WebProNews

Tag: cpu

  • Intel CEO: Tiger Lake Will Deliver 20% More Performance

    Intel CEO: Tiger Lake Will Deliver 20% More Performance

    Intel launched their 10nm Tiger Lake CPU today increasing product performance by 20 percent. “Our 10-nanometer process that our Tiger Lake product will run on today is a step function improvement from the 10-nanometer process we launched just last year,” says Intel CEO Bob Swan. “Its process will deliver 15 to 20 percent more performance in the products that we are launching. At the end of the day, product performance is what matters most to our customers.”

    Bob Swan, CEO of Intel, discusses the launch of their 10nm Tiger Lake CPU which provides a significant improvement in product performance:

    Product Performance Is What Matters

    The PC is a more and more an essential ingredient of our everyday lives. Whether you are studying from home, working from home, and trying to stay connected from home, it’s just more important. The Tiger Lake product that we are launching today, in essence, addresses those activities that we are doing. Whether it’s content creation, inherent productivity, or connectivity, it addresses those key things that are becoming more relevant in terms of how we engage with our PC and how we engage with each other.

    At the end of the day, product performance is what matters most to our customers. Under that umbrella, there are multiple things that have evolved over time. Process continues to be very important. Packaging becomes more relevant as we pull different technologies together. Software plays an increasingly important role. The technologies required to build a computer today are much different than they used to be. With Tiger Lake, it’s not just about the CPU or the microprocessor, it’s about the WiFi. Connectivity is so important, upgrading WiFi, and upgrading graphics capabilities, The nature of the PC today and how it’s evolved incorporates more technology. Where process continues to be important, it’s not relatively as important as it once was.

    Tiger Lake Will Deliver 20 Percent More Performance

    The naming convention over time has lost its relevance. It’s become less of a technical articulation of capabilities and a little bit more of a marketing articulation. Our 10-nanometer process that our Tiger Lake product will run on today is a step function improvement from the 10-nanometer process we launched just last year. Its process will deliver 15 to 20 percent more performance in the products that we are launching. It’s a very exciting time not just because of the Tiger Lake product (the CPU) but how we’ve coupled it with other technologies to address the most top of mind experiences with advanced processing technology that we refer to as SuperFin.

    The relative importance of graphics and the role that it plays, not just in gaming but in communications today is so much higher. That’s why with this product launch the enhanced capabilities of our integrated graphics is a real big bump in overall performance. It’s also an increasingly relevant technology and capability in today’s PC. In essence, the use of the PC and what the graphics technology we’ve built into this product does is rising the role that the PC will play as it become more and more an essential ingredient in our everyday lives.

    There Will Be Significant Demand For Tiger Lake

    Over the last several years we’ve added $20 billion in revenue to the size of the company. From our PC, our internet of things, our communication, and from our cloud businesses, we’ve experienced dramatic growth. It was critical for us to keep pace in ensuring that we have the capacity and the supply to deal with that growth. We’ve made tremendous progress at the end of last year and through the first six months of this year getting that capacity in place.

    For both 14-nanometer, which today is the lion’s share of the products we are shipping, but increasingly we are adding capacity. We expect there will be significant demand for the new product that we announced today but also the new products that we have coming in the second half of this year, particularly in the server Xeon chip.

    https://youtu.be/PMAi5lXMkXA
    Intel CEO Bob Swan: Tiger Lake Will Deliver 20% More Performance
  • Google and NVIDIA Partner to Bring A100 to the Cloud

    Google and NVIDIA Partner to Bring A100 to the Cloud

    Google Cloud has become the first cloud provider to offer NVIDIA’s new A100 Tensor Core GPU.

    NVIDIA made a name for itself making high-powered graphics processing units (GPU). While many people associate GPUs with gaming and video, since NVIDIA’s GeForce 8 series, released in 2006, GPUs have been making inroads in areas traditionally ruled by the central processing unit (CPU). Because of the GPU’s ability to handle large quantities of parallel data, they are ideal for offloading intensive operations, including machine learning and artificial intelligence.

    The new A100 is designed with this in mind. Built on the NVIDIA Ampere architecture, the A100 boasts a 20x performance improvement for machine learning and inference computing. This represents the single biggest generational leap ever for NVIDIA.

    “Google Cloud customers often look to us to provide the latest hardware and software services to help them drive innovation on AI and scientific computing workloads, ” said Manish Sainani, director of Product Management at Google Cloud. “With our new A2 VM family, we are proud to be the first major cloud provider to market NVIDIA A100 GPUs, just as we were with NVIDIA T4 GPUs. We are excited to see what our customers will do with these new capabilities.”

