Nvidia Tegra 4, leaked information, has 72 graphics cores

Leaked on the net the first image (and all information relating thereto) by Nvidia Tegra 4, the next product System-On-A-Chip Nvidia house. In other words is the processor that will be used on the next generation of smartphones and tablets Android (but not only).

It is a quad core processor (4 +1, as the previous Tegra 3), based on the Cortex A15 with ARM architecture. This is therefore a generation of completely different products, compared to the previous Tegra 3 quad core. This becomes even more obvious when we discover that the graphics processors increased from 12 to around 72.

The production process will then 28nm (the same of Snapdragon S4) and simplifying, we can say that this will ensure an energy saving definitely superior.

This support for resolutions up to 2660 x 1440 pixels, video playback 4K (the future, after the Full HD) and USB 3.0 ports. No mention of LTE connectivity, but will almost certainly be present and simply not mentioned in the leaked slide.

The challenge is now on: Samsung has unveiled its dual-core A15, the version quad-core is arriving ARM is already talked of an A50 (but not before 2014!). They begin the dance for Tegra 4: HTC is really the first to mount it?

source-visit

AMD Piledriver FX: faster than 20% of the Bulldozer

According to reports from Softpedia.com, the next CPU Desktop AMD FX architecture Piledriver will be at least 15% faster than the bulldozer FX solutions. The site dares actually a 20%, a consideration made ​​based on a demonstration by AMD that saw in front of a bulldozer FX-8150 CPU and APU Trinity (think of a 5800K-A10). To have a certain uniformity in the tests, the FX-8150 has been overclocked to 3.8 GHz, disabling two modules for a total of 4 threads.

 

The performance of Trinity were best, with a maximum deviation of 15%, despite the FX-8150 had access to a cache of 8 MB L3 (absent of Trinity). If we think then that will have a significant FX Piledriver L3 Cache, Softpedia calculations may be accurate.

Finally, considering that the AMD FX-8350 will be proposed by the company with an operating frequency higher (you can read AMD FX 8350will have a frequency of 4 GHz ), the performance could be even better, allowing AMD to catch up with Intel .

AMD FX 8350 will have a frequency of 4 GHz?

In recent days we were busy of ' AMD FX 8350 , a CPU-based architecture Vishera that should debut in the third quarter of 2012. The FX 8350 will be a processor with 8-Core Socket AM3 +, built with a 32nm SOI Production Process and native support for DDR3 1866 MHz Memory

 

The SOI process optimization and the results obtained with the new AMD APU Trinity, promise a very high clock frequencies. According to recent rumors, the ' FX 8350 may operate at a base frequency of 4 GHz , a value (if confirmed) considering the Turbo Core functionality will probably reach around 4.6 GHz .

The only question for this processor is currently the TDP, especially considering that the consumption of used, despite the stated 125W AMD, are not so content. The FX-8350 will be the new flagship model for the house Sunnivale and will fight with Ivy Bridge, waiting for confirmations and new information, especially with regard to performance and price.

Represented by the world's fastest single-processor 3D-card - AMD Radeon HD 7970 GHz Edition

As expected , AMD has released a 3D-card AMD Radeon HD 7970 GHz Edition. According to the company, the new product is the world's fastest single-processor 3D-card. Thus, AMD regained title of the world's fastest single-processor 3D-card, was briefly intercepted by NVIDIA.

 

C a technical standpoint AMD Radeon HD 7970 GHz Edition differs from the AMD Radeon HD 7970 , AMD is in December last year opened an era of 28-nanometer GPU, only the high frequencies components. Clock speed GPU Tahiti with 2048 stream processors is equal to 1050 MHz (in the case of AMD Radeon HD 7970 - 950 MHz) RAM - 1500 MHz (AMD Radeon HD 7970 - 1375 MHz).

In the configuration of the product includes 3 GB of memory GDDR5, which are connected with the GPU 384-bit bus. It features proprietary technologies AMD Eyefinity 2.0, App Acceleration and CrossFire. It is equipped with interface PCI Express 3.0.

Sales of AMD Radeon HD 7970 GHz Edition partners AMD, including ASUS, Gigabyte, HIS, MSI, Sapphire, TUL and XFX will begin next week. Price new - $ 499.

