47382025
submission
crookedvulture writes
"With its Sandy Bridge and Ivy Bridge processors, Intel allowed standard Core i5 and i7 CPUs to be overclocked by up to 400MHz using Turbo multipliers. Reaching for higher speeds required pricier K-series chips, but everyone got access to a little "free" clock headroom. Haswell isn't quite so accommodating. Intel has disabled limited multiplier control for non-K CPUs, effectively limiting overclocking to the Core i7-4770K and i5-4670K. Those chips cost $20-30 more than their standard counterparts, and surprisingly, they're missing a few features. The K-series parts lack the support for transactional memory extensions and VT-d device virtualization included with standard Haswell CPUs. PC enthusiasts now have to choose between overclocking and support for certain features even when purchasing premium Intel processors. AMD also has overclocking-friendly K-series parts, but it offers more models at lower prices, and it doesn't remove features available on standard CPUs."Link to Original Source
46774773
submission
crookedvulture writes
"Nvidia's GK110 graphics chip is a 7.1-billion-transistor monster. It powers the firm's compute-focused Tesla K20 and its ultra-high-end GeForce GTX Titan graphics card. Today, a de-tuned version of the chip makes its debut in the GeForce GTX 780. This new card has three of GK110's 15 SMX units disabled, allowing Nvidia to use GPU silicon that didn't make the grade for its Titan and Tesla products. The GTX 780 also scales back GK110's support for double-precision FP math, which is important for compute applications but unnecessary for games. Speaking of which, the GTX 780 nearly matches the gaming performance of the thousand-dollar GTX Titan. It's quieter under load and costs a staggering 35% less, too. The $650 asking price is still incredibly steep, but this is just the first member of the GeForce 700 series. Nvidia is expected to fill out the family with less expensive cards."Link to Original Source
46709149
submission
crookedvulture writes
"For years, three-platter notebook hard drives have been too thick to actually fit into most notebook drive bays. HGST's Travelstar 5K1500 is different; it squeezes three platters into a notebook-friendly 9.5-mm casing. Shrinking the drive's circuit board and internal mechanics allowed HGST to cram in the extra platter. Thanks to the additional disc, the Travelstar boasts 1.5TB of storage—50% more capacity than its 9.5-mm peers. The platters spin at only 5,400 RPM, so this isn't a high-performance model. To make up for the slower rotational speed, notebook makers are expected to combine the 5K1500 with separate caching SSDs."Link to Original Source
46318459
submission
crookedvulture writes
"Seagate and Toshiba both offer hybrid hard drives that manage their built-in flash caches entirely in firmware. WD has taken a different approach with its Black SSHD, which instead uses driver software to govern its NAND cache. The driver works with the operating system to determine what to store in the flash. Unfortunately, it's Windows-only. You can choose between two drivers, though. WD has developed one of its own, and Intel will offer a separate driver attached to its upcoming Haswell platform. While WD remains tight-lipped on the speed of the Black's mechanical portion, it's confirmed that the flash is provided by a customized SanDisk iSSD embedded on the drive. The iSSD and mechanical drive connect to each other and to the host system through a Serial ATA bridge chip, making the SSHD look more like a highly integrated dual-drive solution than a single, standalone device. With Intel supporting this approach, the next generation of hybrid drives appears destined to be software-based."Link to Original Source
46243759
submission
crookedvulture writes
"Since their debut five years ago, Intel's low-power Atom microprocessors have relied on the same basic CPU core. That changes with the next generation, which will employ an all-new Silvermont microarchitecture built using a customized version of Intel's tri-gate, 22-nm fabrication process. Silvermont ditches the in-order design of previous Atoms in favor of an out-of-order approach based on a dual-core module equipped with 1MB of shared L2 cache. The design boasts improved power sharing between the CPU and integrated graphics, allowing the CPU cores to scale up to higher speeds depending on system load and platform thermals. Individual cores can be shut down completely to provide additional clock headroom or to conserve power. Intel claims Silvermont doubles the single-threaded performance of its Saltwell predecessor at the same power level, and that dual-core variants have lower peak power draw and higher performance than quad-core ARM SoCs. Silvermont also marks the Atom's adoption of the "tick-tock" update cadence that guides the development of Intel's Core processors. The successor to Silvermont will be built on 14-nm process tech, and an updated microarchitecture is due after that."Link to Original Source
46076091
submission
crookedvulture writes
"Intel has revealed fresh details about the integrated graphics in upcoming Haswell processors. The fastest variants of the built-in GPU will be known as Iris and Iris Pro graphics, with the latter boasting embedded DRAM. Unlike Ivy Bridge, which reserves its fastest GPU implementations for mobile parts, the Haswell family will include R-series desktop chips with the full-fat GPU. These processors are likely bound for all-in-one systems, and they'll purportedly offer close to three times the graphics performance of their predecessors. Intel says notebook users can look forward to a smaller 2X boost, while 15-17W ultrabook CPUs benefit from an increase closer to 1.5X. Haswell's integrated graphics has other perks aside from better performance, including faster Quick Sync video transcoding, MJPEG acceleration, and support for 4K resolutions. The new IGP will support DirectX 11.1, OpenGL 4.0, and OpenCL 1.2, as well."Link to Original Source
45991489
submission
crookedvulture writes
"AMD has revealed more details about the unified memory architecture of its next-generation Kaveri APU. The chip's CPU and GPU components will have a shared address space and will also share both physical and virtual memory. GPU compute applications should be able to share data between the processor's CPU cores and graphics ALUs, and the caches on those components will be fully coherent. This so-called heterogeneous uniform memory access, or hUMA, supports configurations with either DDR3 or GDDR5 memory. It's also based entirely in hardware and should work with any operating system. Kaveri is due later this year and will also have updated Steamroller CPU cores and a GPU based on the current Graphics Core Next architecture."Link to Original Source
45971669
submission
crookedvulture writes
"Slashdot's early coverage of AMD's dual-GPU Radeon HD 7990 relied on data collected with Nvidia's FCAT tools, which capture frames just before they hit the display. FCAT is great for quantifying smooth frame delivery, but it doesn't track interruptions earlier in the pipeline that can produce perceptible jitter in the game animation. Those interruptions can be measured with Fraps, correlated with FCAT data, and complemented with video samples to achieve a much deeper understanding of actual performance. Combining those tools to evaluate the 7990 reveals microstuttering that produces choppier gameplay than a single-GPU Radeon with half the theoretical horsepower (and a much lower price). AMD has prototype frame pacing software that can smooth out the stuttering in some games, but there's no timetable for its release. Right now, you're better with the $400 Radeon HD 7970 than you are with AMD's $1000 flagship."Link to Original Source
44902713
submission
crookedvulture writes
"Seagate announced its third-generation hybrid drives last month, revealing a full family of notebook and desktop drives that combine mechanical platters with solid-state storage. These so-called SSHDs are Seagate's first to be capable of caching write requests in addition to reads, and the mobile variants are already selling online. Unfortunately, a closer look at the Laptop Thin SSHD reveals some problems with Seagate's new design. While the integrated flash cache reduces OS and application load times by 30-45%, overall performance appears to be held back by its 5,400-RPM mechanical component. Seagate's last-gen Momentus XT hybrid spins its platters at 7,200-RPM, and it's faster than the new SSHD in a wide range of tests. The upcoming desktop SSHDs will also have 7,200-RPM spindle speeds, so they may prove more appealing than the mobile models."Link to Original Source