    This will likely be a big hit with Google’s customer base, especially since machine learning support is an area where Google Cloud is particularly strong.

  • Arm Holdings Opens Its CPU Cores to Allow Custom Instructions

    Arm Holdings Opens Its CPU Cores to Allow Custom Instructions

    Forbes is reporting that Arm Holdings has taken a major step toward helping its processors compete even better and make them more appealing to customers.

    Arm designs processors and then licenses those designs to companies for use in their products. ARM CPUs are used across the entire computing spectrum, although they are most widely used in mobile devices, such as phones and tablets.

    According to Forbes’ report, Arm announced that it is opening its CPU cores to allow licensees to add custom instructions via a special block that’s integrated into the CPU’s cores. This will allow licensees to optimize chips for power, energy, differentiation and reduced costs. Best of all, thanks to how Arm is implementing the custom instructions, the reliability, security and predictability of the processors is unaffected.

    This will be a boon to companies who want the benefits of utilizing an existing design—rather than starting from scratch—but need more customization than is offered by standard, third-party chips.

    The first chip with the new capability, the Cortex M33, is due out in 2020.

  • Qualcomm Snapdragon 410 Is The First 64-Bit CPU For Android Devices

    Earlier this year, Apple introduced the first 64-bit CPU for a mobile device with the A7 chip found in the iPhone 5S and iPad Air. At the time, many wondered when Android devices would start to see 64-bit CPUs. Well, wonder no more as the world’s biggest manufacturer of Android SoCs has announced its first 64-bit CPU.

    Qualcomm announced a new SoC today called the Snapdragon 410 and claims its the first 64-bit CPU built for Android devices. As the number implies, the Snapdragon 410 is an improvement on last year’s low-cost Snapdragon 400 CPU. This means that the 410 will be heading to emerging markets where the 410 will provide better performance and LTE to low-cost devices.

    “We are excited to bring 4G LTE to highly affordable smartphones at a sub $150 ( ̴ 1,000 RMB) price point with the introduction of the Qualcomm Snapdragon 410 processor,” said Jeff Lorbeck, senior VP and COO of Qualcomm Technologies in China. “The Snapdragon 410 chipset will also be the first of many 64-bit capable processors as Qualcomm Technologies helps lead the transition of the mobile ecosystem to 64-bit processing.”

    As Lorbeck said, the Snapdragon 410 is only the first of many 64-bit processors to be hitting Android devices next year. While we don’t have any word on when we’ll start seeing more powerful 64-bit processors, I’m willing to bet we’ll hear more at CES in early January. After all, phone manufacturers will want to show off their new flagship devices complete with 64-bit CPUs to drum up excitement ahead of their launches in the middle of next year.

    Going back to the Snapdragon 410, when can we expect to see it in devices? Qualcomm says it will begin shipping to OEMs in the first half of 2014 and will begin appearing in devices after summer. We’ll hopefully see more powerful CPUs from Qualcomm appearing in devices at that time as well.

    [Image: Qualcomm]
    [h/t: Droid-Life]

  • Qualcomm Announces Snapdragon 805, Can Playback 4K Video

    4K video, or “Ultra HD,” is going to be the standard in a few years thanks to increased availability of 4K displays. It might even become standardized even faster if Qualcomm has anything to say about it.

    Qualcomm announced today a new SoC – the Snapdragon 805 – that’s meant to be the successor to its Snapdragon 800 CPU. The major focus of this new SoC is graphics processing thanks to it being equipped with the new Adreno 420 GPU which allow devices with the Snapdragon 805 to playback 4K video.

    “Using a smartphone or tablet powered by Snapdragon 805 processor is like having an UltraHD home theater in your pocket, with 4K video, imaging and graphics, all built for mobile,” said Murthy Renduchintala, executive vice president, Qualcomm Technologies, Inc., and co-president, QCT. “We’re delivering the mobile industry’s first truly end-to-end Ultra HD solution, and coupled with our industry leading Gobi LTE modems and RF transceivers, streaming and watching content at 4K resolution will finally be possible.”

