actually bit higher than the Phenom II X2 560 CPU clocked at 3.3GHz. See, this is where AMD tricks you to choose between pricing and performance.

Llano is slated for release near the end of Q2 next year. While it won’t be a big step forward in CPU performance, we should see a huge increase in integrated graphics performance.

AMD Phenom II, Athlon II New Price List

A Third Phenom II X6

The 1075T 3.0 Ghz, priced at $245, can turbo up to 3.5GHz if three or fewer cores are in use. You get a 6MB L3 and a 3MB L2 (512KB per core).

The Phenom II X6 1075T has no competitively priced answer from Intel. The Core i7 860 is priced at $284, while the Core i5 760 will set you back $205. The default clock speed of the 1075T should bring it close to the Core i5 760 in many tasks, while anything threaded will for sure favor the 1075T.

Intel’s cores get better performance per clock, but not that much better. Single threaded performance and power consumption are both better with the Core i5, but the rest all falls in AMD’s favor.

A 3.5GHz Quad-Core

The new Phenom II X4 970 Black Edition pushes quad-core clock speed to 3.5GHz. The 970 ships with all cache enabled, so that’s 6MB L3 and 2MB total L2.

At $185 the Phenom II X4 970 only has to compete with the Core i5 750 or a bunch of dual-core Clarkdale CPUs. Without Hyper Threading, the matchup can be close.

Single threaded performance is close as AMD has a huge clock speed advantage. AMD gets attractive for slightly lower price and better upgrade path as you’ll can stick a Phenom II X6 in the same Socket-AM3 motherboard.

There’s almost a solution for every budget, and its affordable. Will Intel now slash down prices to give AMD some competition?

Related: AMD unveils CPU GPU Fusion [Llano]

We write Latest in Hardware: Intel, AMD, Research,Gadgets: Android, iPhone, Apple, Google and Tech Guides, Tech News @taranfx on Twitter and:

All the work was done under the secret research lab aimed to improve the performance of its existing mainframe systems. The new Fastest processor would become the heart of IBM’s new zEnterprise clocked at 5.2GHz. Although, overclockers can challenge the “Fastest” processor with Liquid Nitrogen cooled systems, But, IBM’s processor is all about at native room temperatures with no special cooling requirements.

This 5.2GHz chip is not about generic x86 PC’s but designed to run on IBM’s mainframes and some unix based AIX systems that barely run UI or any of your hardcore graphics games.

IBM is targeting September 10th for the launch of speedy processor for serious business stakeholders. The system will be suited for heavy workloads that meets the requirements of  banks and Realtime transactional systems and ever increasing Data hungry networks.

The heart of the system is z196 processor Quad core processor  that comfortably integrates 1.4 billion transistors on a 512-square millimeter (mm) die, which is much smaller than a coin (sized at 2.2 x 2.2 cm).

The brilliance has been fabricated using the IBM’s 45 nanometer (nm) SOI processor technology, and it makes use of IBM’s patented embedded DRAM (eDRAM) technology, which allows IBM to place dense DRAM caches, or components, on the same chips as high-speed microprocessors, resulting in improved performance. Adding DRAM on the processor dies has significant benefits. By reducing the effective distance every electrical signal has to travel, the new architecture is able to save time in 10s of nanoseconds, giving it a performance uplift of multiple folds of any x86 processor even when run at same clock

IBM has bravely built a system that incoporates a large number of such processors into a Mainframe. As per what IBM claims, the core server in the zEnterprise System — called zEnterprise 196 — contains 96 of the world’s fastest, most powerful microprocessors, capable of executing more than 50 billion instructions per second. That’s roughly 17,000 times more instructions than the Model 91, the high-end of IBM’s popular System/360 family, could execute in 1970.”

What would it cost? Definitely something sky high, after all it’s comfortably world’s fastest.

We write about Google, Twitter, Security, Open Source, Programming, Web, Apple, iPhone,Android and latest in Tech @taranfx on Twitter or by subscribing below:

Evidently, it’s the one major part of the PC that’s still carried over from the PC’s ancient times,but the familiarly-clunky BIOS could soon be R.I.P., according to MSI. The motherboard makers including MSI vision newer and better replacement for the BIOS. MSI says it’s now making a big shift towards point and click UEFI (universal extensible firmware interface) systems, which is all set for the end of the year.

Though MSI will start to phase in UEFI starting from the end of this year, we can expect it will be widely adopted after three years.

