Browsing all articles in AMD
Nov
14

AMD adds new chips for 2014

Author admin    Category AMD, IT News     Tags

AMD has announced its next generation of PC CPUs, aimed at systems headed to store shelves in the spring and summer of 2014.

Most of the details of these new chips, and the PC hardware partners building products around them, are being held until CES 2014 in January, but AMD is eager to publicize the new code names and some performance claims early.

The previous low-power and ultra-low-power platforms, code named Kabini and Temash, are being replaced with new versions called Beema and Mullins. Both sets of parts, however, use the familiar consumer-facing A4, A6, A8, etc., branding (the higher the number, the more powerful the CPU).

The big jump, according to AMD, is that these chips are more power efficient, while also offering better performance. That’s especially important, as AMD has lagged behind rival Intel in both of these metrics for some time. The company says it is especially interested in providing quad-core CPUs for next year’s thinner, fanless PC designs.

AMD’s 2014 road map.

AMD is also adding new security features to appeal to IT professionals. The Trusted Execution Environment splits the system into normal and secure domains, and may help AMD gain a bigger foothold in the corporate environment, where security and manageability is important. Like the performance gains, we expect more details early in 2014.

Recent high-profile AMD-powered laptops and hybrids have looked good on paper, but in CNET Labs testing, they have either disappointed, or else seemed overpriced for the performance and battery life offered.

For example, the recent Samsung Ativ Book 9 Lite was pitched as an affordable ultrabook, but it cost $799 when launched, and the performance and battery life felt like they belonged in a less-expensive system.

Even more recently, the Toshiba Satellite Click was an ambitious attempt to build a low-cost AMD-powered hybrid. It launched at $599, which is reasonable for a Windows 8 tablet PC with a separate keyboard attachment, but the performance felt especially sluggish and the the tablet screen ran for only three hours, making the device feel more like a Netbook than anything else.

Both of the examples above may find a sweet spot at the right price, but that variable is largely in the hands of PC makers, not AMD itself. Despite a smaller PC market share than Intel, AMD has had great success in game consoles of late, as the company is providing graphics hardware for both the PlayStation 4 and Xbox One.

[cnet]

Jul
17

AMD gets a boost in supercomputing

Author admin    Category AMD, IT News     Tags
The OpenACC API was developed to provide a vendor neutral platform for the fastest computers in the world. Now, it is supports AMD APUs and dGPUs.
STMicroelectronics’ US-based compiler subsidiary, Portland Group, is making available a beta release of the PGI Accelerator Fortran, C and C++ compilers with support for the OpenACC API targeting AMD Accelerated Processing Units (APUs) and discrete Graphics Processing Units (dGPUs).
According to Douglas Miles, Director of The Portland Group, the OpenACC standard was developed in response to the high performance computing (HPC) community’s need for ”a vendor-neutral, platform-independent, directive-based accelerator programming model.”
“Adding PGI Accelerator support for AMD APUs and GPUs is the latest step in the evolution of OpenACC and compiler technology for heterogeneous parallel computing at PGI,” said Miles.
Unveiled in November 2011, the OpenACC API was developed by PGI, Cray, and NVIDIA, with support from CAPS Entreprise. OpenACC is already supported by PGI compilers on Nvidia GPUs with the CUDA parallel-programming architecture.
The OpenACC 1.0 specification was developed in cooperation by the founding members and is based on the PGI Accelerator programming model. The OpenACC 2.0 specification has just recently been ratified. The OpenACC Application Programming Interface (API) describes a collection of compiler directives to specify loops and regions of code in standard C, C++ and Fortran. These regions can be offloaded from a host CPU to an attached accelerator, providing portability across operating systems, host CPUs and accelerators.
“By exposing parallelism to the compiler, directives allow the compiler to do the detailed work of mapping the computation onto the accelerator to deliver significant improvements to application performance,” said the company.
“Using directives, developers can have a single code base that is multi-platform and multi-vendor compatible, a key advantage for multi-platform and multi-generation application development,” said the company.
In a recent poll of over 1200 OpenACC evaluators, over 70% of the respondents found OpenACC easy to use and more than 75% reported seeing a speedup when running on an accelerator.
“OpenACC is being adopted by HPC researchers and programmers as they look for easier ways to take advantage of the benefits of accelerated computing. OpenACC provides a straight forward means for programmers to accelerate their applications using familiar programming techniques,” said Margaret Lewis, Director, server software planning at AMD.
The first Beta release of the PGI Accelerator compilers with support for the OpenACC standard on AMD dGPU and APU platforms is available now on a limited basis, with an open Beta release currently scheduled for later in 2013.
[tgdaily]
Jun
20