    Beyond 4K video, the Snapdragon 805 will introduce a number of new features that will make Qualcomm’s latest chip one of the most powerful pieces of silicon to hit devices next year:

  • Blazing fast apps and web browsing and outstanding performance: Krait 450 quad-core CPU, the first mobile CPU to run at speeds of up to 2.5 GHz per core, plus superior memory bandwidth support of up to 25.6 GB/second that is designed to provide unprecedented multimedia and web browsing performance.
  • Smooth, sharp user interface and games support Ultra HD resolution: The mobile industry’s first end-to-end Ultra HD solution with on-device display concurrent with output to HDTV; features Qualcomm Technologies’ new Adreno 420 GPU, which introduces support for hardware tessellation and geometry shaders, for advanced 4K rendering, with even more realistic scenes and objects, visually stunning user interface, graphics and mobile gaming experiences at lower power.
  • Fast, seamless connected mobile experiences: Custom, efficient integration with either the Qualcomm Gobi MDM9x25 or the Gobi MDM9x35 modem, powering superior seamless connected mobile experiences. The Gobi MDM9x25 chipset announced in February 2013 has seen significant adoption as the first embedded, mobile computing solution to support LTE carrier aggregation and LTE Category 4 with superior peak data rates of up to 150Mbps. Additionally, Qualcomm’s most advanced Wi-Fi for mobile, 2-stream dual-band Qualcomm VIVE 802.11ac, enables wireless 4K video streaming and other media-intensive applications. With a low-power PCIe interface to the QCA6174, tablets and high-end smartphones can take advantage of faster mobile Wi-Fi performance (over 600 Mbps), extended operating range and concurrent Bluetooth connections, with minimal impact on battery life.
  • Ability to stream more video content at higher quality using less power: Support for Hollywood Quality Video (HQV) for video post processing, first to introduce hardware 4K HEVC (H.265) decode for mobile for extremely low-power HD video playback.
  • Sharper, higher resolution photos in low light and advanced post-processing features: First Gpixel/s throughput camera support in a mobile processor designed for a significant increase in camera speed and imaging quality. Sensor processing with gyro integration enables image stabilization for sharper, crisper photos. Qualcomm Technologies is the first to announce a mobile processor with advanced, low-power, integrated sensor processing, enabled by its custom DSP, designed to deliver a wide range of sensor-enabled mobile experiences.

    • So, when can you expect to see the Snapdragon 805 in devices? Qualcomm says it’s currently in sampling which means you should start to see it pop up in mobile devices in the first half of 2014. We’ll hopefully see some demos of the new 805 in action at CES or Mobile World Congress early next year.

    [Image: Qualcomm]

  • Apparently, Mobile CPU Performance Is Just Like Playing Guitar Hero

    Qualcomm CPUs are in pretty much every major smartphone available today. There’s a good reason for that – they’re damn good CPUs. That doesn’t mean there aren’t other good CPUs out there, but Qualcomm thinks it still has the best around.

    In a new video released this week, Qualcomm explains how its quad-core CPUs outperform the competition’s octa-core CPUs. But wait, eight cores are better than four cores, right? That would be the case if the octa-core processors were using the latest technologies. According to Qualcomm, it’s competition, in this case MediaTek, is using older ARM CPUs while its latest quad-core CPUs are using the latest technology to provide faster speeds over previous SoCs.

    All of the above is illustrated in a “battle of the bands” using a Guitar Hero like UI. It’s pretty strange, but it gets the point across – the Qualcomm SoCs are faster than the competition by a long shot.

    There’s some truth to this as faster clock speeds can beat out more cores if the apps in question aren’t optimized to use more cores. Once octa-cores become commonplace, however, apps will start to distribute their tasks among all the cores for increased performance. Of course, Qualcomm will have introduced octa-core SoCs by then and will release another ad lambasting the competition. Let’s just hope they reference something a little more recent.

    [Image: QualcommVlog/YouTube]
    [h/t: Engadget]

  • Intel Could be Ditching Atom Branding [RUMOR]

    A new report from Taiwanese news outlet DigiTimes states that Intel is “considering” ditching the Atom brand name. The publication’s unnamed sources “from the upstream supply chain” stated that the decision may be based on the growing impression of Atom processors as low-end, having become associated with the sometimes low-quality products they can be found in.

    The report goes on to say that Intel actually believes that shipments of Atom-powered smartphones and tablets may have been negatively affected due to the Atom brand’s “negative image.” The low-power Atom processors can be found in smartphones, tablets, netbooks, and a variety of other portable devices. Last last year Intel even introduced a server-class Atom processor aimed at datacenter clients.

    The change in branding from Atom could begin as early as the fourth quarter of 2013, according to DigiTimes. This will be around the same time Intel is releasing its new Haswell-branded Pentium processors for the PC market.

    These rumors come just as Intel CEO Brian Krzanich called Atom processors “Intel’s future” in a statement accompanying the company’s second quarter earnings report.