According to the MSI mole, the first new UEFI products will be based on Intel’s Sandy Bridge chipset, featuring in motherboards from low-end budget ones to the top-notch models. After all, its not expensive, yet, more desirable.

Note: Sandybridge is the new Intel Architecture which is essentially successor of Nehalem. Sandy bridge uses 32nm fabrication methods from Westmere, but supports higher cores, bursts with Hyper threading.

UEFI is a continuation of Intel’s original EFI project, which was designed to replace the BIOS with a user-friendly point-and-click interface, as well as addressing many other troublesome areas of the PC’s legacy. 

MSI introduced Click BIOS on a few motherboards based on Intel’s P45 chipsets.

The move to UEFI is now much more important because of its implications for storage coz as Seagate said, UEFI system would be an essential requirement in order for a PC to boot from a drive larger than 2TB.

This is how the MSI UEFI ClickBIOS from 2008 looks like:

The limitation of 2TB is seriously low and would force users to migrate to this  new UEFI. Its obvious that mainstream notebooks will use almost 1TB of storage next year, not to mention desktop systems, so we need to start adoption of UEFI faster than ever.

Implementing a UEFI system isn’t an easy job for motherboard manufacturers used to working with standard BIOS technology, though. The motherboard manufacturers had held off moving to UEFI because of the huge resources you have to throw at it.

Issues with Migration to UEFI

There are a lot of issues to address here:

1. First one is the size: A UEFI system is generally bigger than a traditional BIOS and most of the onboard ROM is not that big, so you can’t flash UEFI into a traditional BIOS board.
2. Limited Mothboard Support:  you have to use certain code with certain motherboards. Here’s Why: Motherboard companies spend a lot of time developing their own features and technology that distinguish their motherboards from those of the competition. If these features are designed to interface with the code in a traditional BIOS, then they may not be able to communicate with a UEFI system. 
3. Programming platform: UEFI is written in C, while BIOS is written in assembly code. But, this means that there’s much more flexibility with the code, it would become much more customizable, hackable to do things which were not easy to do with BIOS before.

UEFI is going under a lot of continuous work, but the final thing would be much more adaptable, customizable, feature-ful, hackable and yet cheap.

via

We write on Hardware, Open Source, Programming, Tech news, gadgets,  Get them @taranfx on Twitter or Subscribe to us below:

Moore’s Law predicts that the amount of memory that can fit on a given area of silicon, for a fixed cost doubles every 12-18 months. The limit of this prediction is being tested as components get ever smaller and their computationally useful properties become less reliable.

Researchers have managed to create a transistor made from just seven atoms. When such technology is used to design computers, the processor would be 1/100th of the size it is today, making it possible to package more transistors on a single chip, and hence increasing the power of computing by several times. The scientists believe that it is also a step towards a solid-state quantum computer.

Basically, Transistors acts as a  tiny switch which becomes the building block of all silicon chips.  However, this transistor is not the smallest ever created as two research groups have previously managed to produce working single-atom transistors, but the latter was never demonstrated to work as effectively as the current one.

The paper is entitled “Spectroscopy of Few-Electron Single-Crystal Silicon Quantum Dots“.

“We are manipulating individual atoms and placing them with atomic precision, in order to make a working electronic device,” elaborated Simmons. “We have replaced just seven individual silicon atoms with phosphorus atoms. That is amazing exactness”.

Modern Chips where components are 22 nanometres in size, transistor gates are about 42 atoms wide. The working transistor was created by replacing seven atoms in a silicon crystal with phosphorus atoms.

This is the world’s first electronic device in silicon systematically created on the scale of individual atoms as per Professor Michelle Simmons, lead researcher on the project at the University of New South Wales.

If an entire chip could be made with every one of its billions of transistors made from the silicon crystals, it could mean an “exponential” leap in processing power.

When?

There’s a long way before these chips commercialize, The current tiny transistor they created was handmade using a scanning tunnelling microscope to move the phosphorus atoms into place.

Although it was first developed in 1981, it uses extremely challenging techniques that require highly clean and stable surfaces, exceptional vibration control, and sophisticated electronics. Simmons’ team is now applying those techniques towards their first quantum computer.

Quantum computing is expected to be the next big scientific leap, and could revolutionize cryptography, weather forecasting, and nuclear modeling amongst other fields.

