Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
Compare cell phone plans using Wirefly's innovative plan comparison tool ×

Submission + - AMD Unveils Zen Processor Details, Benchmark Showdown Versus Intel Broadwell-E (hothardware.com)

MojoKid writes: AMD has been talking about the claimed 40% IPC (Instructions Per Clock) improvement of its forthcoming Zen processor versus the company's existing Excavator core for ages. Zen's initial availability is slated for late this year, with lager-scale roll-out planned for early 2017. However, last night, at a private press event in San Francisco, AMD unveiled a lot more details on their Zen processor architecture. AMD claims to have achieved that 40 percent IPC uplift with a newly-designed, higher-performance branch prediction and a micro-op cache for more efficient issuing of operations. The instruction schedule windows have been increased by 75% and issue-width and execution resources have been increased by 50%. The end result of these changes is higher single-threaded performance, through better instruction level parallelism. Zen's pre-fetcher is also vastly improved. There is 8MB of shared L3 cache on board now, a unified L2 cache for both instruction and data, and separate, low-latency L1 instruction and data caches. The new archicture offers up to 5x the cache bandwidth to the cores versus previous-gen offerings. However, after all the specsmanship was out of the way, AMD actually showcased a benchmark run of an 8-core Zen Summit Ridge procesor versus Intel's Broadwell-E 8-core chip, both running at 3GHz and processing a Blender rending workload. In the demo, the 8-core Zen CPU actually outpaced Intel's chip by a hair. Blender may have been chosen for a reason but this early benchmark demo looks impressive for AMD and its forthcoming Zen architecture.

Submission + - Intel Unveils Project Alloy Merged Reality Wireless Headset (hothardware.com)

MojoKid writes: Intel CEO Bryan Krzanich took to the stage at the Moscone Center in San Francisco today kick off this year's Intel Developers Forum. Kyrzanich unveiled a number of new projects and products including a product code named "Project Alloy." The device is an un-tethered, merged reality Head Mounted Device (HMD) that combines compute, graphics, multiple RealSense modules, various sensors, and batteries into a self-contained headset that offers a full six degrees of freedom. Unlike the Oculus Rift and HTC Vive, Project Alloy does not need to be wired to a PC or other device and it does not require externally mounted sensors to define a virtual space. Instead, it uses RealSense cameras to map the actual physical world you're in while wearing the HMD. The RealSense cameras also allow the device to bring real-world objects into the virtual world, or vice versa. The cameras and sensors used in Project Alloy offer full depth sensing, so obstacles can be mapped, and people and objects within camera range – like your hand, for example — can be brought into the virtual world and accurately tracked. During a live, on-stage demo performed by Intel's Craig Raymond, Craig's hand was tracked and all five digits, complete with accurate bones and joint locations, were brought into the the VR/AR experience. Project Alloy will be supported by Microsoft's Windows Holographics Shell framework.

Submission + - NVIDIA Drops Pascal Desktop GPUs Into Laptops With Mobile GeForce GTX 10-Series (hothardware.com)

MojoKid writes: NVIDIA's new Pascal core graphics architecture is being driven throughout the company's entire product portfolio, as is typically the case. Today, NVIDIA brings Pascal to notebooks with the introduction of the NVIDIA Mobile GeForce GTX 10-Series. What's interesting is that the first laptop-targeted GPUs are actually quite similar to their desktop counterparts. In fact, all three of the Mobile GeForce GTX 10-Series graphics processors NVIDIA is announcing today come sans the traditional "M" tacked on the end of their model numbers. As it turns out, the migration to a 16nm manufacturing process with Pascal has been kind to NVIDIA and the Mobile GeForce GTX 1080 and Mobile GeForce GTX 1060 have nearly identical specs to their desktop counterparts, from CUDA core counts, to boost, and memory clock speeds. However, the Mobile GeForce GTX 1070 actually has a few more CUDA cores at 2048, versus 1920 for the desktop GTX 1070 (with slightly lower clocks). By tweaking boost clock peaks and MXM module power requirements, NVIDIA was able to get these new Pascal mobile GPUs into desktop replacement class machines and even 5-pound, 15-inch class standard notebook designs (for the 1060). In the benchmarks, the new Mobile GeForce GTX 10-Series blows pretty much any previous discrete notebook graphics chip out of the water and smooth 4K or 120Hz gaming is now possible on notebook platforms.

