News Posts matching "40 nm"

Return to Keyword Browsing

First Devices Based on AMD Z-Series APUs Arrive in November

AMD is eyeing a slice of the Windows 8 tablet pie with its Z-Series "Hondo" dual-core x86-64 APU, which was launched earlier this week. According to sources among Taiwan-based notebook makers, the first devices based on the chips will arrive as early as this November. The company, however, did not disclose design wins or the companies working on products around its chip. AMD Z-60 will face off with Intel's recently-launched Atom Z2760 dual-core chip, designed for the same class of devices. Built on the 40 nm "Brazos 2.0" silicon, the Z-60 packs two x86-64 cores, and Radeon HD 6250 DirectX 11 graphics. Its TDP is just 4.5W.

Source: DigiTimes

GeForce GTX 680 A Sellout Success: NVIDIA

NVIDIA's flagship single-GPU graphics card, the GeForce GTX 680, achieved performance leadership over AMD's Radeon HD 7970, and forced a price-cut, however, a section of the community feels that availability is an issue with it. According to NVIDIA, availability is attributed to sales, and not lack of volumes. At an annual investors' meeting with the company's top-brass, NVIDIA released a slide which depicts GeForce GTX 680 as having 60% higher sales than GeForce GTX 580, six weeks following their respective launches.

There is one cosmetic inaccuracy in the graph, though. GeForce GTX 680 and GTX 580 are labeled "GT". One inference that can be drawn out of the graph is that NVIDIA is seeing some success in putting the 28 nm silicon fabrication process to use, despite the GTX 680 being one of the first chips built on it. In comparison, the GTX 580 arrived when the 40 nm process achieved a higher level of maturity. There seems to be a genuinely high demand for the GTX 680.

Source: PC Perspective

NVIDIA Licenses Integrated, OV-Tolerant I/O and ESD Tech. from Sofics and ICsense

Sofics bvba of Gistel, a leading provider of ESD solutions for ICs, and ICsense of Leuven, a prominent designer of analog, mixed-signal, and high-voltage ICs and turnkey ASICs, today announced that NVIDIA has licensed their integrated ESD and I/O technology to provide a stable 3.3V I/O with robust ESD protection on its Icera modem processors that use 1.8V transistors.

The license includes customized ESD solutions from Sofics and ICsenseā€™s overvoltage-tolerant I/Os. These solutions are based on a novel circuit technique proven in TSMC 0.18 um, 40 nm, and 28 nm processes that allows I/Os to handle more than 2X the voltage of the transistors on the chip.

ARM Expands Processor Optimization Packs for TSMC 40 nm and 28 nm Process Variants

ARM today announced the availability of a significantly expanded lineup of ARM Processor Optimization Pack (POP) solutions for TSMC 40 nm and 28 nm process technologies targeting a range of ARM Cortex processors. At least nine new POP configurations targeting Cortex-A5, Cortex-A7, Cortex-A9 and Cortex-A15 processor cores will be released. An essential element of ARM's comprehensive implementation strategy, POPs enable ARM partners to quickly close timing of single-, dual- and quad-core implementations across a broad envelope of power, performance and area optimization points. This solution reduces risk and improves time-to-market in the development of Cortex processor-based Systems-on-Chip (SoCs) with partners achieving competitive results in as little as six weeks.

At the leading-edge 28 nm HPM (high performance for mobile) and 28 nm HP (high performance) process variants, ARM is launching new POPs for the Cortex-A9 core as well as the first POPs for ARM's newest Cortex-A7 and Cortex-A15 processors. Since the Cortex-A7 and Cortex-A15 cores are used in tandem as ARM's big.LITTLE energy-efficient processing solution, the addition of POPs for both cores assures a complete solution for big.LITTLE implementations. ARM's lead licensee for the Cortex-A15 POP for TSMC 28 nm HPM is progressing toward the tape out of its first chip in the coming months.

NVIDIA Creates Two New OEM-only GF119-based GeForce 600 Series SKUs

The GeForce 600 series grew by two members today (albeit, OEM-only), NVIDIA re-branded the GeForce GT 520 to a new model name, "GeForce GT 620". This "new" part is otherwise identical to its predecessor, except that its standard memory amount has been halved from 1 or 2 GB to 512 MB or 1 GB. A feature addition here, is that the GT 620 supports the OpenGL 4.2 API, something the GT 520 doesn't. The GT 620 continues to be based on the 40 nm GF119 silicon, with 48 CUDA cores, 8 TMUs, and 4 ROPs.

NVIDIA also unveiled to OEMs the "new" GeForce 605, which is a re-branded GeForce 510. Based on the same GF119 silicon as the GT 620, the GeForce 605 core runs at 523 MHz, with 1046 MHz CUDA cores. This model comes with memory size options of 512 MB and 1 GB. It also inherits the core configuration of the GeForce 510, with 48 CUDA cores, 8 TMUs, and 4 ROPs.

Source: Tom's Hardware

Orbis Implements Multi-GPU, Too

Sony's next-generation PlayStation, reportedly codenamed "Orbis", is known to be powered by an AMD x86-64 CPU with graphics based on its Southern Islands architecture, from the older report. We're now hearing that Sony may implement a multi-GPU solution of its own. According to an IGN.com report, the CPU in question will be a custom-version of AMD's A8-3850 quad-core APU. This should serve as indication that the processor cores will be based on AMD's K10 Stars architecture, rather than K15 Bulldozer/Piledriver.

The GPU, on the other hand, will be based on the "Southern Islands" architecture, and the IGN.com report pin points it to resemble Radeon HD 7670. The HD 7670 is a re-branded HD 6670, which is based on the 40 nm "Turks" GPU. Turks uses neither Graphics CoreNext nor VLIW4, but the older VLIW5 number-crunching machinery. The most interesting piece of information here is talk of a multi-GPU configuration between this Turks-based GPU, and the GPU that's embedded into the "Llano" APU. We know that the graphics core embedded into AMD A8-3850, the Radeon HD 6550D, can work in tandem with Radeon HD 6670 to yield an AMD Hybrid CrossFireX configuration called "Radeon HD 6690D2". This could be end up being Sony's graphics weapon of choice.

Sparkle Introduces its GeForce GTX 560 SE Graphics Card

Today, Sparkle announced the launch of GeForce GTX 560 SE graphics card aiming at midrange market. As the most expected superstar product for mainstream market in the first half of this year, this card features a mature 40 nm GF114 GPU, delivering the ultimate next generation gaming experience. The excellent performance not only leads over similar competing products, but also shows no way inferior to GeForce 5 series. Now is the perfect time to upgrade your graphics card at a surprisingly affordable price!

Toshiba Qosmio X870 Packs A Potent Combo

When we learned early details about the Qosmio X870 from Toshiba, we took it as a sufficiently impressive combination of "Ivy Bridge" and "GeForce Kepler", without a clue about which exact models they were. DonanimHaber went hands on with one of these beasts and discovered it instead packs top-rate versions of Ivy Bridge and GeForce Fermi...err, right.

The X870 is driven by Core i7-3610QM. This chip is perhaps the most popular Core i7 mobile chip notebook designers will have access to, from the 3rd generation Core processor family. Armed with 4 cores, 8 threads (enabled with HTT), the i7-3610QM has a nominal clock speed of 2.30 GHz, with a Turbo Boost frequency as high as 3.30 GHz. Unlike higher Core i7 Extreme mobile models, its L3 cache is limited to 6 MB. Handling graphics, on the other hand, is the NVIDIA GeForce GT 670M. The GT 670 is based on 40 nm GF114 GPU, and packs 336 CUDA cores, and 2 GB of GDDR5 memory over a 256-bit wide memory interface. Other notable features of the Qosmio X870 include 16 GB of dual-channel DDR3 memory, a 17.3-inch display with 1920x1080 pixels resolution, an SSD holding the OS and programs, and a 2 TB HDD holding data.

Source: DonanimHaber

TSMC seeing orders fill sub-40nm capacity

Taiwan's premier chip foundry, TSMC, is reportedly seeing strong demand for sub-40 nm chip manufacturing. It's easy to manufacture smaller, simpler chips on new foundry nodes than complex devices such as GPUs. Hence, the source notes that it's wireless communication device chip manufactures that have sub-40 nm nodes at TSMC fully booked up. The foundly also scored orders from local and foreign fabless audio IC firms. "In fact, TSMC's 6-inch fab dedicated to process analog and LCD driver ICs has been running at full capacity since late February, with shipment delivery times to customers being extended to more than 12 weeks, the sources pointed out," notes DigiTimes.

Source: DigiTimes

Galaxy GeForce GTX 560 SE Pictured, Benchmarked

Even as NVIDIA is inching towards the launch of its next-generation GeForce GTX 670 Ti, it is rushing out the GeForce GTX 560 SE to stem loss in competitiveness to the Radeon HD 7770. Galaxy is readying a compact, cost-effective graphics card based on the new GPU, which is pictured below. Based on the 40 nm GF114 GPU (variant: GF114-200-KB-A1), the GTX 560 SE features 288 CUDA cores, 48 TMUs, 24 ROPs, and a 192-bit wide GDDR5 memory interface, holding 1 GB [(4x 1 Gbit)+(2x 2 Gbit)] of GDDR5 memory.

Galaxy's card uses a short PCB, its VRM area has been pushed to the front of the card, consisting of a 4+1 phase design. It draws power from two 6-pin power connectors. The card is cooled by a compact aluminum-fin heatsink to which heat is conveyed by copper heat pipes, and ventilated by a big (80 mm) fan. Chinese site QK123 put the card through a few synthetic benchmarks, measured power-draw, and OC performance. The GPU-Z screenshot reveals its reference speed.

Benchmarks follow.

AMD Outlines Its 2012-2013 Client Roadmap, Big Focus is on APUs

Today at its annual Financial Analyst Day, AMD has presented an updated roadmap detailing the hardware it plans to bring to the table during 2012 and 2013. For this year, the Sunnyvale-based company is preparing a processor quarter which includes the Trinity, Brazos 2.0 and Hondo APUs (accelerated processing units) and the Vishera CPU.

Set to be the main weapon in AMD's x86 arsenal, the Trinity APU (aka the 2nd gen A Series) is made on 32 nm process technology, and features DirectX 11 graphics, two/four Piledriver cores (Piledrive is said to deliver 25% better performance than the Stars cores found in Llano APUs), and a TDP that can go as low as 17 W on mobile parts. Trinity is expected to debut in Q2 and already has close to 100 design wins (more than Llano had before its release).

Tilera's 36 and 16-core TILE-Gx 64-bit processors now generally available

Tilera Corporation, the leader in manycore microprocessors, today announced several significant steps for the company including the immediate general availability of two of its highly anticipated, low-power, high-performance 64-bit processors - TILE-Gx36 and TILE-Gx16 - as well as companion evaluation systems. These processors are setting new records for performance and performance per watt, running multiple applications including networking, cloud computing and multimedia. Tilera is engaged with more than 80 customers for its TILE-Gx processors, including Harmonic and Mercury Computer Systems.

Moreover, Tilera's former CEO and Tilera co-founder Devesh Garg returns as CEO to scale the company into a leading processor provider in the market.

AMD Slips Out Radeon HD 7670 to OEMs

Without making any noise, AMD rolled out an OEM-exclusive graphics card model, the Radeon HD 7670. This GPU is completely identical to the previous-generation Radeon HD 6670, making it a rebrand. It has identical specifications to the 40 nm Turks GPU, which drives the retail HD 6670, with 480 VLIW5 stream processors, a 128-bit wide GDDR5 memory interface holding 512 MB or 1 GB of memory, 24 TMUs, 8 ROPs, and clock speeds of 800 MHz core, and 4.00 GHz memory. This GPU was featured on some of HP's desktop PC products. The product page of this OEM-only GPU can be found here.

Source: Anandtech

Christmas Special: The PC Technology of 2011

Welcome to the TechPowerUp 2011 PC technology Christmas special. We hope that you will enjoy reading it while tucking into your turkey, Christmas presents and a little too much wine... In this article, we go through the technology of 2011 that has had the most significance, the most impact and was generally the most talked about. It's not necessarily the best tech of 2011 which is the most significant though, since lemons can be just as significant as the ground-breakers in how they fail to deliver - and the backlash that goes with it.

January: Intel Sandy Bridge i5 & i7

Released on January 9th, the new Intel Core i5 & i7 processors were based on Intel's second generation Core architecture built on a 32 nm production process (HEXUS review). They included an IGP (Integrated Graphics Processor) physically on the same piece of silicon along with HyperThreading. These new dual and quad core processors soundly beat all previous generations of Intel processors in terms of processing performance, heat, power use, features and left AMD in the dust. Therefore, Intel badly needed some competition from AMD and unless you have been living under a rock, you will know how that turned out in October with the launch of Bulldozer. Sandy Bridge was a sound win and is generally considered to be the only architecture worth considering at this point. The i5-2500K is currently at the sweet spot of price/performance. It comes at a stock speed of 3.3 GHz, but typically overclocks to an amazing 4.5 - 5 GHz with a decent air cooler and without too much difficulty in getting there. Models in the budget i3 range were released at various times later. See this Wikipedia article for details.

Radeon HD 6930 2 GB Tested

Unbeknownst to many, AMD launched the Radeon HD 6930 in some markets. The company apparently doesn't want this launch to disturb reviewers from key high-volume markets, who have their hands full with Radeon HD 7970, and so the HD 6930 got a limited launch. For one, the HD 6930 is most certainly launched in China, and so Expreview gave it a run against the HD 6950 1 GB. The Radeon HD 6930 is carved out of the 40 nm "Cayman" silicon, on which other HD 6900 series products are based. It features 1280 VLIW4 stream processors, 1 GB or 2 GB of GDDR5 memory over a 256-bit wide memory interface, 80 TMUs, 32 ROPs, and clock speeds of 750 MHz (core), 1200 MHz or 4.80 GHz effective (memory). Very few partners made English press-releases about this SKU, HIS was among them. The company launched an IceQ-X graphics card on Monday.
Performance summary follows.

AMD Working On Radeon HD 6930 Graphics Card

AMD is reportedly working on a new Radeon HD 6900 series single-GPU graphics card based on the "Cayman" silicon, the Radeon HD 6930. This SKU will be designed to make things very competitive for the non-Ti GeForce GTX 560 from NVIDIA. In its most recent salvo, NVIDIA launched a limited edition GeForce GTX 560 Ti with 448 CUDA cores, targeting select markets in the winter shopping season. Tests showed it to be very competitive with HD 6950 and HD 6970, and is priced accordingly, at $289. AMD's new SKU will be designed to heat things up in the sub-$200 market where GTX 560 non-Ti and HD 6870 are trading blows.

Carved out of the 40 nm "Cayman" silicon, the GPU in its HD 6930 configuration will carry the codename "Cayman-CE". It will feature 1280 advanced VLIW4 stream processors, 80 TMUs, 32 ROPs, and a 256-bit wide GDDR5 memory interface that will hold 1 GB of memory. The core will be clocked at 750 MHz, and the memory at 1200 MHz (4.80 GHz effective). Most AIBs will reuse their cost-effective HD 6950 1 GB board designs with the new SKUs. The new Radeon HD 6930 is expected to be priced around $180.

Source: MyDrivers

Inno3D Intros GTX 560 Ti 448SP HyperCore Graphics Card

Inno3D is among the select few with a limited-edition GeForce GTX 560 Ti 448 CUDA cores, the Hong Kong-based company launched its GTX 560 Ti 448SP HyperCore graphics card. The card features an in-house GF110 board design by Inno3D, and a new custom design single-fan cooler. Based on the 40 nm GF110 GPU, it features 448 CUDA cores, and 1280 MB of GDDR5 memory over a 320-bit memory interface. It features slightly overclocked speeds over reference speeds; 760 MHz core, 1520 MHz CUDA cores, against reference speeds of 732/1464 MHz. The memory clock sticks to specifications, at 950 MHz (3.80 GHz effective). Like every other GTX 560 Ti 448, this card will be available in limited quantities, and only in select North American and European markets.

Yeston Intros Cost-Effective Radeon HD 6790 Graphics Card

Chinese company Yeston released a new Radeon HD 6790 graphics card for gamers on a tight budget. It makes use of cost-effective cooler and PCB designs to make itself available at a price-point of 799 RMB (about $125). The familiar-looking cooler borrows its design from the likes of MSI Cyclone. It consists of a copper-plate base which makes contact with a heatsink with spirally-projecting fins and two 8 mm thick nickel-plated copper heat-pipes; these heat-pipes pass through two aluminum fin arc structures on either sides of the main heatsink. Ventilation is care of a central 80 mm fan.

The PCB uses a cost-effective 3+1 phase VRM to power the 40 nm Barts LE GPU, making use of common coil-type chokes and DPAK MOSFETs. The card is one of few HD 6790 offerings out there, that draw power form just one 6-pin PCIe power connector (most designs use two). The GPU features clock speeds of 840 MHz core and 1050 (4.20 GHz effective) memory; and is aided by 1 GB of GDDR5 memory across a 256-bit wide memory interface. It packs 800 stream processors. Display outputs include two DVI, and one each of HDMI 1.4a and DisplayPort 1.2.

Source: Expreview

EVGA Intros GeForce GTX 580 Batman: Arkham City Graphics Card

EVGA released a new Batman: Arkham City-themed GeForce GTX 580 graphics card. Carrying the model number 015-P3-1582-A1, this card carries NVIDIA clock speeds of 797/1594/4050 MHz (core/CUDA cores/memory effective). Apart from the game-themed cooler shroud sticker and a themed box, we can't really see what's new with this product. Perhaps it has a voucher for a copy of the game?

Based on the 40 nm GF100 graphics processor, GeForce GTX 580 is the single fastest GPU on the planet. It packs 512 CUDA cores, and 1536 MB of GDDR5 memory across a 384-bit wide memory bus. The GTX 580 also packs features Batman: Arkham City can benefit from, such as PhysX. Available on American retailer Newegg.com, the EVGA GTX 580 Batman: Arkham City Edition is priced at $529.99. At $30 over the base model GTX 580, it has got to pack a copy of the game.

Palit Shows Off GeForce GTX 560 Ti Twin Light Turbo Graphics Card

Palit unveiled a new limited-edition GeForce GTX 560 Ti based non-reference design graphics card, the Palit GTX 560 Ti Twin Light Turbo. The card's design is based on a black colored PCB (Palit uses a red-colored one on its regular GTX 560 Ti cards), and a unique GPU Cooler design. The heatsink follows essentially the same structure as the one featured on Gainward Phantom cards, in which heat is conveyed to the aluminum fin stack by four heat pipes, but the fans that ventilate the card are located on the side of the heatsink facing the PCB, rather than on top of it. The fans draw in air from the heatsink. Palit claims that the cooler has a noise output of less than 10 dBA.

The clock speeds of the card are not given out, yet. Like every other GTX 560 Ti, this card makes use of a 40 nm GeForce Fermi 114 GPU, is DirectX 11 compliant, packs 384 CUDA cores, and makes use of 1 GB of GDDR5 memory across a 256-bit wide memory interface. Display outputs include two DVI, and one each of D-Sub and HDMI (full-size). There is one SLI connector that allows 2-way SLI with any other GTX 560 Ti card, and power is drawn in from two 6-pin PCIe power connectors. Availability and pricing information is not known at the moment.

Source: TechConnect Magazine

ASUS Ready with HD 6770 DirectCu Silent Graphics Card

ASUS is ready with a new silent (passive-cooled) graphics card based on the AMD Radeon HD 6770 graphics processor, the ASUS HD 6770 DirectCu Silent. ASUS designed a new passive GPU cooler from ground up, which makes use of heat pipe direct-touch design, which ASUS refers to as DirectCu (direct copper). The cooler is essentially a large aluminum fin heatsink that uses four nickel-plated copper heat pipes, conveying heat to a large aluminum fin stack, that is longer than the card's PCB itself.

Based on the 40 nm "Juniper" silicon, the HD 6770 is a rebrand of the HD 5770, it packs 800 stream processors, and a 128-bit wide GDDR5 memory interface to hold 1 GB of memory. The core is clocked at 850 MHz, and memory at 1200 MHz (4.80 GHz effective). The card draws power from one 6-pin PCI-E power connector. It uses high-grade "Super Alloy" VRM components, that are efficient, and don't lose energy to high-pitched noise on load. The card's display outputs include one each of DVI, D-Sub, and HDMI 1.4a. There's no word on the pricing and availability.

AMD to Claim Share of Tablet Pie with Brazos-T APU Platform

Microsoft's leap of faith into the tablet OS market which is dominated by Apple iOS and Google's Android OS, with Windows 8 operating system will be driven by two distinct hardware platforms - x86, led by Intel and its Clover Trail Atom platform, and ARM, and its swarm of client manufacturers such as Samsung, Qualcomm, etc. The third player out to claim its share of the pie is AMD, with its Brazos-T platform. Similar to Intel's Clover Trail, Brazos-T is an x86-based platform, it uses an ultra-low power accelerated processing unit (APU), codenamed "Hondo".

Hondo is a low-wattage, low-footprint APU that packs two x86-64 "Bobcat" architecture cores, an AMD Radeon HD 6250 DirectX 11 compliant graphics core, single-channel DDR3 IMC, and integrated PCI-Express. Like Clover Trail, it is a 2-chip solution, with the other chip being the "Hudson" M2T chipset, which provides an array of display connectivity options, SATA and USB connectivity. The key feature with Hondo APU is its low power consumption of just 2W, and TDP of 4.5W. The chipset is designed to consume just 1W. Both the APU and chipset are built on the 40 nm process. The platform is slated for Q2 2012, just in time for Windows 8 tablets to hit the market.

Source: DonanimHaber

EVGA Rolls Out First GeForce GT 545 Graphics Card

EVGA released the first consumer-channel graphics card based on NVIDIA's GeForce GT 545 graphics processor. The GT 545 has been an OEM-only SKU. Based on the 40 nm GF116 silicon, the GT 545 has 144 of the chip's 192 CUDA cores enabled, the same 192-bit wide memory interface, but making use of DDR3 memory instead of GDDR5 on the GeForce GTX 550 Ti. Clock speeds set at 720 MHz core, 1440 MHz CUDA cores, and 900 MHz (1800 MHz effective) memory, churning out memory bandwidth of 43 GB/s. There is 1.5 GB of memory.

EVGA's implementation resembles NVIDIA's reference design. It uses a short full-height PCB, and a single-slot cooler. Display outputs include one each of HDMI 1.4a, D-Sub, and DVI. It can pair with another card of its kind in 2-way NVIDIA SLI. Backed by 10 year warranty (if purchased this month), the EVGA GeForce GT 545 1.5 GB is priced at US $150.

Acer Readying Tablets Based on AMD Z-Series APUs

Acer has just placed an order for 80,000 pieces of AMD Z-series accelerated processing units. Based on essentially the same design as Fusion "Zacate", Z-series APUs are designed to have lower TDP and to be of higher quality, so they could be deployed in enterprise and IPC (industrial PC) environments. The AMD Z-01 is Acer's choice, this chip combines two x86-64 cores clocked at 1.00 GHz with AMD Radeon HD 6250 DirectX 11 compliant graphics, and a DDR3 memory controller. The TDP of the entire chip stands at 5.9W, it is built on the 40 nm process at TSMC.

Acer's first tablets based on AMD Z-01 will run Windows 7, since Android 3.0 (codenamed "Ice Cream Sandwich") is not going to be out any time before the end of 2011. Acer isn't the only big tablet-maker opting for AMD Z-series over Intel's Atom Pine Trail platform, MSI is also reported to be working on x86 tablets running AMD Z-series. Manufacturers are opting for Z-series over Pine Trail, because the latter has both higher price and TDP. With its relatively faster iGPU, Z-series should be able to drive graphics-intensive custom user-interfaces on tables sized up to 10.1-inches. Industry sources expect AMD to ship up to 500,000 units of the chip in the second half of 2011.Source: DigiTimes

HIS Intros Radeon HD 6790 Fan Graphics Card

HIS rolled out a new custom-design Radeon HD 6790 graphics card, the HIS HD 6790 Fan. "Fan" editions are known to bring with them airy fan-heatsinks that rely a fair bit on the fan's airflow and the way it's channeled, rather than adding weight to the heatsink. Apart from being custom-design, the card features reference clock speeds of 840 MHz core and 1050 MHz (4200 MHz effective) memory, and is loaded with 1 GB of GDDR5 memory across a 256-bit wide memory interface. Based on the 40 nm Barts GPU, the HD 6790 has 800 stream processors enabled, along with its full memory bus width. Display outputs on this card include two DVI, and one each of HDMI 1.4a and DisplayPort 1.2 (full-size). Expect standard pricing of US $160.
Return to Keyword Browsing