For latest Open Source, iPhone, Android, Hardware, Tech news @taranfx on Twitter or subscribe below:

AMD Fusion was planned for 2011, but as per today’s announcement, they seem pretty confident that they would be able to deliver Fusion products to system builders within this year. No doubt, AMD has been talking about Fusion for years, and Intel has already taken the lead (only in time) to AMD by launching its Clarkdale Core i3 and Core i5 CPUs with integrated graphics, even though these use separate CPU and GPU dies combined in a single CPU package.

Related: Indepth Tech analysis of AMD’s CPU+GPU Fusion: Llano

AMD however, is determined to combine everything into one piece of silicon that does both General purpose CPU and Graphics. On being asked, How well is this going to be, AMD’s representative Bob Grim replies:

“I don’t think there’s a simple answer to that, if you look at the history of AMD, when we came out with dual-core processors, we built a true dual-core processor. When we came out with quad-cores, we built a true quad-core processor. What our competitors did was an MCM solution – taking two chips and gluing them together.

There was a fair bit of engineering work involved too, but we just have a tradition of building a piece of silicon from the ground up, in fact the only MCM (Multi-Chip Module) solution I’m aware of that we’ve ever done is on the server side with our 12-core product (the Opteron 6174). [Regardless], what we’ll be launching with Fusion is definitely all on one die.”

AMD believes (and which is logically true) that building a CPU/GPU hybrid chip on a single piece of silicon would yield significant speed advantages if not Tremendous. Apart from that, it should have power and performance advantages because it is done with latest 32nm manufacturing process. The Future is Fusion.

Read more about AMD Fusion

For latest Open Source, iPhone, Android, Hardware, Tech news @taranfx on Twitter or subscribe below:

So the processors on the devices are not fully exploited, but with overclocking it is very much possible, but only on jailbroken iPhone/ iPod touch. The processor of the iPhone 2G, 3G is indeed 600MHz, but Apple has underclocked it to 412 MHz only, iPhone 3GS instead of 833 MHz it is operated at 600Mhz. But its easy to run them at their factory clocks.

How to Overclock  CPU on iPhone 2G, iPhone 3G, iPhone 3GS, iPod Touch

Step 1. Make sure you have a Jailbroken iPhone/iPod Touch. (Jailbreaking guides)

Step 2. Using a SSH tool like Filezilla, Navigate to System/Library/System/System Configuration/PowerManagement.bundle/

Step 3. Rename file “com.apple.SystemPowerProfileDefault.plist” to  “SystemPowerProfileDefaultbak.plist” or something that device doesn’t recognize.

Step 4. Reboot, and your iPhone/iPod Touch would Run on native Processor clocks.

Important: Increasing the clock speed would degrade the CPU’s lifespan by several minutes. However, since the device is not designed to handle the heat generated at higher clocks, we recommend you to terminate apps if device appears to overheat. Also checkout tips to Prevent Overheating of iPhone

We write latest in  Google, Android, iPhone and Tech news, Grab them all via @taranfx on Twitter or subscribe below:

ARM currently controls a big piece of the mobile processing market, but Intel is attempting to make a comeback.

To give you an estimate of the power of the new processor, Intel demonstrated Quake 3 running lightning fast (100fps) on one of their custom smartphones powered by Atom-Z (Moorestone), a 45nm chip.

Without a doubt, such performance can also be used to offer flawless smooth HD video output, multitasking apps, and media-rich web browsing giving a desktop-equivalent experience.

Strong on Specs

Chip Power: They run from upto 2.0 GHz and have between 0.65 and 2.0 W TDP rating respectively that can dip down to 0.01 W when idle.

Multithreading, Caches, FSB: It features a 2-issue simultaneous multithreading, 16 stage in-order pipeline with 32 KB instruction L1 and 24 KB data L1 caches, integer and floating point execution units, x86 front end, a 512 KB L2 cache and data transferred at 533 MHz FSB (front-side bus).

Fabrication: The design is manufactured in 9M 45 nm high-k metal-gate CMOS and housed in a 441-ball µFCBGA package

Intel Atom Z vs. ARM Cortex

Intel claims that its latest Atom Z is a better option than popular ARM processors. As per the chip giant, Power consumption is 50x less than current Atom chips, and added advantage being for developers: ” No porting required”, all x86 apps would run as is.