Submission + - NVIDIA's Pascal-Based Titan X Tested, Expensive But Dominates Benchmarks (hothardware.com)

MojoKid writes: NVIDIA took the wraps off its new Pascal-based, flagship graphics card, dubbed the Titan X, a couple of weeks ago, but only pictures and specifications were available. NVIDIA Titan X cards are now shipping in limited quantities, however, and the benchmark numbers are in. The new Titan X (the company kept the same branding as its previous Maxwell-based Titan), based on NVIDIA's Pascal architecture, is some 60 percent faster than its older, Maxwell-based Titan counterpart and 20 – 30 percent faster than the new GeForce GTX 1080. On board Titan X are 1024 more CUDA cores versus a GeForce GTX 1080 (3584 versus 2560) and a wider 384-bit GDDR5X memory bus versus the 1080's 256-bit interface. Though the Titan X has the same memory clock as a GTX 1080, it has 12GB of GDDR5X memory, versus 8GB on the 1080. In testing, nothing can touch it and there's still additional headroom for overclocking. The new Titan X's $1200 price point, however, will give even hardcore gamers sticker shock. For graphics professionals and deep learning applications it could be a reasonably good value though, versus pro graphics GPUs.

Submission + - Microsoft Extends Free Windows 10 Upgrades For Assistive Technologies Users (hothardware.com)

MojoKid writes: Microsoft is granting a grace period for a free Windows 10 upgrade, for people with accessibility needs who use assistive technologies. For the general public, the yearlong offer expired last Friday July 29 (or July 30 in the wee hours of the morning, depending on where you live), but for anyone who uses an assistive technology product, there's still time. In a FAQ announcing the free offer extension, Microsoft said it hasn't yet announced an end date for customers using assistive technologies, but will give everyone a heads-up prior to whenever the company decides on an extended deadline. In the meantime, there's a special webpage setup where users can go and click on the "Upgrade Now" button to get started.

Submission + - AMD Unveils Radeon Pro WX And Pro SSG Professional Graphics Cards (hothardware.com)

MojoKid writes: AMD took the wraps off its latest pro graphics solutions at Siggraph today, and announced three new professional graphics cards in the new Polaris-based Radeon Pro WX Series. The Radeon Pro WX 4100 is the entry-level model with a half-height design for use in small form-factor workstations. The Radeon Pro WX 5100 is the middle child, while the Radeon Pro WX 7100 is AMD's current top-end WX model. The Radeon Pro WX 7100 has 32 compute units, offers 5 TFLOPs of compute performance, and is backed by 8GB of GDDR4 memory over a 256-bit memory interface. The Radeon Pro WX 5100 offers 28 compute units and 4 TFLOPs of performance along with 8GB memory over the same 256-bit interface and the Radeon Pro WX 4100 is comprised of 16 compute units at 2 TFLOPs of perf with 4GB memory over a 128-bit memory link. The Radeon Pro WX 4100 has four mini DisplayPort outputs, while the Radeon Pro WX 5100 and 7100 each have four full-size DisplayPort connectors. None of these cards will be giving the new NVIDIA Quadro P6000 a run for its money in terms of performance, but they don't have to. The Quadro card will no doubt costs thousands of dollars, while the Radeon Pro WX 7100 will eek in at just under $1,000. The Radeon Pro WX 5100 and 4100 will slot in somewhat below that mark. AMD also announced the Radeon Solid State Storage Architecture and the Radeon Pro SSG card today. Details are scant, but AMD is essentially outfitting Radeon Pro SSG cards with large amounts of Solid State Flash Memory, which can allow much larger data sets to reside close to the GPU in an extended frame buffer. Whereas the highest-end professional graphics cards today may have up to 24GB of memory, the Radeon Pro SSG will start with 1TB, linked to the GPU via a custom PCI Express interface. Giving the GPU access to a large, local data repository should offer significantly increased performance for demanding workloads like real-time post-production of 8K video, high-resolution rendering, VR content creation and others.