ARM-based server chips are on the way for AMD

Author admin    Category AMD, IT News     Tags

AMD has publicly disclosed its strategy and roadmap in an effort to recapture critical server market share.

Specifically, AMD revealed details of its 2014 server portfolio, including Accelerated Processing Units (APUs), two- and four-socket CPUs, and details on what it expects to be the industry’s premier ARM server processor.

“This is on the heels of announcing the general availability of the AMD Opteron X-Series processor, code named ‘Kyoto,’ which dominates the small-core server market on every performance benchmark,” an AMD rep told TG Daily.

“These forthcoming AMD Opteron processors bring important innovations to the rapidly changing compute market, including integrated CPU and GPU compute (APU); high core-count ARM servers for high-density compute in the data center; and substantial improvements in compute per-watt per-dollar and total cost of ownership.”

According to the rep, AMD’s strategy is to differentiate itself by using its unique IP to build server processors that are particularly well matched to a target workload and thereby drive down the total cost of owning servers.

“This strategy unfolds across both the enterprise and data centers and includes leveraging our graphics processing capabilities and embracing both x86 and ARM instruction sets,” added AMD exec Andrew Feldman.

“[We] led the world in the transition to multicore processors and 64-bit computing, and we intend to do it again with our next-generation AMD Opteron families.”

Indeed, in 2014, AMD will launch what it refers to as the “premier” ARM server CPU. The 64-bit CPU, code named “Seattle,” is based on ARM Cortex-A57 cores and is expected to provide category-leading throughput as well as setting the bar in performance-per-watt.

AMD will also debut “Berlin,” an x86 CPU and APU, based on a new generation of cores named “Steamroller.” Designed to double the performance of the recently available “Kyoto” part, “Berlin” will offer a nice amount of compute-per-watt that will enable massive rack density.

The third processor announced today is code named “Warsaw,” AMD’s next-generation 2P/4P offering. It is optimized to handle the heavily virtualized workloads found in enterprise environments including the more complex compute needs of data analytics, xSQL and traditional databases. “Warsaw” will provide significantly improved performance-per-watt over today’s AMD Opteron 6300 family.

As noted above, “Seattle” will be the industry’s only 64-bit ARM-based server SoC from a proven server processor supplier. “Seattle” is an 8- and then 16-core CPU based on the ARM Cortex-A57 core and is expected to run at or greater than 2 GHz. The “Seattle” processor is expected to offer 2-4X the performance of AMD’s recently announced AMD Opteron X-Series processor with significant improvement in compute-per-watt.

It will also deliver 128GB DRAM support, extensive offload engines for better power efficiency and reduced CPU loading, server caliber encryption, and compression and legacy networking including integrated 10GbE. It will be the first processor from AMD to integrate AMD’s advanced Freedom Fabric for dense compute systems directly onto the chip. AMD plans to sample “Seattle” in the first quarter of 2014 with production in the second half of the year.