Announcement of the co-processors Intel Xeon Phi

During the event, International Supercomputing Conference, Intel announced a brand Intel Xeon Phi, which will be used to refer to all future products on the architecture of Intel Many Integrated Core Architecture (Intel MIC). Deliveries of the first such product shall commence before the end of this year. The first will be a family of co-processors under the symbol Knights Corner. As conceived by Intel, it will complement the family of CPUs, and Intel Xeon E5-2600/4600 will improve performance on tasks with a high degree of parallelism. The first generation of Intel Xeon Phi products will be focused on the use of supercomputers, but in the future, the manufacturer also expects to reach segments of the corporate VC and workstations.

 

The advantages of the Knights Corner Company considers the use of a familiar programming model for developers and compatibility with the tools to develop software for the architecture of Intel.

Co-processors Intel Xeon Phi will not only compatible with the software architecture models, x86, but can also be seen as separate applications to compute nodes, running its own OS based on Linux, regardless of the primary operating system and optimized for parallel computing. According to the manufacturer, it offers a high degree of flexibility in creating clusters, unattainable in the case of decisions based on the GPU.

 

Coprocessor is an expansion card for the bus PCI Express. It is a 22-nanometer chip, "with more than 50 kernels" , in the possession of which is "not less than 8 GB of memory GDDR5». Last year, Intel demonstrated a working one coprocessor Knights Corner , whose performance on the double-precision operations over 1 TFLOPS.

Although the serial products appear only at the end of the year, according to Intel, the first cluster based on Intel Xeon Phi 150 runs and took a position in the list of high-performance computers in the world Top500.

ASUS adds support for Thunderbolt in the board for AMD processors

On the release of its first motherboard with support for Thunderbolt , ASUS announced in May. In these models, Thunderbolt connector located on the edge of the board, next to the terminals of other interfaces. Several other support for Thunderbolt in ASUS motherboards for processors from AMD.

Displayed at Computex model Crosshair V Formula-Z (chipset 990FX + SB950), M5A99FX PRO R2.0 (990FX + SB950), Sabertooth 990FX R2.0 (990FX + SB950) and M5A99X EVO R2.0 (990X + SB950 ) calculated on CPU performance in the AM3 +.

 

A common feature of all these models is the pin with signature TB_HEADER.

 

This connector connects extension card ASUS Thunderbolt EX, is installed in slot PCI Express.

 

The basis of maps Thunderbolt EX, equipped with the interface, PCI Express 2.0 x4, the controller is Intel Cactus Ridge 2C. DisplayPort connects to the input of the output 3D-card.  Source: VR-Zone

The Intel Core i5-3350P will be the 'Hyper Threading

It seems that Intel has plans to release soon a new Processor Core i5-3350P , a CPU-based architecture Ivy Bridge and then built with 22 nanometer manufacturing process. Like his models i5 and Core i5-2380P-2450P, even for the Core i5-3350P is not provided integrated graphics.

The 'i5-3350P is a Quad-Core and will have a core clock of 3.1 GHz (3.3 GHz in Turbo mode), we find onboard 6 MB of L3 cache and Hyper Threading technology support, usually not integrated by the manufacturer on Core i5 models.

According to the source of the Intel Core i-3350P will have a TDP of 69 watts and should reach the market in summer, a solution that, given the specific requirements, may make the throat to many users. Currently we have no information regarding the possible sale price.

Intel has decided to phase out the processor Atom D2700

Intel has published a notice of changes (Product Change Notification, PCN) at No. 111445-00, which states that the range of Atom processor family will leave the flagship model D2700. Moreover, it should be noted, would leave very quickly: the CPU orders will be accepted until June 29, and the last shipment will be held no later than September 28th of this year.

 

Intel Atom D2700, we recall, was introduced in late September last year. CPU is the flagship line of Cedarview-D: it has two cores, supports multi-threading Hyper-Threading and runs at 2.13 GHz. Manufacturer's suggested price of the product to date is $ 52.

Intel processors in overclocking and problems Ivy Bridge

Intel admits the problems of processors Ivy Bridge, caused by the new technology of heat dissipation. The company is know, however, not to be concerned since it is of a different way to produce the processor and therefore can be solved. This could then lead to a new series of processors Ivy Bridge, but there are still news confirmed by the company.

 

In processors Intel Ivy Bridge fact, under the IHS there is a thermal paste instead of a normal welding fluxless used on other processors. This system therefore would not be sufficient to dissipate the heat produced during overclocking sessions, causing instability.

We'll see how the situation will evolve and we'll let you know if we will have updates in this regard.

Intel has acknowledged that Ivy Bridge CPU overclocking hotter than Sandy Bridge

According to sources, Intel acknowledged that the Core of the third generation (Ivy Bridge) to disperse run hotter than their predecessors. Messages that hot new processors began to appear shortly after the premiere April 23 Ivy Bridge .

Ivy Bridge processors have become the world's first 22-nanometer processors. That transition to finer process technology is partly due to increased heat to disperse. The fact that the die is smaller and therefore decreased and the area of ​​its contact with the plate playing the role of the lid of the processor. In other words, increased "heat flux". Another cause of overheating - the refusal of the solder paste in favor of the role of the thermal interface, originally discovered by enthusiasts, and now confirmed by the manufacturer.

 

Specify that a higher temperature is observed only when working at higher frequencies, so to speak ill of the defect. Confirms this, and the manufacturer, saying that the processors' correspond to the expectations of quality and reliability when operating under normal conditions. " Sources: TheInquirer , Overclockers

Processors AMD FX-8150 in the European retail considerably cheaper

Processors AMD FX-8150 can compete with the products of generations of Intel Sandy Bridge, such as the Core i5-2500K, but the output of the Quad desktop processors Intel Ivy Bridge broke the balance in this segment. To remedy the situation and improve the relationship between price and performance of its processors, AMD has slashed prices on the FX-8150 on the European market. As the data sources, price FX-8150 is now starting to EUR 179 (including VAT). Recall, after the October decline , this model has cost 213 euros.

 

Interestingly, the manufacturer changed the packaging of the product. If before the processor AMD FX-8150 was placed in a tin box (top illustration), but now it has given way to more familiar to buyers of a cardboard box (lower illustration).

Obviously, the transition to a cheaper package - one of the reserves to reduce price.

Intel Core i7 3770K Ivy Bridge, the first time to 22 nanometers

After much anticipation and a little snooze, today is finally the day of processors Intel Ivy Bridge , the first ever to be built with 22 nanometer manufacturing process. In the era of communication digital and social networks, has become almost impossible to hide the news, which is why in recent months the information (including details) on the new Intel platform are circulated without problems.

We start by summarizing what are the characteristics Main (already partly known) CPU Intel Core Third Generation.

In the now well-known method of development of the house of Santa Clara, Ivy Bridge belongs to the phase Tick, effectively introducing a new production process, while keeping the same architecture and the same socket with the previous generation of CPUs. In this case, therefore, Ivy Bridge uses a socket LGA 1155, backward compatible with motherboards designed for Sandy Bridge Series 6.

More important news, which we'll do better to follow, are then the new Tri-gate transistor, the graphics component Intel Graphics HD 4000 and the introduction of 7-series chipset.
Before proceeding further it should be noted that, as happened to Sandy Bridge, Intel released on time what we can define (by price) the solution of the mainstream, then remain on site solutions for the band arriving on Extreme LGA 2011 (see Ivy Bridge-E).

Today, April 23, Intel launched a supply of new generation processors, code-named Ivy Bridge. This was reported by a number of foreign online resources, Information on the official website of the company is missing.

From today, Intel will begin deliveries of 13 models of 4-core processors with four cores in a series of Core i5 and Core i7, the bulk of which is designed for desktops and laptops. To supply a new generation of processors with lower ultrabook Intel plans to begin later, but before the end of spring. Many analysts expect seriously that Apple will not resist the temptation to use the chips in the first wave of an updated line of MacBook Pro.

Ivy Bridge processors have several important innovations. First, these are the first chips, which are made on the basis of 22-nm process. Secondly, this is the first processor, which incorporates "three dimensional" transistor made by technology Intel 3D Tri-Gate.

Unlike conventional transistors, 3D Tri-Gate valve is a three-dimensional structure, increasing the area through which the electrons move. This reduces the drive current and, consequently, the leakage current. At Intel, the transition to such semiconductors are called revolutionary because, according to company representatives, to no one involved in mass production of transistors.

It is noted that the processors Ivy Bridge is 20% faster than previous generation chips while consuming 20% ​​less energy. By analogy with Sandy Bridge processors in the new graphics cores are placed directly on the same chip as the main computational kernel. It is reported that "the people who use integrated graphics solutions, along with the new chips will be one of the most tangible benefits." In addition to working with Full HD-video, these include a more rapid conversion of videos.

Note that in 2013 replaced the Ivy Bridge processors come Haswell , in which the corporation plans to 20 times better performance of energy consumption in standby mode. The company expects that this improvement will be equivalent to 10 days of the laptop in standby mode, if you have a permanent network connection.

Ivy Bridge-EP/EX Preview: 15 core?

Ivy Bridge will soon be released. Although there 22nm process, native USB 3.0/PCI-E 3.0, many new bright spot, but stagnant for the pursuit of high-standard hardware players, four core, 8MB L3 cache seems I could not get the nature of . Well, look at the server field of the dual Ivy Bridge-EP, four Ivy Bridge-EX is how? The fastest within a year you can see them.

 

Ivy Bridge-EP is obviously the successor of Sandy Bridge-EP, still uses the LGA2011 package interface , named will continue to be included in the Xeon the E5 sequence, have up to 10 core, 25MB L3 cache (say 30MB, but it seems do not fly), the frequency will increase by 15-20% .

22nm import of new technology is expected to resolve troubled Sandy Bridge-EP, the high power consumption, high heat, not only a higher frequency of high-performance version will have lower power consumption, energy-saving version is expected to 95W, 130W, 150W can see the three grades of thermal design power, respectively, 2.4GHz, 3.0GHz, 3.3GHz around ten-core models.

The same time, the desktop the fever platform of Ivy, Bridge-E can also expect the eight-core and even 10-core model , not content with "mere" six core Core i7-3960X players blessed.

Ivy, Bridge-EP, with the chipset will Patsburg C600, but the stepper should be updated, SAS the 6Gbps the class will cease to exist, but to look at the Intel can perfect solution to the storage controller.

Ivy Bridge-EX look for four large-scale server and data center, which is a new generation of the Xeon the E7 - and so on, one or Westmere-EX, then the middle of the Sandy Bridge-EX Where to go? Sorry, it does not exist. Before the arrival of the 22nm process, the more cores, cache, features stuffed together is too difficult, Intel simply skip this step, but with the time of the Ivy, Bridge-EP, will be closer.

Ivy Bridge-EX core of a very strange number, instead of the traditional multiple of 2, but 15. Intel Why do so in the end is how to do, or even intelligence, or perhaps the final 16-core yet clear.

Each core corresponding to the L3 cache or 2.5MB , but the frequency will be lower than the Ivy Bridge-EP a lot, estimated that no more than 2.4GHz (currently top of the Xeon the E7-4870 this speed). Memory controller will be integrated into four, with expandable memory buffer chip supports eight-channel DDR3-1600 memory, the maximum capacity of 1.5TB (four is 6TB).

QPI bus is 23 , two more than the Ivy Bridge-EP Westmere-EX, but less than four. Three QPI bus for the four-way system, just not too much, but if you want the outside to join the MIC all the core architecture to calculate the expansion of the cards and the like, and then to make a detour, and will naturally increase delay. Taking into account the future Haswell-EX the Braodwell-EX will follow the same platform as the QPI bus limit some really justified.

Intel 22nm to find a third OEM customers

Silently between Intel's OEM business is growing up. Archronix, Tabula, a leading manufacturer of flow processor (flow processors all the) Netronome today became the Intel 22nm process customers. Netronome said that based on the strategic partnership with the Intel Custom Foundry, the two sides will jointly offer the world's first 3-D of the Tri-Gate transistor technology flow processor , have revolutionized the performance of network and security applications, mid-stream processor , power and cost targets, in particular, the performance will reach the highest of similar products.

Of Netronome, Intel also OEM launched a very in-depth cooperation, involving wafer optimization, equipment, packaging, assembly and testing, worked together to accomplish the high quality of design for manufacturing (DFM), the test design (DFT), reliability design (DFR).

The Netronome stream processors manufactured by Intel 22nm process is expected to pilot production in 2013 , mass production and shipping dates to be determined.

The Netronome a fabless semiconductor company, the main product solutions include stream processing silicon, software, tools, and acceleration platform, speed 200Gbps-ranging, its customers are telecom operators and large communications companies around the world.