Submission + - NVIDIA Drops Surprise Unveiling Of Pascal-Based GeForce GTX Titan X (hothardware.com)

MojoKid writes: Details just emerged from NVIDIA regarding its upcoming powerful, Pascal-based Titan X graphics card, featuring a 12 billion transistor GPU, codenamed GP102. NVIDIA is obviously having a little fun with this one and at an artificial intelligence (AI) meet-up at Stanford University this evening, NVIDIA CEO Jen-Hsun Huang first announced, and then actually gave away a few brand new, Pascal-based NVIDIA TITAN X GPUs. Apparently, Brian Kelleher, one of NVIDIA's top hardware engineers, made a bet with NVIDIA CEO Jen-Hsun Huang, that the company could squeeze 10 teraflops of computing performance out of a single chip. Jen-Hsun thought that was not doable in this generation of product, but apparently, Brian and his team pulled it off. The new Titan X is powered by NVIDIA's largest GPU; the company says it's actually the biggest GPU ever built. The Pascal-based GP102 features 3,584 CUDA cores, clocked at 1.53GHz (the previous-gen Titan X has 3,072 CUDA cores clocked at 1.08GHz). The specifications NVIDIA has released thus far include: 12-billion transistors, 11 TFLOPs FP32 (32-bit floating point), 44 TOPS INT8 (new deep learning inferencing instructions), 3,584 CUDA cores at 1.53GHz, and 12GB of GDDR5X memory (480GB/s). The new Titan X will be available Aug. 2 for $1,200 direct from NVIDIA.com.

Submission + - Lenovo And Motorola Launch Moto Z And Moto Z Force Droids With Moto Mods (hothardware.com)

MojoKid writes: Lenovo and Motorola launched the Moto Z Droid, Moto Z Force Droid and their companion snap-on Moto Mods today, which are a new series of Android smartphone devices that offer something unique among other Android smartphones. The base specs of both the Moto Z Droid and Moto Z Force Droid read like a top-shelf Android device should, with Qualcomm's latest Snapdragon 820 SoC and a healthy 4GB of RAM and 32GB or 64GB storage options, along with microSD card expansion up to another 2TB. Both Moto Z Droids have essentially the same base platform, but differ significantly in a couple of areas. The Moto Z Droid is a thin (5.19mm) variant with a 2600 mAh battery and a 2560X1440 QHD AMOLED display. The Moto Z Force Droid sports that same QHD display, but it is sheathed behind Moto ShatterShield technology making it virtually indestructible. Motorola guarantees it not to crack or shatter if dropped. ShatterShield, along with the phone's larger 3500 mAh battery, make the Moto Z a somewhat thicker device. However, what's truly standout are Moto Mods, which are snap-on back-packs of sorts that add new features, like the JBL Speaker, Moto Insta-Projector and Incipio OffGrid Power Pack (2220 mAh) mods. Integration of the mods is excellent through Moto's patented rear magnetic and pin connector technology. Even the fairly complex projector mod fires up in seconds and works really well.

Submission + - NVIDIA Launches GeForce GTX 1060 To Take On AMD's Radeon RX 480 (hothardware.com)

MojoKid writes: NVIDIA just launched their answer to AMD's Radeon RX 480 mainstream card today, dubbed the GeForce GTX 1060. The GP106 GPU at the heart of the GeForce GTX 1060 has roughly half of the resources of NVIDIA's current flagship GeForce GTX 1080. NVIDIA claims the GTX 1060 performs on par with a previous generation high-end GeForce GTX 980 and indeed this 120W mainstream offers an interesting mix of low-power and high-performance. The new GeForce GTX 1060 features a new Pascal derivative GPU that's somewhat smaller, called the GP106. The GP106 features 10 streaming multiprocessors (SM) with a total of 1280, single-precision CUDA cores and eight texture units. The GeForce GTX 1060 also features six 32-bit memory controllers, for 192-bits in total. GeForce GTX 1060 cards with either 6GB or 3GB of GDDR5 memory will be available and in benchmark testing offered performance that just misses the mark set by the pricier AMD Radeon R9 Nano but often outran the 8GB Radeon RX 480. The GeForce GTX 1060 held onto its largest leads over the Radeon RX 480 in the DirectX 11 tests, though the Radeon had a clear edge in OpenCL and managed to pull ahead in Thief and in some DirectX 12 tests (like Hitman). The GeForce GTX 1060, however, consumes significantly less power than the Radeon RX 480 and is quieter too.

Submission + - Micron Announces 9100 MAX NVMe PCIe Enterprise Solid State Drives (hothardware.com)

MojoKid writes: Micron just launched its new 9100 Series NVMe solid state drives which come in a number of capacities, configurations and form factors. The Micron 9100 PRO series targets read-centric environments, while the 9100 MAX targets mixed workloads. Capacities for the drives range from 800GB on up to 3.2TB, though all of the drives are outfitted with a similar Microsemi 16-core / 16-channel controller and 16nm Micron MLC NAND flash memory. The fastest drives in the series are rated for peak sequential read and write throughput of 3GB/sec and 2GB/sec, respectively. In testing, the drives generally outpace Intel's DC 3700 series drive, but can't catch Intel's higher-end SSD DC P3608 in some read tests, though the Micron drives did outpace Intel's flagship in some write tests and can hit their peak 3GB/sec specified bandwidth number easily.

Submission + - Microsoft Xbox Project Scorpio Puts Out 6 TFLOPs On Par With Current Gaming PCs (hothardware.com)

MojoKid writes: Microsoft is hoping to usher in a new era in console gaming just over a year from now. While the company is just a month away from launching the Xbox One S refresh in the US, Project Scorpio is the console that really has gamers talking. During E3, Microsoft provided scant details on the console, only cluing us in to the fact that it would support virtual reality, 4K gaming, and push 6 TFLOPs of computing power. Mateusz Tomaszkiewicz, CD Projekt Red's Principal Narrative Designer, had a few things to say about that last bullet point regarding compute performance. If you recall, AMD's newly introduced Radeon RX 480 offers peak performance of 5.8 TFLOPs, which puts it in close proximity of Microsoft's Project Scorpio. But of course, trying to compare consoles to PCs using this stat alone isn't exactly apples to oranges, though Tomaszkiewicz explains, "For sure it [Scorpio] will have better looking games," Tomaszkiewicz said. "If this was available when we were working on Wild Hunt, I would expect similar quality that we have on PC right now or even better maybe."

Submission + - AMD Launches New Radeon RX 480, Benchmark Numbers Are In (hothardware.com)

MojoKid writes: AMD launched its new Radeon RX 480 graphics card today, based on the company's all new Polaris GPU architecture. The card is powered by the Polaris 10 GPU which is outfitted with 36 Compute Units, with a total of 2,304 shader processors. Reference specifications call for boost and base GPU clocks of 1266 MHz and 1120 MHz, respectively, and either 4 or 8GB of GDDR5 memory over a 256-bit interface. All told, the Radeon RX 480 offers up a total of 5.8 TFLOPs of compute performance with up to 224GB/s of peak memory bandwidth and the card requires only a single 6-pin PCIe power feed. The Radeon RX 480 is only about 9.5" inches long and sports a typical dual-slot form factor. It offers strong performance in its price segment ($199 — $239) as well. In comparison to NVIDIA's more expensive GeForce GTX 970, AMD's Radeon RX 480 fares very well. The Radeon RX 480 also offers roughly 85-95% of the performance of the more expensive previous gen Radeon R9 390 and was able to overtake it with some basic overclocking. The Radeon RX 480's power characteristics were slightly better than the GeForce GTX 970 as well but when you consider the almost two-year old NVIDIA GPU is manufactured using a 28nm process, versus the 14nm FinFET process of Polaris 10, AMD's Radeon RX 480 power characteristics are less impressive.

Submission + - Windows 10 Anniversary Update To Take Hassle Out Of Reactivating After Upgrades (hothardware.com)

MojoKid writes: Microsoft is cooking up some nifty feature enhancements to Windows 10 that will roll out with the much anticipated Anniversary Update later this summer. One of the newest tweaks will make it easier to perform hardware upgrades, such as a motherboard or hard drive, as you won't have to dial up a support representative and explain why your license should still be valid. The activation tweak is also being rolled out preview build 14371 to Windows Insiders in the Fast ring. It's part of what Microsoft is calling the "Activation Troubleshooter," which is intended to address user feedback from Windows Insiders who've run into activation issues on Genuine Windows devices after making certain hardware changes. You can launch the tool by going to Settings > Update & security > Activation and select Troubleshoot.

Submission + - Self-Driving Cars To Someday Face Moral Dilemma Of Who Lives And Who Dies (hothardware.com)

MojoKid writes: While the AI present in today's experimental self-driving cars can navigate city streets, change lanes, avoid accidents and are for the most part fairly competent "drivers", what happens when it comes to an "us versus them" scenario? What if a self-driving car is presented with no-win situation — no matter what the outcome of a collision, someone will likely die? Does the self-driving car protect its passengers at all costs with no regard for the lives of others, or should the car instead put its passengers in harm's way to avoid a higher number of casualties? That's the subject of a new study published in Science, entitled, "The Social Dilemma of Autonomous Vehicles." 1,928 participants were surveyed on a number of scenarios in which a self-driving car is faced with a moral dilemma that would result in the death of one or more people. The survey results showed that people overwhelmingly decided that self-driving cars should take a "utilitarian approach" in which casualties are minimized, even it means that passengers within the car must have their lives sacrificed for the greater good. But on the flip side, these same participants said that if they were shopping for a car to purchase or were a passenger, they would prefer to be within a vehicle that would protect their lives by any means necessary. Participants also balked at the notion of the government stepping in to regulate the "morality brain" of self-driving cars.

Submission + - Intel Ships 72-Core Knight's Landing Xeon Phi Processors (hothardware.com)

MojoKid writes: It has been nearly two years since we first heard about Intel's next generation Xeon Phi "Knights Landing" processors, which are designed for High Performance Computing (HPC) applications. The processors are a big part of Intel's Scalable System Framework (SSF) and are built on using general-purpose x86 architecture and open standards. Today, Intel announced that its Xeon Phi processors are finally available to customers, nearly a year after the company's originally-quoted launch date. Intel Xeon Phi processors feature double-precision performance in excess of 3 teraflops along with 8+ teraflops of single-precision performance. All Xeon Phi processors incorporate 16GB of on-package MCDRAM memory, which Intel says is five times more power efficient as GDDR5 and offers 500GB/s of sustained memory bandwidth. MCDRAM can effectively be used as a high-speed cache or as a complimentary addition to the system DDR4 memory. Intel is targeting its Xeon Phi as a more competitive solution versus NVIDIA's dedicated Tesla GPU accelerators, citing up to a 5.2x performance advantage in visualization, up to a 2.7x in mathematical modeling, and up to a 5x increase in life sciences apps. The Xeon Phi is available in four basic configurations with 64 to 72 cores, and with processor frequencies ranging from 1.3GHz to 1.5GHz. All four support up to 384GB of DDR4 memory, but the base Xeon Phi 7210 is limited to the 2133MHz variety. Intel notes these are the company's first bootable host processors specifically designed for highly parallel workloads.

Slashdot Top Deals

"Truth never comes into the world but like a bastard, to the ignominy of him that brought her birth." -- Milton

Working...