Meanwhile, “Berlin” is an x86-based processor that will be available both as a CPU and APU. The processor boasts four next-generation “Steamroller” cores and will offer almost 8X the gigaflops per-watt compared to current AMD Opteron 6386SE processor. It will be the first server APU built on AMD’s revolutionary Heterogeneous System Architecture (HSA), which enables uniform memory access for the CPU and GPU and makes programming as easy as C++. “Berlin” is expected offer extraordinary compute per-watt that enables massive rack density. It is slated to be available in the first half of 2014.

Lastly, “Warsaw” is an enterprise server CPU optimized to deliver optimized performance and total cost of ownership for two- and four-socket servers. Designed for enterprise workloads, it will offer improved performance-per-watt, which drives down the cost of owning a “Warsaw”-based server while enabling seamless migration from the AMD Opteron 6300 Series family. It is a fully compatible socket with identical software certifications, making it ideal for the AMD Open 3.0 Server – the industry’s most cost effective Open Compute platform. It is expected to be available in the first quarter of 2014.

[tgdaily]

Jun
13

AMD’s FX-9590 CPU hits 5 GHz

Author admin    Category AMD, Hardware, IT News, Processor     Tags

AMD-FX-9590-5-GHz

AMD has debuted the first commercially available 5 GHz CPU processor, dubbed the FX-9590. These 8-core CPUs are targeted at gamers and high-end users looking to power their rigs with some of the fastest silicon available.

“At E3 this week, [we] demonstrated why [we are] at the core of gaming,” explained AMD exec Bernd Lienhard.

“The new FX 5 GHz processor is an emphatic performance statement to the most demanding gamers seeking ultra-high resolution experiences including AMD Eyefinity technology.”

According to Lienhard, both the 5 GHz FX-9590 and 4.7 GHz FX-9370 feature the “Piledriver” architecture, are unlocked for easy overclocking and pave the way for enthusiasts to enjoy higher CPU speeds and related performance gains. Additionally, the processors bost AMD Turbo Core 3.0 technology to dynamically optimize performance across CPU cores and enable maximum computing for the most intensive workloads.

As you may recall, AMD was the first to break the 1 GHz barrier in May of 2000 and continues to roll out innovative silicon, including the first Windows compatible 64-bit PC processor and the first native dual-core and quad-core processors. Oh, and yes, AMD also introduced the first APU (unifying CPU and Radeon graphics on the same chip) as well as the first x86 quad-core SoC.

The new AMD FX CPUs will hit the streets this summer in two configurations:

* FX-9590: Eight “Piledriver” cores, 5 GHz Max Turbo.
* FX-9370: Eight “Piledriver” cores, 4.7 GHz Max Turbo.

[tgdaily]

Dec
6

AMD reveals Opteron 3300 and 4300 processors for the penny-pinching enterprise

Author admin    Category AMD, Hardware, IT News, Processor     Tags

As a followup to its flagship Opteron 6300 launch last month, AMD has just released several more Piledriver-based processors meant for the server room. One eight-core and two quad-core models are part of the Opteron 3300 series, while the Opteron 4300 series gets six new CPUs: one quad-core, three six-core and two eight-core designs. With all this new silicon, IT pros may have concerns about compatibility issues — but fear not, for all of AMD’s new gear has sockets that fit in with the 3200 and 4200 series to make upgrading a painless process. Designed for small-to-medium sized businesses and web host servers, the chips are relatively inexpensive with prices ranging from $174 to $501, a far cry from the the $575 to $1,392 price of the higher-end 6300.

Despite the low cost, AMD claims the CPUs have a 24 percent performance per watt increase and 15 percent less power usage than their predecessors. The chip maker will likely still face an uphill battle against Intel’s mighty Xeon, but businesses looking to save a little cash might be the Opteron’s saving grace. There’s more detailed specs on the newly announced processors at the source, and you can get a peek at the pricing table after the break.