Initially, the Atom Z will be seen in two variants: A 1.5GHz for smartphones, and a 1.9GHz model for Tablet devices, and both platforms run PowerVR 3D graphics acceleration.

Atom-Z Availability

Intel says devices will appear on the market in the 2ndhalf of 2010.

For latest Open Source, iPhone, Android, Hardware, Tech news @taranfx on Twitter or subscribe below:

ARM manufactures high-performance mobile computing chips. Of course, these processors cannot match the performance offered by x86 processors but there’s something that still make them attractive, more attractive than x86 processors for server farms.

ARM’s  CEO Warren East said that servers based on ARM multicore processors should arrive within the next twelve months. The current architecture, designed for client-side computing, can surprisingly be also used in server applications.

Though the implementations of ARM have traditionally been aimed at relatively low performance optimized for minimum power consumption, but, we are seeing higher speed, multicore implementations now pushing up to 2 GHz. ARM’s A9 at 2 GHz has four cores, which makes them a viable candidate for servers. However, the main difference an ARM-based server processor would offer is the addition of high-speed communications interfaces.

No matter how fast these buses are, speed is definitely not an advantage ARM would offer. However, with a growing concern to reduce the amount of energy consumed by servers and server farms, ARM processors offer a great deal, especially the multi-core options in the higher range. ARM might solve part of the problem by offering a Green ServerFarm that would operate at less than 20% of the energy of the current Intel, AMD x86 server processors.

Obviously, we won’t see these processors being deployed in high-performance farms. What looks possible is that it might limit its options to the print and storage server market.

We write about Latest in tech, Google, Green Tech, Gadgets, Open Source, Programming. Grab them all@taranfx on Twitter or below:

We might have adopted quad cores on the desktops, but a new study reveals that human brain is capable of processing  only two tasks at a time, something close to a HyperThreading on a single core processor.

When faced with two tasks, a part of the brain known as the Medial Prefrontal Cortex (MFC) divides so that half of the region focuses on one task and the other half on the other task. This logical partitioning allows a person to get hold of two tasks at a time without affecting much performance. (of course it varies by individual skill). And when we attempt to throw a third task to the brain, its easy to have poor performance in two or all of them.

For instance we can talk on phone while walking in a street or even while working on something on computer. As per the study researcher Etienne Koechlin of the Université Pierre et Marie Curie in Paris, France:

“What really the results show is that we can readily divide tasking. We can cook, and at the same time talk on the phone, and switch back and forth between these two activities. However, we cannot multitask with more than two tasks.”

For the very same reason its discouraged to drive and talk on phone where both tasks use Brain heavily and context switching can cause delays, sometimes. However, listening to music and driving is much safer since listening to music hardly uses the brain.

Multitasking in the brain

Scientists knew that a region at the very front of the brain, called the anterior prefrontal cortex (APC), was involved in multitasking. But they weren’t sure how the MFC was involved.

The research experiment

Koechlin and his colleagues conducted an experiment to study human brain activity in reaction to various situations. The test involved 32 subjects who were give  a letter-matching task while they had scanners attached to their head. These scanners were essentially functional magnetic resonance imaging (fMRI). The subjects were given a set of uppercase letters and task was to determine whether those letters were presented in the correct order in order to spell out a certain word. For every successful attempt, they were awarded with cash.

It was observed, that higher the monetary reward, the more activity there was in the MFC. (That proves the greed lies in Brain and not heart )

The next test made the task more difficult by introducing lowercase letters in addition to uppercase. As a result, brain  had to switch back and forth between matching the uppercase letters to spell out, say, aSmEOwE (Awesome)

During this dual task, the MFC did its job and divided it. One hemisphere of the brain encoded uppercase letter task, and so showed activity during that task, while the other region encoded the reward associated with the lowercase task, Koechlin said.

To test the human brain’s response to three tasks, the researchers introduced a third letter-matching task. The accuracy dropped drastically. Logically, once each hemisphere was occupied with managing one task, there was nowhere for the third task to go. Clearly, The human brain perform as if they systematically forget one of the three tasks.

Brain’s Decision-making

The results also explain why its harder for human brain to make choices between three objects as compare to two.

Human brain is good at remembering two things at a time hence efficiently compare them and make decisions. When  options are multiple, human brain discards the choices by considering two (at max, at a time) until they are left with two and then one.

We write on Hardware, Open Source, Programming, Tech news, gadgets,  Get them @taranfx on Twitter or subscribe below: