Quantcast

30 June, 2010

AMD Readies 95W Six-Core Thuban


Share
AMD is preparing to launch a new version of its highly successful and dirt cheap 1055T six-core. The chipmaker has managed to cut the TDP down to just 95W, which works out to just 15.8W per core, VAT excluded. The original 1055T had a 125W TDP, but it appears the new 95W part uses the same E0 stepping, hence the rest of the specs have remained unchanged. Although Intel proudly bears the performance crown in the six-core market segment, AMD’s parts offer much better value for money.
1055T gets even cooler

AMD is preparing to launch a new version of its highly successful and dirt cheap 1055T six-core.

The chipmaker has managed to cut the TDP down to just 95W, which works out to just 15.8W per core, VAT excluded. The original 1055T had a 125W TDP, but it appears the new 95W part uses the same E0 stepping, hence the rest of the specs have remained unchanged.

Although Intel proudly bears the performance crown in the six-core market segment, AMD’s parts offer much better value for money. Phenoms are still the people’s six-cores, although this might sound a bit communist, or worse.

You can find the listing here, but there's no pricing info. We expect it to cost no more than the 125W version, which sells for about €180.

Source: fudzilla.com

55W Quad Fusion Is Coming


Share
AMD's Fusion project will get to quad-core. Of course the first one is a dual-core, aiming for the Brazos platform and after that there should be a Llano version of Fusion that comes in dual and quad-core versions. We've already said that Llano dual-core has a 20W TDP and some of them will get even to 40W, but more importantly the quad-core Llano with integrated graphics should set to 55W TDP. This is not that bad considering that Fusion has most parts of chipset, graphics and a quad core CPU.
32nm, DDR3, 2011

AMD's Fusion project will get to quad-core. Of course the first one is a dual-core, aiming for the Brazos platform and after that there should be a Llano version of Fusion that comes in dual and quad-core versions.

We've already said that Llano dual-core has a 20W TDP and some of them will get even to 40W, but more importantly the quad-core Llano with integrated graphics should set to 55W TDP.

This is not that bad considering that Fusion has most parts of chipset, graphics and a quad core CPU. The launch date is again 2011 and we cannot get more precise than that.

The platform supports DDR3, and is a 32nm product. As we said many moons ago the 45nm version of Fusion has been cancelled a while back.

Source: fudzilla.com

The Mix Between CPUs And GPUs In Servers Will Change – AMD


Share
Graphics processing units (GPUs) are gaining market acceptance in high-performance computing space and are also gaining hardware features that are specifically designed to improve their compute performance. While central processing units (CPUs) will still remain in use in the long term, the mix between them and GPUs in servers will change, according to AMD. “I think what CPUs and GPUs can do is change the mix [of their existence inside servers]. The x86 CPU architecture is on the curve towards the end of Moore’s law due to power limitations…
The Mix Between CPUs and GPUs in Servers Will Change – AMD

Graphics processing units (GPUs) are gaining market acceptance in high-performance computing space and are also gaining hardware features that are specifically designed to improve their compute performance. While central processing units (CPUs) will still remain in use in the long term, the mix between them and GPUs in servers will change, according to AMD.

“I think what CPUs and GPUs can do is change the mix [of their existence inside servers]. The x86 CPU architecture is on the curve towards the end of Moore’s law due to power limitations… It is hard to build an exascale server using purely x86 technology because that server is going to be too big and will consume too much power. There are already scalability limitations and some of them are pretty thoroughly explored. So, the mix between CPUs and GPUs will, I think, potentially, change,” said Patricia Harrell, director of Stream computing at AMD, in a conversation with X-bit labs.

Some fifteen years ago all supercomputers were based on various proprietary chips. However, the vast majority of HPCs today are powered by x86-based chips. Graphics chips are also moving into that space and going forward they have chances to replace conventional CPUs on that market. However, they are unlikely to completely replace microprocessors, at the end of the day it is still impossible to run operating system on a graphics chip; moreover, some code needs to be run on central processing units. In general, there dawn of heterogeneous computing is coming, not the dawn of all-around GPU computing.

“There is a market trends towards heterogeneous computing and what we call Fusion architecture. There is tremendous potential for that kind of technology in the HPC space as well. On the software side there are research projects investigating how game developers can use all of the resources available on a system. So, they do not have to think exclusively what architecture to use for their application,” said Ms. Harrell.

Even Intel Corp. admits that the mix between central processors and graphics/stream processing chips inside servers is set to change by announcing Larrabee and eventually MIC architectures, there will still be applications that will rely on pure x86 products, according to AMD.

“I think there will always be applications that run on one architecture better than on another. I believe, there will always be a space for discrete GPUs and there will always be a space for x86 technology that can run traditional applications. So, there will always be a place for both architectures and the question for an application is what is the mix of CPUs and GPUs is there and how it is architected,” said the director of Stream computing at AMD.

At present AMD offers FireStream compute accelerators for HPC servers based on ATI graphics chips. In the future the company plans to integrate CPUs and GPUs onto the same piece of silicon for both clients and servers.

It is interesting to note that one of the sessions at the Hot Chips 2010 symposium dedicated to various processing and server technologies is entitled “Surviving the End of Scaling of Traditional Microprocessors in HPC”. The specialists from Schlumberger and Stanford universities are going to discuss limitations of today’s microprocessors when it comes to HPC servers.