DNP AMD reveals Opteron 3300 and 4300 processors for the pennypinching enterprise

[engadget]

Oct
23

AMD updates its FX processors: 8-core chip has 4GHz base clock, ’15 percent’ more oomph

Author admin    Category AMD, Hardisk, IT News, Processor     Tags

AMD announces FX refresh eightcore chip now clocks in at 42GHz, offers up to '15 percent' speed increase

If you get the impression that AMD is diverting its energy away from traditional CPUs and towards APUs and fresher PC form factors such as all-in-ones, then you’re certainly right — but you’re also slightly ahead of the game. The company promises there’s a still a good few years of life left in its CPU-only chips and the AM3+ socket, and it’s putting today’s announcement forward as evidence. As of now, last year’s eight-core FX-8150 has been superseded on retailers’ shelves by the FX-8350, which notches the stock clock speed up to 4GHz, or 4.2GHz on turbo (alas with no obvious sign of that resonant mesh we once heard about). The full stack (codenamed ‘Vishera’) includes eight-, six- and four-core options, all based on the new Piledriver architecture which — when combined with these higher clock speeds — promises an overall performance uplift of around 15 percent versus the old Bulldozer cores. To be fair though, those Bulldozers weren’t so snappy to begin with, and besides, the most significant performance claims with this upgrade relate to multi-threaded applications and a few gaming titles like Skyrim and Civ 5. Judging from the slide deck below, gains in other areas of performance may be lower — perhaps in the region of seven percent — so as usual we’re going to roundup a bunch of reviews later today before we jump to any conclusions.

If it turns out that stock performance alone isn’t enough to sell these chips, then potential buyers still ought to check out FX’s pricing relative to Intel — not least because, as is typical, AMD sells overclockable chips at no extra charge. The top-end FX-8350 will hit the market at $195, which is not only cheaper than some earlier leaks suggested, but also $40 cheaper than an unlocked Core i5-3570K that has a lower clock speed and a smaller L3 cache — although the relative performance of these two chips remains to be independently tested. Meanwhile, the entry-level quad-core FX-4300 will virtually match the price of a locked i3-2120 at $122, but can be readily overclocked to 5GHz with water-cooling. AMD is also making a few claims based on the cost of multiple components in a rig: for example, that you can spend $372 on an FX-8350 and Radeon HD 7850 combo that delivers a 25 to 70 percent gaming advantage over a similarly priced Core i5 3570K with a GeForce GTX 650 Ti. Again, stay tuned for our roundup and we’ll figure out just how compelling this really is.

[engadget]

Jul
20

AMD’s Bolton Uses Just 7.8 Watts

Author admin    Category AMD, IT News     Tags

AMD Fusion Marketing Shot

- AMD Fusion Marketing Shot

We just reported on AMD’s Richland APU here and now it seems that some information about the supporting chipset has surfaced on the internet. The new chipset will use only 7.8 watts and will bring RAID 0, 1, 5 and 10 support to the FM2 platform.

We reported here that AMD’s Richland would be compatible with the current FM2 socked, but hardware experts at Fudzilla.com have uncovered some more info about the new chipsets AMD will be launching next year.

The FM2 platform will reportedly be somewhat renewed with the Bolton FCH. In AMD talk, FCH is short for Fusion Controller HUB.

AMD’s next-generation chipset will consume exactly the same amount today’s A75 chipset uses and will pack 4 USB 3.0 ports, 14 USB 2.0 ports and 8 SATA III connectors.

CrossFire support is still there and the users will be able to match a modest video card with the HD 7000 iGPU inside AMD’s Richland.

[softpedia]
Jul
16

AMD’s Vishera Piledriver FX 8320 and FX 8300 8-Core Processors Revealed

Author admin    Category AMD, IT News     Tags

AMD FX / Bulldozer CPU Die

AMD customers that are still enjoying the AM3+ platform are not forgotten by the company and the Texas based CPU and GPU designer is getting ready to launch some very powerful eight-core processors.

The new models use the long-awaited Piledriver enhanced x86 core and the same 8 MB level 3 cache.