TSMC is having difficulty with the release of 28-nanometer production

According to industry sources, the world's largest contract manufacturer of semiconductor products TSMC is having difficulty meeting demand for 28-nanometer products. The main customers are companies TSMC Qualcomm, AMD and NVIDIA. It is believed that the situation will improve in the third quarter of this year.

However, Qualcomm agreed to transfer part of their orders for ARM processors for the company United Microelectronics (UMC), because the volume of products manufactured by TSMC, is not enough for the rapid market of smartphones and tablets.

AMD has introduced the first graphics accelerator based on a 28-nanometer GPU at the end of last year, but shipments family of video cards Radeon HD 7000 is still quite small.

NVIDIA has managed to release two cards based on 28-nanometer GPU Kepler: GeForce GTX 680 desktop PCs and GeForce GT 640M mobile, but, apparently, will also be forced to postpone plans.

For this reason, TSMC is considering the expansion of production . Construction of a new line in the factory Fab 14, which works with 12-inch (300 mm) plates, will begin April 9. Total for the year 2012 the company plans to increase production by 10%.

Issue APU AMD Trinity is scheduled for May 15

While Intel processors occupy first place in the niche of high-performance processors, AMD has an opportunity to compete for leadership in the middle class.

On the slide, AMD indicated that the new APU Trinity is 29% better performance and a 56% superior to the graphics processor of the APU Llano. Also there is information regarding the optimization of APU Trinity for the future of Windows 8.

The new processors will support a more advanced version of the dynamic overclocking technology - Turbo Core 3.0. A mobile version processors allow more efficient use of battery power, which enables mobile devices to work over 12 hours.

There will also be HD Media Accelerator - a set of algorithms that will improve the image quality.

According to sources, the first model of the family will come May 15, 2012. by 

Intel Ivy Bridge: new rumors on prices

A loose retailer in Singapore has published an 'attractive offer concerning the upcoming Intel Ivy Bridge, bundled with a lot of tab mother . We are offering a series chipset motherboard with 6 or 7 (both with socket LGA 1155) coupled with a processor Ivy Bridge Core i7 or Core i5.

The table shown below, if confirmed (considering change), confirming the rumors that Intel was going to propose the new processors at very competitive prices. 

The flagship Core i7 3770K it has a minimum cost of $ 506 in Singapore with a lot of motherboard Gigabyte GA-H61N, the cost is of $405 US Dollars.

Ivy Bridge Intel Core i7-3770K overclocked to 7 GHz

On site Expreview appeared some screen showing the new processor Intel Core i7-3770K Ivy Bridge to grips with some overclocking sessions. A user of the forum has shown that it is very easy to increase the frequency of this processor, using, a relatively low voltage.

The CPU can reach 4.5 GHz with 1.1 V, the 5 GHz with 1.17 volts and then the 7 GHz 1.889 V, the latter result is obtained naturally cooled with liquid nitrogen, but the thing " positive "is that everything was possible without disabling the Core.

So overclockers and performance enthusiasts will be happy and patients to get their hands on this gem.

Intel Core i7-3820 Sandy Bridge-It is available from February 13

Intel to deliver the new processor, Core i7-3820 from 13 February. Recall that this CPU belongs to the family Sandy Bridge-E LGA 2011, but unlike the high-end solutions 3960X and 3930K has 6 Core architecture but rather to 4.

The Core i7-3820 supports Hyper-Threading has 10 MB of cache, controller for DDR3 Memory Dual-Channel and base frequency of 3.6 GHz is the TDP of 130 watts. Intel CPU will propose that $ 285, price in quantities of 1000 units.

AMD Bulldozer FX: Good sales, stops the production of the Phenom II

Despite the enthusiast user does not have appreciated fully the absolute performance of the new AMD FX (you can read  Review:AMD FX-8150, 8 Core 3.6 GHz ), sales of the first units arrived in the shop and the stocks OEMs have clocked good numbers, facts already running out of stocks available.

AMD has so much steel and copper alloys of a request processor architecture Bulldozer FX in addition to that of the Llano chip platform. This strong demand seems to have brought home to Sunnyvale to stop the production of the Phenom II and Athlon II.

This move, taken from the site Nordichardware, may not be well accepted by users who look at absolute performance, in particular also because we remember that the Phenom II X6 gave a hard time with the new FX especially in multi-threaded applications.

In short, a choice that can be criticized but that in a market perspective it seems quite logical as the AMD FX high-end models allow the manufacturer a much higher gain.