    “Looking ahead, the market will continue buying a wide range of computing products,” said Krzanich. “Intel Atom and Core processors and increased SOC integration will be Intel’s future. We will leave no computing opportunity untapped. To embrace these opportunities, I’ve made it Intel’s highest priority to create the best products for the fast growing ultra-mobile market segment.”

    (via DigiTimes)

  • Intel Introduces Low-Power Server-Class Atom Processor

    The Intel Atom processor is the company’s ticket into the lucrative tablet and smartphone market. It’s slowly working its way into more mobile devices, but Intel will now offer its low-power processing solution to servers as well.

    Intel announced today that its Atom S1200 is the world’s first 6-watt server-class processor. It’s a system on-chip processor that features lower-power levels, error code correction, 64-bit support and virtualization technologies.

    “The data center continues to evolve into unique segments and Intel continues to be a leader in these transitions,” said Diane Bryant, vice president and general manager of the Datacenter and Connected Systems Group at Intel. “We recognized several years ago the need for a new breed of high-density, energy-efficient servers and other datacenter equipment. Today, we are delivering the industry’s only 6-watt SoC that has key datacenter features, continuing our commitment to help lead these segments.”

    As for the processor itself, it will feature two physical cores and total of four threads enabled with Intel’s Hyper-Threading technology. It also supports up to 8GB of DDR3 RAM and eight lanes of PCI Express 2.0 devices. As for x86 software, the new processors will continue to support legacy applications that are still used in datacenters today.

    The new Atom processors are just the start for low-power servers. Intel is now working on an Atom successor named Avoton that will be available next year. It will feature even further SoC capabilities and use Intel’s 3D Tri-Gate 22nm transistors.

    As for those who prefer Intel’s Xeon processors, the company will be out with a new version of its most popular server processor as well. The new Xeons will be based on the company’s Haswell architecture and feature new energy-saving options.

    Customers can start ordering the new Atom S1200 processor today starting at $54 in quantities of 1,000. Find more information here.

  • Intel CEO Says Windows 8 Isn’t Ready For Release [Rumor]

    We’re a little over a month away from the launch of Windows 8 on October 26. It’s the biggest change for the Redmond-based company since the launch of Windows 95. A lot is riding on this launch and Microsof has been pushing the operating system as hard as they can. Intel has been pushing right alongside them, but the processor maker may not be as confident in Windows 8 as Microsoft is.

    Bloomberg reports that Intel CEO Paul Otellini recently spoke to employees in Taiwan about Windows 8. The CEO reportedly said that Windows 8 isn’t ready for release according to a person who was in attendance. If Windows 8 truly isn’t ready, the release could turn into a fiasco similar to the debacle that was Windows Vista.

    Still, Otellini was reportedly optimistic about the future of the company. He noted that processor sales were down due to lackluster demands for PCs, but he expected the market to grow in 2013. He also said that the company will not have to lay off workers.

    Intel has been pushing a little into the mobile market, but the company is still primarily dedicated to the desktop computing scene. Intel processors can be found in just about every pre-built Windows PC with enthusiast PC builders also turning to the company for their top-of-the-line i7 CPUs.

    The company may seem some success late this year and early next year as its processors will be used in a variety of Windows 8 tablets. Microsoft’s Surface tablet will launch with an ARM-based CPU this year, but next year’s Windows 8 Pro Surface will feature an Intel-based CPU. Other tablet manufacturers are also turning to Intel to power their mobile experience.

    It’s safe to say that Intel should be fine going into next year. They are moving into mobile, and Intel’s chips have been historically better than the competitions. The only problem they will have going forward is reducing the price of their CPUs. Otellini’s comments, however, add more anxiety to the already worrisome launch of Windows 8.

  • CPU Gets 20% Performance Boost With New Configuration

    CPU Gets 20% Performance Boost With New Configuration

    Researchers from North Carolina State University have developed a new technique that allows graphics processing units (GPUs) and central processing units (CPUs) on a single chip to collaborate – boosting processor performance by an average of more than 20 percent. Processor speed is one of the main stats that developers and consumers look at in making buying decisions.

    GPUs were initially designed to execute graphics programs, and they are capable of executing many individual functions very quickly. CPUs, or the “brains” of a computer, have less computational power – but are better able to perform more complex tasks.

    CPUs and GPUs fetch data from off-chip main memory at approximately the same speed, but GPUs can execute the functions that use that data more quickly. So, if a CPU determines what data a GPU will need in advance, and fetches it from off-chip main memory, that allows the GPU to focus on executing the functions themselves – and the overall process takes less time.

    In preliminary testing, the team found that its new approach improved fused processor performance by an average of 21.4 percent. This approach has not been possible in the past because CPUs and GPUs were located on separate chips.