The maximum supported memory is still 1866 MHz DDR3, but the processors themselves will likely offer an overall 20% performance increase over today’s FX 8150 CPU like we’ve reported here.

The new additions are reportedly called FX 8300 and FX 8320.

These are unlocked CPUs and the former runs at a base frequency of 3.3 GHz while the latter rated at 3.5 GHz with a 4.0 GHz Turbo option.

AMD’s FX 8300 has every chance of becoming an overclocker’s favorite as it only sport a 95 watts maximum TDP while the FX 8320 is rated at 125 watts TDP just like the FX 8350 that we’ve reported here.

[softpedia]
Feb
13

AMD 2012 CPU and APU Roadmap Presumably Revealed

Author admin    Category AMD, IT News     Tags

AMD has already confirmed that its next-generation Trinity APUs will become available in mid-2012, but a recently leaked company roadmap has now arrived to give us more details about the launch of these APUs, as well as about the Brazos 2.0 and Vishera processors.

The first new chips to come out from AMD will arrive in the second quarter of this year, and they will cover the low-end and upper-mainstream performance sectors.

The starts of the show will be of course the new Trinity APUs based on the Bulldozer architecture, four such parts being expected to arrive by the end of the second quarter, according to the leaked Donanim Haber roadmap.

AMD will split these into the A10- and A8-Series, the first one including the A10-5800 and A10-5700 APUs with Radeon HD 7660D graphics, while the latter will welcome the A8-5600 and A8-5500 models with Radeon HD 7560D graphics.

These APUs will coexist with AMD’s previous Llano processors until the third quarter of this year when the chip maker plans to introduce the A6-5400 and A4-5300 APUs with Radeon HD 7540D and 7840D GPUs.

In the performance sector, the third quarter of this year will witness the introduction of the Vishera processors featuring the same Piledriver cores as those used for the Trinity APUs.

Leaked AMD roadmap detailing the company's 2012 APUs and CPUs
Enlarge picture

Four such CPUs are prepared, two of them including eight processing cores, the FX-8350 and FX-8320, while the other two pack six and, respectively, four computing cores. These two chips are called the FX-6300 and FX-4320.

For the low-end computer market, AMD plans to introduce the Brazos 2.0 platform in the second quarter of this year.

This includes the AMD E2-1800 and E1-1200 APUs, both of these chips coming as slightly faster versions of the E-300 and E-450 processors they are meant to replace. We’ll keep you up to date with how things evolve from now on.

[softpedia]

Dec
19

AMD Radeon HD 7970 Packs 4.3 Billion Transistors

Author admin    Category AMD, Hardware, IT News, VGA     Tags

AMD Radeon HD 7970 packs 4.3 billion transistors -

AMD Radeon HD 7970 packs 4.3 billion transistors

AMD’s Tahiti XT graphics core, which stands at the heart of the soon to be released Radeon HD 7970, features a whopping 4.3 billion transistors, according to a recent report to hit the Web.

This is almost twice as much as Intel’s recently launched Sandy Bridge-E chips which feature 2.27 billion transistors. 

What’s inside it you ask? Well, a massively parallel architecture of course that packs 32 so called Compute Units to deliver a total of 2048 streaming processors.

Some other hardware logic is also packed inside the chip, like dual geometry engines, a render back end, some L2 cache and a 384-bit wide memory controller, but as you can see from the slide provided by OBR Hardware, the largest part of the GPU is occupied by the Compute Units.

The 4.3 billion transistors is truly a massive number, which makes us wonder where will GPU makers go from here. After all, they can’t keep on increasing the transistor count forever.

[softpedia]
Follow us on Twitter! Follow us on Twitter!
[Powered by Android]

Blogroll

Google Search :)

Calendar

April 2014
M T W T F S S
« Mar    
 123456
78910111213
14151617181920
21222324252627
282930  

Archives

Recent Posts