Source: xbitlabs.com

AMD's First Fusion Comes In Q4 2010


Share
The first Fusion to come from AMD is a dual-core. This chip fits in Brazos platform that take care the entry level of market, and such a GPU has a big chance to end up in notebooks. We can tell you that this dual-core has a DirectX 11 GPU, it comes in BGA packaging and it works with a quite acceptable 25W TDP. The planned launch date is the latter part of Q4 2010 and this is of course if all goes well.
Dual core, fits in Brazos platform

The first Fusion to come from AMD is a dual-core. This chip fits in Brazos platform that take care the entry level of market, and such a GPU has a big chance to end up in notebooks.
We can tell you that this dual-core has a DirectX 11 GPU, it comes in BGA packaging and it works with a quite acceptable 25W TDP.

The planned launch date is the latter part of Q4 2010 and this is of course if all goes well. You can bet that after CES 2011, many vendors might have this CPU in their desktop and notebooks systems.

We can also add that this is a 32nm CPU/GPU or APU (Application Processing Unit) how AMD likes to call it and even this version of Fusion can support up to 4 cores, but it's different from Llano APU that goes in Lynx platform.

Source: fudzilla.com

Intel: GPUs Only 14x Faster Than CPUs


Share
A recent paper written by Intel and presented to the International Symposium on Computer Architecture in France claims that Nvidia's GeForce GTX 280 GPU is only 14x faster than its Core i7 960 processor. The paper attempts to debunk claims made by Nvidia developers who saw a 100x performance improvement in some application kernels using CUDA when compared to running them on a CPU. But is that any surprise? GPUs like the Nvidia GTX 280 have 240 processing core--the average CPU only has six cores.
While Nvidia developers see a 100x speed increase, Intel only sees 14x with some kernels using CUDA.

A recent paper written by Intel and presented to the International Symposium on Computer Architecture in France claims that Nvidia's GeForce GTX 280 GPU is only 14x faster than its Core i7 960 processor. The paper attempts to debunk claims made by Nvidia developers who saw a 100x performance improvement in some application kernels using CUDA when compared to running them on a CPU.

But is that any surprise? GPUs like the Nvidia GTX 280 have 240 processing core--the average CPU only has six cores. However it's uncertain how Intel came to its "14x" conclusion, as the findings refer to a set of unknown benchmarks--Nvidia even pointed out that they weren't specified in the paper.

"[But] it's actually unclear...what codes were run and how they were compared between the GPU and CPU," said Nvidia spokesperson Andy Keane. "[Still], it wouldn't be the first time the industry has seen Intel using these types of claims with benchmarks."

Playing on the paper's title--Debunking the 100x GPU vs CPU Myth--Keane said that the real myth is that multi-core CPUs are easy for any developer to use and see performance improvements. "In contrast, [our] CUDA parallel computing architecture is a little over 3 years old and already hundreds of consumer, professional and scientific applications are seeing speedups ranging from 10 to 100x using Nvidia GPUs."



Naturally Intel retaliated, saying that Nvidia had taken one small part of the paper out of context and even added that GPU kernel performance is often exaggerated.

"General purpose processors such as the Intel Core i7 or the Intel Xeon are the best choice for the vast majority of applications, be they for the client, general or HPC market segments," said an Intel spokesperson. "This is because of the well-known Intel Architecture programming model, mature tools for software development and more robust performance across a wide range of workloads--not just certain application kernels."

Source: tomshardware.com

AMD Introduces Server Processors For Cloud And Hyperscale Data Centers


Share
Advanced Micro Devices this week introduced its new AMD Opteron 4100-series microprocessors that target cloud and hyperscale data centers. The new chips come at very low cost and are supported by AMD’s new cost-efficient server platform code-named San Marino and low-power platform called Adelaide. AMD claims that select new central processing units (CPUs) offer the lowest “per-core” power consumption in the server industry.
AMD Releases Low-Cost Server Microprocessors for the Price Starting at $99

Advanced Micro Devices this week introduced its new AMD Opteron 4100-series microprocessors that target cloud and hyperscale data centers. The new chips come at very low cost and are supported by AMD’s new cost-efficient server platform code-named San Marino and low-power platform called Adelaide. AMD claims that select new central processing units (CPUs) offer the lowest “per-core” power consumption in the server industry.

“Until now, customers wanting to build a dense and power-efficient cloud or hyperscale data center had to shoehorn expensive, higher-end solutions into their computing environment, or they had to choose low-power client-based designs that may not have offered the right level of performance and server functionality. With the AMD Opteron 4000-series platform, these customers now have a server platform that is extremely power- and cost-efficient, allows a high degree of customization,” said Patrick Patla, corporate vice president and general manager of server and embedded division at AMD.

AMD’s quad-core six-core Opteron 4100-series microprocessors feature 2MB/3MB of level-two cache (512KB per core), 6MB of level-three cache, two HyperTransport 2.0 links and dual-channel DDR3 memory controller that supports up to PC3-10600 (DDR3 1333MHz) memory in addition to low-voltage DDR3 and quad-rank DIMMs. The chips are designed with C32 socket (LGA 1207) and sport C1E, Cool Speed, Precision Thermal Monitor, Remote Power Management Interface, DDPM, AMD CoolCore, Enhanced AMD PowerNow! Technology, AMD Wide Floating Point Accelerator, AMD Memory Optimizer Technology, AMD Balanced Smart Cache, AMD-Vc, EVP, OPMA and other technologies.

The new Opteron 4100-series chips are available in 32W, 50W and 75W average CPU power (ACP) envelopes, which translate into 35W, 65W and 95W thermal design power (TDP) envelopes. AMD is especially proud of its six-core Opteron 4162 EE and 4164 EE processors with 35W TDPs, which have the lowest known power per core of any server microprocessor, at 5.83W.

According to AMD, based on its checks with builders of cloud or hyperscale datacenters, for their applications power efficiency, density and cost are more important than raw performance, per core scalability or memory scalability, qualities important for traditional servers.

AMD claims that server platforms with reduced power consumption allow installation of increased amount of machines into power budgets that previously could support half the amount of servers. For example, two years ago 5.5KVA power budget could support 19 servers based on AMD Opteron 2300 “Barcelona” chips with 152 cores in total, whereas now 5.5KVA power budget can support 42 servers based on AMD Opteron 4100-series with 504 cores in total.

With the release of the AMD Opteron 4100-series microprocessors, AMD reconsiders pricing of server CPUs for the second time of the year. The starting price for the quad-core chips that can work in 2-way servers is now just $99, whereas the least expensive server processor with six cores costs $174. The top-of-the-range 4164 EE processor will still cost $698. The whole lineup of AMD Opteron 4100-series looks as follows:

• AMD Opteron 4122 – 2.20GHz, 4 cores, ACP 75W – $99
• AMD Opteron 4130 – 2.60GHz, 4 cores, ACP 75W – $125
• AMD Opteron 4162 EE – 1.70GHz, 6 cores, ACP 32W – $316
• AMD Opteron 4164 EE – 1.80GHz, 6 cores, ACP 32W – $698
• AMD Opteron 4170 HE – 2.10GHz, 6 cores, ACP 50W – $174
• AMD Opteron 4174 HE – 2.30GHz, 6 cores, ACP 50W – $255
• AMD Opteron 4176 HE – 2.40GHz, 6 cores, ACP 50W – $377
• AMD Opteron 4180 – 2.60GHz, 6 cores, ACP 75W – $188
• AMD Opteron 4184 – 2.80GHz, 6 cores, ACP 75W – $316

Systems from Acer Group, Dell, HP, SGI, Supermicro, ZT Systems, and numerous other channel partners are expected beginning this week and in the coming months.

Source: xbitlabs.com

Intel Readies Ten-Core Microprocessor For Servers


Share
Intel Corp. has confirmed plans to release ten-core microprocessor for servers based on the code-named Westmere micro-architecture. The chip is likely to be released next year and Intel will disclose details about it this August. On the 24th of August, 2010, the world’s largest maker of central processing units will reveal details about its ten-core chip code-named Westmere-EX at the Hot Chips conference.
Intel Preps Ten-Core Westmere Chip

Intel Corp. has confirmed plans to release ten-core microprocessor for servers based on the code-named Westmere micro-architecture. The chip is likely to be released next year and Intel will disclose details about it this August.

On the 24th of August, 2010, the world’s largest maker of central processing units will reveal details about its ten-core chip code-named Westmere-EX at the Hot Chips conference. At present only rumours exist about the microprocessor and the program of the symposium is the first official confirmation that the chip exists in plans. Regrettably, Intel did not reveal any additional information about the chip in the description of its presentation.

At present Intel sells eight-core Xeon MP microprocessor originally code-named Nehalem-EX. It is noteworthy that the chip emerged about one and a half years after the original Nehalem processor for high-end desktops and dual-chip servers, whereas Westmere-EX is likely to emerge sometime in the first half of 2011, about a year after the first Westmere chip code-named Gulftown.

The ten-core Westmere microprocessor will be able to process up to twenty threads of code at once thanks to Hyper-Threading technology. It will also support such capabilities as AES-NI, which improves performance in security applications. The chip will be made using 32nm fabrication process.

Even though ten processing engines is a remarkable number, the arch-rival of Intel – Advanced Micro Devices – will release server chips with up to sixteen cores based on the new code-named Bulldozer micro-architecture next year. While at present Intel’s multi-processor server platform offers a number of advantages compared to AMD’s it remains to be seen whether those advantages will be enough to compete against sixteen-core chips using a ten-core CPU in 2011.

Source: xbitlabs.com

Intel Negotiating New Plant In Israel


Share
Intel is currently negotiating the construction of a new plant in Israel and it’s asking the government for some assistance, in the form of a $400 million incentive package. The plant would be located in Kiryat Gat and it would employ around 400 workers, so each new job would cost the government a cool $1 million, which doesn’t sound like a very good deal for taxpayers. However, the Israeli Ministry of Industry, Trade and Labor is reportedly offering $200 to $250 million, but there is a catch.
Seeking $400 million incentive package

Intel is currently negotiating the construction of a new plant in Israel and it’s asking the government for some assistance, in the form of a $400 million incentive package. The plant would be located in Kiryat Gat and it would employ around 400 workers, so each new job would cost the government a cool $1 million, which doesn’t sound like a very good deal for taxpayers.

However, the Israeli Ministry of Industry, Trade and Labor is reportedly offering $200 to $250 million, but there is a catch. Israeli media report that the ministry would gladly offer a bigger package if Intel chooses to construct another facility in northern Israel sometime in the future.

Intel currently operates several facilities in five Israeli cities and it employs 6,300 workers, which is quite a lot in a nation of 7.5 million, so it’s no wonder that it’s seeking a generous offer from the Israeli government.

Source: fudzilla.com

15 June, 2010

AMD Reaffirms Plans To Develop Fusion Processors For Servers


Share
Advanced Micro Devices reaffirmed on Friday that the so-called accelerated processing units (APUs) – the chips that combine x86 processing cores along with graphics/stream processing engines – will eventually find their place on the market of servers. However, such chips will only be available in years since the lion’s share of server software cannot take advantage of computing capabilities of graphics processing units (GPUs). “I believe the push for an APU within servers is still to come. It is something AMD is committed to delivering in the years ahead and when the time is right, more info on Fusion APUs for servers will come,” said John Fruehe, the director of product marketing for server/workstation products at AMD.
AMD to Offer Accelerated Processing Units for Servers “in Years”

Advanced Micro Devices reaffirmed on Friday that the so-called accelerated processing units (APUs) – the chips that combine x86 processing cores along with graphics/stream processing engines – will eventually find their place on the market of servers. However, such chips will only be available in years since the lion’s share of server software cannot take advantage of computing capabilities of graphics processing units (GPUs).

“I believe the push for an APU within servers is still to come. It is something AMD is committed to delivering in the years ahead and when the time is right, more info on Fusion APUs for servers will come,” said John Fruehe, the director of product marketing for server/workstation products at AMD.

Presently AMD offers Opteron microprocessors along with FireStream compute processors for high-performance computing (HPC) industry. For example, the current No. 7 cluster – Tianhe – in the Top 500 Supercomputer list is run on Intel Xeon 5500-series CPUs as well as ATI Radeon HD 4870 X2 stream processing boards. Moreover, the world’s second most powerful supercomputer – Nebulae – is based on Intel Xeon 5600-series chips and is boosted by Nvidia Tesla C2050 compute accelerators. Still, the globe’s most powerful supercomputer – Jaguar – features Cray XT5-HE nodes powered by “traditional” six-core AMD Opteron 2.60GHz.

Clusters like Nebulae or Tianhe have specialized software for the GPU to run parallel math operations that assist the CPU in decoding instructions and solving large computing problems. This is an example of where an application has been recompiled. The need to recompile the application is one reason why heterogeneous computing for servers is still to come. It took a long time to transit to 64-bit computing after AMD introduced its Opteron chips in April, 2003, and it will also take a long time before software makers learn how to use exceptional stream processing capabilities of modern GPUs, such as ATI Radeon HD 5000-series or Nvidia GeForce Fermi-series.

According to Mr. Fruehe, there are two things stand out to me that can happen sooner rather than later when it comes to GPGPU (general purpose processing on GPUs):

• OS-level enablement will likely grease the wheels for more rapid adoption among ISVs;
• Finding a way for the CPU to speak more directly to the GPU/.

“Future silicon advances, including our next generation of AMD FireStream solutions, planned for released later this month, will go a long way towards making this a reality. However, we shouldn’t assume that there is only one way to accomplish this level of integration. The key to the whole discussion is that this solution is driven by the ecosystem and will be software-led,” concluded Mr. Fruehe.

Source: xbitlabs.com

09 June, 2010

Intel Establishes Third “Exascale” Research Lab


Share
Intel Corp., imec and five Flemish universities on Tuesday officially opened the Flanders ExaScience Lab at the imec research facilities in Leuven, Belgium. The lab will develop software to run on Intel-based future exascale computer systems delivering 1000 times the performance of today's fastest supercomputers, using up to 1 million cores and 1 billion processes to do so. The ExaScience Lab will be the latest member of Intel's European research network – Intel Labs Europe – that consists of 21 labs employing more than 900 R&D professionals.
Intel and Partners Open ExaScience Lab in Leuven, Belgium

Intel Corp., imec and five Flemish universities on Tuesday officially opened the Flanders ExaScience Lab at the imec research facilities in Leuven, Belgium. The lab will develop software to run on Intel-based future exascale computer systems delivering 1000 times the performance of today's fastest supercomputers, using up to 1 million cores and 1 billion processes to do so.

The ExaScience Lab will be the latest member of Intel's European research network – Intel Labs Europe – that consists of 21 labs employing more than 900 R&D professionals.

Designing exascale computers using current technology and design methodologies would mean the systems would become extremely hot and require a power plant to deliver the power needed to run them. When building a system consisting of millions of cores, getting all of them to work together for an extended period of time also represents a challenge. Hence, completely new computer programming methods and software will be required to bring power consumption to acceptable levels and to make the system fault tolerant. Power and reliability will be key challenges that will need to be understood to turn the vision of exascale computing into reality.

According to Intel, reaching the next level of supercomputing performance is about more than just reaching an arbitrary milestone, but it is about crossing many different thresholds of possibility that reside in the exascale domain, to provide scientists and doctors new tools to draw new insights from of massive amounts of data. It’s about, along the way, developing the technologies that will one day allow the cloud to scale to level where massive distributed computers can simulate reality and synthesize “holodeck” like science-fiction experiences, Intel said. Over the long term, high performance technologies become personal technologies.

The exascale labs begin research as Intel unveils new plans for the Intel many-core x86 architecture for high-performance computers, which build upon Intel’s history of many-core related research including Intel’s “Larrabee” program and single-chip cloud computing.

Breakthroughs in exascale computing could mean the ability to simulate very complex systems, impossible to replicate today like the human body or Earth's climate. The result, if the computing industry is successful, could mean finding cures for diseases or better predicting natural disasters. The Flanders ExaScience Lab will be focused at enabling scientific applications, beginning with the simulation and prediction of "space weather," or electromagnetic activity in the space surrounding Earth's atmosphere. Solar flares – large explosions in the Sun's atmosphere – can cause direct damage to Earth. Damage can be to electric power networks, pipeline systems and the quality of wireless communication, as examples. To accurately predict and understand the effects, exascale computing power is needed. Chosen for its extremely complex nature, the software findings are expected to be used and extended to address many other problems.

Source: xbitlabs.com

Intel: The World Needs Itanium, So Do We


Share
The gap between performance, feature-set and capabilities of Intel Xeon and Intel Itanium central processing units (CPUs) is closing. Nonetheless, IA64 microprocessors will still be needed by certain customers, according to the manufacturer. Last week Intel Corp. unveiled its code-named Knights Corner chip, which is specifically designed to accelerate high-performance computing (HPC) tasks, and earlier this year the company unleashed its Xeon-series microprocessors that support reliability, availability and scalability (RAS) features, which are essential for mission critical applications that are served by the Itanium chips.
Despite Advances of Xeon, HPC Accelerators, Itanium Still in Demand

The gap between performance, feature-set and capabilities of Intel Xeon and Intel Itanium central processing units (CPUs) is closing. Nonetheless, IA64 microprocessors will still be needed by certain customers, according to the manufacturer.

Last week Intel Corp. unveiled its code-named Knights Corner chip, which is specifically designed to accelerate high-performance computing (HPC) tasks, and earlier this year the company unleashed its Xeon-series microprocessors that support reliability, availability and scalability (RAS) features, which are essential for mission critical applications that are served by the Itanium chips. Nonetheless, the world’s largest maker of chips is confident that the Itanium products will still be needed both in mid- and long-term future.

“Itanium enables Intel and HP to compete in the high-end, mission-critical UNIX market. Many in the industry believe that the combination of HP-UX and the Itanium architecture provides an exceptionally strong mission-critical solution, suitable for mainframe replacement. The Itanium architecture is at the base of a multibillion dollar business for HP, as well as being an important business for Intel,” said Patrick Ward, an Intel spokesman for Itanium business unit.

Last Monday Intel unveiled its Knights Corner device that targets high-performance computing segments, such as exploration, scientific research and financial or climate simulation, which will be made on Intel's 22nm manufacturing process and will feature “more than 50 processing cores” on a single chip, something that promises exceptional performance. The vast majority of workloads will still run best on Intel Xeon processors, and the Knights Corner will only help to accelerate select highly parallel applications. Earlier this year Intel launches Xeon CPUs that support Machine Check Architecture (MCA) Recovery, a feature that allows the silicon to work with the operating system and virtual machine manager to recover from otherwise fatal system errors, a mechanism until now found only in the company's Intel Itanium processor family and RISC processors.

“The recent Intel announcement of many integrated core (MIC) chips targets high-performance computing, not the mission-critical market that Itanium-based systems target. As you know, customers in the mission critical markets value the stability, reliability, and the vendor ecosystem backing their mission-critical solution. The latest, fastest processor is not their priority. Running the software their business depends (often UNIX-based) on a highly stable and reliable platform is crucial for them. Supplying that high-end mission critical market is a very big business for HP as well as other companies like Bull in Europe and Itanium OEMs in Japan and China. That is where Itanium-based systems earn billions of dollars,” added Mr. Ward.

Source: xbitlabs.com

08 June, 2010

No Windows For Atom Z600 “Moorestown” Platforms Ever – Intel


Share
Almost every modern personal computer has an x86 processor inside it. The programming code for x86 has transformed a lot over the years, but microprocessors still can run it thanks to operating systems by Microsoft Corp. But it looks like one of the strategic partners of Microsoft says goodbye for Windows: Intel Corp.’s Atom Z600-series “Moorestown” platform is just not designed for Windows, Intel claims. "Moorestown was designed for low-power and small form-factors, for example, tablets and smartphones. Hence, the design decision was to use the low power interfaces for handhelds, such as low power audio, NAND for storage, etc.,” said Claudine Mangano, an Intel spokeswoman.
Despite x86 Compliancy, Atom Z600 Cannot Run Windows OS

Almost every modern personal computer has an x86 processor inside it. The programming code for x86 has transformed a lot over the years, but microprocessors still can run it thanks to operating systems by Microsoft Corp. But it looks like one of the strategic partners of Microsoft says goodbye for Windows: Intel Corp.’s Atom Z600-series “Moorestown” platform is just not designed for Windows, Intel claims.

"Moorestown was designed for low-power and small form-factors, for example, tablets and smartphones. Hence, the design decision was to use the low power interfaces for handhelds, such as low power audio, NAND for storage, etc.,” said Claudine Mangano, an Intel spokeswoman.

Although Atom Z600-series system-on-chip (SoC) supports interesting new features and a multitude of technologies to trim down power consumption of core(/s), it is not enough to compete against ARM-based chips, which have even lower power consumption.

Eerier this week Intel unleashed Oak Trail, which essentially builds on Moorestown, but which was designed to support Windows, among other software solutions. The SoC is targeted at tablets as well as sleeker netbook designs.

“Moorestown was not designed to run Windows. It is designed to run flavors of Linux, including MeeGo and Android. Oak Trail builds on Moorestown. It includes Lincroft and Langwell, and then adds in some of the legacy IO to enable Windows solutions, among others,” added Ms. Mangano.

More here: xbitlabs.com

Sandy Bridge Is 22 Percent Smaller


Share
If you compare the next generation Sandy Bridge and current generation Arrandale / Clarksfield CPUs, it looks like that the new CPU will get some 22 percent smaller. When we say smaller we mean the physical package itself as the new chip should live to see 22 percent reduction in x, y and z BGA package. This is quite a big deal, as it will enable even thinner notebooks and it will be easier to make smaller notebook motherboards and make things even smaller and lighter.
Than Nehalem based BGA chips

If you compare the next generation Sandy Bridge and current generation Arrandale / Clarksfield CPUs, it looks like that the new CPU will get some 22 percent smaller.

When we say smaller we mean the physical package itself as the new chip should live to see 22 percent reduction in x, y and z BGA package.

This is quite a big deal, as it will enable even thinner notebooks and it will be easier to make smaller notebook motherboards and make things even smaller and lighter.

Sandy Bridge comes in dual and quad core variants and should be ready to ship in Q1 2011 and it will bring Intel’s version of the Fusion CPU + GPU, all in one chip.

More here: fudzilla.com

03 June, 2010

Intel's Best Chips Are Still Ahead Of It


Share
CHIPMAKER Intel's Moorestown, Oak Trail and Pine Trail details were given with tablet and phone schedules by Chipzilla's ultra mobility group chief Anand Chandrasekher at Computex 2010. Tablets using Intel's Atom Z6xx series processor variant Moorestown will appear later this year, Chandrasekher said, with phones arriving in the first half of 2011. Moorestown is "very similar" to Oak Trail, a chip expected next year, but the mobility group boss explained they differ in that Moorestown is for Meego and Android while Oak Trail is Windows focused and specifically for netbooks.
Computex 2010 Towns and trails

CHIPMAKER Intel's Moorestown, Oak Trail and Pine Trail details were given with tablet and phone schedules by Chipzilla's ultra mobility group chief Anand Chandrasekher at Computex 2010.

Tablets using Intel's Atom Z6xx series processor variant Moorestown will appear later this year, Chandrasekher said, with phones arriving in the first half of 2011. Moorestown is "very similar" to Oak Trail, a chip expected next year, but the mobility group boss explained they differ in that Moorestown is for Meego and Android while Oak Trail is Windows focused and specifically for netbooks. Intel expects Android's Froyo release to be ready for its chips by the third quarter.

Chandrasekher admitted that Moorestown power consumption is average for the target market but claimed first class performance despite that. He hinted that the price for Moorestowns will not be cheap, saying "you can expect us to be hungry but not stupid".

Chandresker also talked about Pine Trail. It is already available and is described on the company's website as a 2010 Atom netbook processor. But Chipzilla has not given it an alphanumeric series number yet, unlike Moorestown, which is the Z6xx series. In a bizarre twist despite Pine Trail being linked to a previously unknown "innovation platform" called Canoe lake by an Intel press release quoting its architecture group co-general manager David Perlmutter, Chandrasekher denied any knowledge of Canoe Lake with the ultra mobility chief asking The INQUIRER, "where did you hear about that?" Perhaps he doesn't read the Intel architecture group's press releases.

The future product Chandrasekher was ready to talk about was the son-of-Moorestown called Medfield, a 32nm scale system-on-chip (SoC). He said it is "tracking nicely the milestones" and it will have "significant" size and power reductions over Moorestown, which has a 21mW idle power consumption. He declined to give any timetable for its commercial launch. µ

Source: theinquirer.net

AMD Shows Off Fusion


Share
AMD has been showing off its new hybrid graphics-microprocessor chips. In a press release AMD said it is on schedule to show working chips later this year and launch the Accelerated Processing Units. AMD said that the Fusion design represents a significant shift in the architecture of personal computers, combining the microprocessor, which is great at processing big tasks one after another, with the graphics chip, which can process lots of small and similar tasks all at the same time.
Hybrid graphics-microprocessor chips

AMD has been showing off its new hybrid graphics-microprocessor chips. In a press release AMD said it is on schedule to show working chips later this year and launch the Accelerated Processing Units.

AMD said that the Fusion design represents a significant shift in the architecture of personal computers, combining the microprocessor, which is great at processing big tasks one after another, with the graphics chip, which can process lots of small and similar tasks all at the same time.

Rick Bergman, senior vice president and general manager of the AMD Products Group, showed off the APU technology in Taipei saying that hundreds of millions of us now create, interact with, and share intensely visual digital content.

“This explosion in multimedia requires new applications and new ways to manage and manipulate data.”

The first APUs are expected to ship in the first half of 2011, but AMD is describing the designs now so that it can get software developers working on making code to run on Fusion. Microsoft is providing DirectX multimedia software that works with Fusion.

Source here: fudzilla.com

AMD Initiates Sampling Of “Ontario” Processors, Targets Launch In First Half Of 2011


Share
Advanced Micro Devices said at Computex Taipei 2010 that the company had initiated sampling process of its code-named Ontario chips that contain both x86 general-purpose cores along with graphics processing engine on the same piece of silicon. Besides, the company said that the Ontario chips will be launched in the first half of 2011, which is slightly sooner than originally anticipated.“Ontario is a part of Brazos platform. Just like Llano, we are sampling it to customers today. We are demoing it at Computex [behind the closed doors].
AMD Begins to Ship Fusion Processors for Tablets, Netbooks, Other Ultra Low-Power Devices

Advanced Micro Devices said at Computex Taipei 2010 that the company had initiated sampling process of its code-named Ontario chips that contain both x86 general-purpose cores along with graphics processing engine on the same piece of silicon. Besides, the company said that the Ontario chips will be launched in the first half of 2011, which is slightly sooner than originally anticipated.

“Ontario is a part of Brazos platform. Just like Llano, we are sampling it to customers today. We are demoing it at Computex [behind the closed doors]. Expect this product to launch in the first half of 2011,” said Rick Bergman, senior vice president and general manager of AMD products group, during AMD’s press conference at the trade-show.

AMD Ontario features up to two x86 cores based on Bobcat micro-architecture, integrated DirectX 11-class graphics core and DDR3 memory controller. The Ontario accelerated processing unit (APU) will be made using bulk 40nm process technology and will feature monolithic design.

As reported previously, the Bobcat micro-architecture features x86-64, virtualization, SSE, SSE2, SSE3 technologies and will be single-threaded with out-of-order execution. The actual Ontario microprocessor, which is a dual-core chip, will be able to offer 90% of today’s “mainstream performance” in less than half of die area, according to the chip designer. AMD claims that Bobcat-based products are sub-1W capable, hence, such chips will be able to address products in various form-factors, including slate-type PCs. AMD also says that AMD Ontario solutions are single-chip products.

Source here: xbitlabs.com

Intel Introduces “Mainstream” Microprocessors For Overclockers


Share
At the Computex Taipei 2010 trade-show Intel Corp. unveiled its new microprocessors designed specifically for overclockers. The chips come with unlocked multipliers and hence allow to easily boost performance of such central processing units without any need to increase the stress onto mainboard and other components of the system. The new Intel Core i7-875K (4 cores/8 threads, 2.93GHz, 8MB L3 cache, 45nm) and Intel Core i5-655K (2 cores/4 threads, 3.20GHz, 4MB L3 cache, 32nm) designed for LGA1156 platforms belong to the New Unlocked Intel Core Processors family and are intended for enthusiasts or computer manufacturers who want to push their systems to the limit with all the necessary overclocking tools and features at their fingertips.
Intel Reveals Relatively Inexpensive Chips with Unlocked Multiplier

At the Computex Taipei 2010 trade-show Intel Corp. unveiled its new microprocessors designed specifically for overclockers. The chips come with unlocked multipliers and hence allow to easily boost performance of such central processing units without any need to increase the stress onto mainboard and other components of the system.

The new Intel Core i7-875K (4 cores/8 threads, 2.93GHz, 8MB L3 cache, 45nm) and Intel Core i5-655K (2 cores/4 threads, 3.20GHz, 4MB L3 cache, 32nm) designed for LGA1156 platforms belong to the New Unlocked Intel Core Processors family and are intended for enthusiasts or computer manufacturers who want to push their systems to the limit with all the necessary overclocking tools and features at their fingertips. As a result, the new processors come with unlocked core ratios to support “enhanced” performance tuning, Intel said.

The Intel Core i7-875K and Core i5-655K are priced at $342 and $216 respectively. Quite noteworthy is that the Core i7-870 processor is currently priced at $562, whereas the Core i5-650 at $176. It is more than probably that the price of the model i7-870 will shortly be decreased to below $342 level, though.

It is interesting to note that at least until the mid-nineties virtually all microprocessors – from Intel, Advanced Micro Devices, Cyrix, etc – featured unlocked multipliers since internal clock-speeds were already higher than bus frequencies, whereas such practice as overclocking was not wide-spread. However, after overclocking became more popular and because it was rather easy to falsify the marking in order to “hike” the clock-speed and sell the chips at higher price. Usually such chips malfunctioned. By the mid-aughts microprocessors not only sported locked multiplier, but their clock-speeds were flashed into their microcode, hence, despite of overclocking, the chips showed their default frequencies alongside their model numbers in special utilities.

Source here: xbitlabs.com

Intel Is Confident Of Its Sandy Bridge Integrated GPU


Share
CHIPZILLA'S Shmuel "Mooly" Eden of Intel's Israel team is one of the most famous recent microprocessor architects, having led the original Centrino architecture push and evolved it into efficient, fast "Core" CPUs that not only replaced the troubled Netburst, but also abruptly ended AMD's performance dominance in 2007. His team created the Sandy Bridge generation, expected to launch in mobile, mainstream and high end markets early next year. A lot is already known about the initial mainstream desktop and mobile Sandy Bridge part, including its four CPU cores together with one GPU core, all sharing 8MB of obviously shared L3 cache, which, just like other on-chip caches, is expected to have lower latency than the current Nehalem or Westmere parts.
Computex 2010 Will hold its own, says Mooly Eden

CHIPZILLA'S Shmuel "Mooly" Eden of Intel's Israel team is one of the most famous recent microprocessor architects, having led the original Centrino architecture push and evolved it into efficient, fast "Core" CPUs that not only replaced the troubled Netburst, but also abruptly ended AMD's performance dominance in 2007. His team created the Sandy Bridge generation, expected to launch in mobile, mainstream and high end markets early next year.

A lot is already known about the initial mainstream desktop and mobile Sandy Bridge part, including its four CPU cores together with one GPU core, all sharing 8MB of obviously shared L3 cache, which, just like other on-chip caches, is expected to have lower latency than the current Nehalem or Westmere parts.

Besides the architectural core execution efficiency improvements, there are also AVX 256-bit vector floating-point instruction extensions with the new 3-operand format, like on the good old RISC machines, and matching doubled vector floating-point units for substantial performance improvement once the code is recompiled. The official DDR3-1600 dual channel support and improved overall interconnects and power management round up the story.

The speed of that integrated GPU in Sandy Bridge was the target of a lot of speculation. Intel's supposed confidential slides circulating on the web mentioned around twice the speed of the current Core i5 6XX series CPU, which would be decent, but not exactly easy to be competitive against a low-end Radeon HD 55XX series derivative expected to be integrated into the top end AMD Fusion parts in the same timeframe. And AMD people I spoke to on condition of anonymity were confident of having better GPU performance in those parts than what Sandy Bridge would have, resulting supposedly in "better overall user experience" despite likely slower CPU cores.

When confronted with that opinion, Mooly told us that he is confident of the Intel part's top performance, processing technology advantage and much better CPU to GPU integration. The latter two do make sense since the tuned 32nm CMOS process is now mature in Intel's fabs. Also, as far as we know Sandy Bridge CPU and GPU cores communicate tightly at the shared L3 cache level, while AMD's Fusion components supposedly talk one level below, at the integrated memory controller and crossbar level.

On the other hand, to really beat AMD's HD55XX series GPU cores in its Fusion parts, and in the absence of Larrabee, Intel will have to work hard on that GPU core anyway, and I'm sure it knows that. Well, we will know too, in about six months, how far ahead both Intel and AMD have gone. µ

Source here: theinquirer.net

01 June, 2010

Leaked Intel Roadmap Details New Fall Core CPUs


Share
We've already seen laptops with Intel's new ULV Core i-series but it seems the company has quite a bit planned for this year. Engadget has uncovered and published an Intel roadmap detailing the chip giants entire fall collection. Engadet reports that, aside from the previously rumored successor to the Core i5-540M (the 2.66GHz / 3.33 GHz Core i5-580M) and the Core i7-740QM/840QM, we can also expect a few more dual-cores at the end of the year. These will come in the form the 2.8GHz Core i7-640M (which turbos to 3.46GHz) and the 2.66GHz / 3.2GHz Core i5-560M.



Wondering what Intel has planned for the rest of 2010 and 2011? Well, read on!

We've already seen laptops with Intel's new ULV Core i-series but it seems the company has quite a bit planned for this year. Engadget has uncovered and published an Intel roadmap detailing the chip giants entire fall collection.

Engadet reports that, aside from the previously rumored successor to the Core i5-540M (the 2.66GHz / 3.33 GHz Core i5-580M) and the Core i7-740QM/840QM, we can also expect a few more dual-cores at the end of the year. These will come in the form the 2.8GHz Core i7-640M (which turbos to 3.46GHz) and the 2.66GHz / 3.2GHz Core i5-560M.

Intel is also going hell for leather when it comes to Ultra Low Voltage chips. Q4 will bring us two 15W chips: a high-end Core i7-680UM (1.46GHz and turbos up to 2.53GHz) and a Core i5-560UM (1.33GHz / 2.13GHz). There'll also be a 25W Core i7-660LM that clocks in at 2.26GHz.

Engadget reports that all of these will have on die Intel HD graphics to tide us over until 2011 when we'll get WiMax, WiDi and Intel Bluetooth along with a new energy saving concept called Zero Power ODD. Zero Power will offer a power-saving sleep mode for noisy optical drives and enough battery life to play two Blu-ray movies on a single charge.

Source here: tomshardware.com

Intel Unveils Knights Corner Accelerator For Highly-Parallel Applications


Share
During the International Supercomputing Conference (ISC), Intel Corporation announced plans to deliver new products based on the Intel many integrated core (MIC) architecture that will create platforms running at trillions of calculations per second, while also retaining the benefits of standard Intel processors. Targeting high-performance computing segments such as exploration, scientific research and financial or climate simulation, the first product, codenamed "Knights Corner”, will be made on Intel's 22nm manufacturing process and will use Moore's Law to scale to more than 50 Intel processing cores on a single chip. While the vast majority of workloads will still run best on Intel Xeon processors, Intel MIC architecture will help accelerate select highly parallel applications.
Intel Reveals 50-Core x86 Special-Purpose Microprocessor

During the International Supercomputing Conference (ISC), Intel Corporation announced plans to deliver new products based on the Intel many integrated core (MIC) architecture that will create platforms running at trillions of calculations per second, while also retaining the benefits of standard Intel processors.

Targeting high-performance computing segments such as exploration, scientific research and financial or climate simulation, the first product, codenamed "Knights Corner”, will be made on Intel's 22nm manufacturing process and will use Moore's Law to scale to more than 50 Intel processing cores on a single chip. While the vast majority of workloads will still run best on Intel Xeon processors, Intel MIC architecture will help accelerate select highly parallel applications.

"Intel's Xeon processors, and now our new Intel Many Integrated Core architecture products, will further push the boundaries of science and discovery as Intel accelerates solutions to some of humanity's most challenging problems. The Intel MIC architecture will extend Intel's leading HPC products and solutions that are already in nearly 82 percent of the world's top supercomputers. Today's investments are indicative of Intel's growing commitment to the global HPC community," said Kirk Skaugen, vice president and general manager of Intel's data center group.

Industry design and development kits codenamed "Knights Ferry" are currently shipping to select developers, and beginning in the second half of 2010, Intel will expand the program to deliver an extensive range of developer tools for Intel MIC architecture. Common Intel software tools and optimization techniques between Intel MIC architecture and Intel Xeon processors will support diverse programming models that will place unprecedented performance in the hands of scientists, researchers and engineers, allowing them to increase their pace of discovery and preserve their existing software investments. The Intel MIC architecture is derived from several Intel projects, including "Larrabee" and such Intel Labs research projects as the Single-chip Cloud Computer (SCC).

"The CERN openlab team was able to migrate a complex C++ parallel benchmark to the Intel MIC software development platform in just a few days. The familiar hardware programming model allowed us to get the software running much faster than expecte,” said Sverre Jarp, chief technology officer of CERN openlab.

To meet the growing challenge of running large-scale simulations in the multi petaflops and exaflops range of computing, Intel, Forschungszentrum Julich (FZJ) and ParTec will announce a multi-year commitment to create the ExaCluster Laboratory (ECL) at Julich. The lab will develop key technologies, tools and methods to power multi petaflops and exaflops machines, focusing on the scalability and resilience of those systems. ECL will become the latest member of Intel Labs Europe, a network of research and innovation centers spanning Europe.

Source: xbitlabs.com

Random Post