Quantcast

26 February, 2010

AMD Readies Low-Power Server Platform


Share
For years Advanced Micro Devices has claimed that its central processing units (CPUs) for servers are more power-efficient compared to rivals from Intel Corp., however, while the latter offered specially-tailored low-power server platforms, AMD only relied onto its energy-efficient chips on standard platforms. But the things are going to change later this year when AMD launches its code-named Adelaide 2-way platform.
Adelaide: The Secret Weapon of AMD

For years Advanced Micro Devices has claimed that its central processing units (CPUs) for servers are more power-efficient compared to rivals from Intel Corp., however, while the latter offered specially-tailored low-power server platforms, AMD only relied onto its energy-efficient chips on standard platforms. But the things are going to change later this year when AMD launches its code-named Adelaide 2-way platform.

AMD Adelaide platform will be based on the code-named Lisbon six-core energy-efficient CPUs as well as AMD SR5650 core-logic (22 PCIe lanes, 9.6W TDP in low-power HT1 mode) with AMD SP5100 input/output controller. AMD Opteron 4160 EE and 4158 EE chips will be clocked at tremendously low clock-speeds – 1.60GHz and 1.50GHz – however, this makes us hope that the microprocessors will also consume dramatically low amount of power – up to 35W. At present AMD Opteron EE processors have 60W thermal design power (TDP) and 40W average CPU power (ACP).

But the low power consumption of Adelaide will come at a price: if the next-generation Maranello and San Marino platforms will feature HyperTransport 3 links, then Adelaide will have to rely HyperTransport 1 instead in order to reduce consumption of both CPUs and core-logic sets. Just like the code-named San Marino, AMD Adelaide will support up to six memory modules per socket, however, it will not support fast DDR3 modules, but will work with low-voltage DDR3 at the speeds of up to 1066MHz.

AMD’s energy-efficient six-core Opteron microprocessors will feature 3MB of level-two cache (512KB per core), 6MB of level-three cache, two HyperTransport 1 links and dual-channel DDR3 memory controller that supports up to PC3-8500 (DDR3 1066MHz) memory in addition to low-voltage DDR3 and quad-rank DIMMs. The chips will be compatible with C32 socket (LGA 1207) and will feature 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.

AMD did not comment on the news-story.

Source: xbitlabs.com


Intel Lists Its Core i7-930


Share
CHIP LEADER Intel has listed its Core i7-930 even though it is not supposed to formally make an announcement until February 28th. Chipzilla's next quad-core CPU has appeared ahead of launch at some European online stores.
CHIP LEADER Intel has listed its Core i7-930 even though it is not supposed to formally make an announcement until February 28th.

Chipzilla's next quad-core CPU has appeared ahead of launch at some European online stores. The Core i7-930 is eagerly awaited. Its prototypes were called "Bloomfield" and it will probably kill off the Core i7-920 model.

The processor is built on the 45nm manufacturing process and its four cores run at 2.80GHz. It has 256KB of L2 cache memory per chip and an 8MB L3 cache. It supports Hyper-Threading and comes with eight threads in total. It also has an integrated triple channel DDR3 memory controller that will enable the CPU to be paired with large amounts of high-speed, top-tier memory.

There should be additional performance gains using Intel Turbo Boost technology, and Intel has said that the Core i7 has extra features, such as the Enhanced Halt State, Extended Stop Grant State, Deep Sleep State, Deeper Sleep State and Deep Power Down for those who think actually turning it off is a bad idea.

Intel's Core i7-930 is currently listed at the price of €254.86. ยต

Source: theinquirer.net


Core i7 940XM Comes In Q3 10


Share
Intel is preparing to launch yet another extreme mobile processor, something to top the current performance king the Core i7 Extreme 920XM. This CPU is an upgrade for Calpella high end performance notebook and it comes in Q3 2010.
2.13GHz extreme quad core

Intel is preparing to launch yet another extreme mobile processor, something to top the current performance king the Core i7 Extreme 920XM. This CPU is an upgrade for Calpella high end performance notebook and it comes in Q3 2010.

The clock speed stops at 2.13GHz but this quad core automatically overclocks all the way to 3.33GHz. This will only happen if it doesn’t get that hot. TDP remains at high 55W and this quad core still supports the quite useless Hyperthreading.

This Clarksfield 45nm CPU comes with 8MB cache and 1333MHz DDR3 support. The only ironic thing about this CPU is that 2.66 GHz Dual-Core Core i7 620M that will overclock to 3.33GHz might easily end up as fast as the much more expensive Core i7 Extreme 940XM that will launch soon.

Source: fudzilla.com


Core i7 980 Extreme Edition Crops Up


Share
We’ve written about this CPU on plenty of occasions, but our colleagues from TechReport have come across an EU listing of Intel’s new addition to its i7 series – the Core i7 980 Extreme Edition. We’ll recap real quick – this is the first six core CPU for desktops and are based on 32nm Westmere architecture.
€1.099,-

We’ve written about this CPU on plenty of occasions, but our colleagues from TechReport have come across an EU listing of Intel’s new addition to its i7 series – the Core i7 980 Extreme Edition.

We’ll recap real quick – this is the first six core CPU for desktops and are based on 32nm Westmere architecture. It comes with HyperThreading, 12MB of L3 cache and supports turbo boost up to 3.6GHz. It features DDR3 support up to 1066MHz and its TDP will be at 130W.

The listing puts the CPU’s price at € 1.099,-, which is pretty good as the same retailer sells i7-975 Extreme Edition at only a tad lower price. The e-tailer lists availability date as March 14th.

You can find the CPU listed here. (in German)

Source: fudzilla.com


22 February, 2010

AMD Begins Revenue Shipments Of Twelve-Core Opteron Microprocessors


Share
Advanced Micro Devices said Friday that it had started shipments of its highly-anticipated twelve-core AMD Opteron microprocessors code-named Magny-Cours. The company indicated that the shipments are limited and are intended to prepare for the launch of servers powered by the new chips due later this quarter.
AMD Has Shipped “Limited Number” of Production Magny-Cours Chips

Advanced Micro Devices said Friday that it had started shipments of its highly-anticipated twelve-core AMD Opteron microprocessors code-named Magny-Cours. The company indicated that the shipments are limited and are intended to prepare for the launch of servers powered by the new chips due later this quarter.

“We have been aggressively sampling production-level parts to customers for nearly 30 days now and have actually shipped a limited number of production parts to allow customers to prepare for launch – on track for later this quarter,” said Phil Hughes, a spokesman for AMD.

AMD Opteron microprocessors transformed Advanced Micro Devices from a producer of inexpensive desktop chips into a world-class supplier of microprocessors for servers back in 2003. At that time the code-named SledgeHammer processor with one processing core and up to 2.40GHz clock-speed brought a number of breakthrough innovations that redefined the mainstream server industry, including integrated memory controller, chip-to-chip interconnect for multi-processor systems, x86-64 capability and a number of other improvements. Seven years later the Magny-Cours processor is supposed to once again transform the server market with twelve x86 processing engines, quad-channel memory controller as well as new high-speed chip-to-chip interconnection. This time, however, AMD Opteron will have to fight against Intel Corp.’s octa-core Xeon processor that not only has the benefits of the Nehalem micro-architecture, but also boasts with a number of reliability, availability, serviceability (RAS) advantages presently only found in mission-critical servers, such as those based on Intel Itanium, IBM Power or Sun UltraSPARC microprocessors.

Central processing units for servers are sold at a great price-premium, which is why it is crucially important for both Sunnyvale, California-based AMD as well as Santa Clara, California-based Intel to have the best microprocessors for server markets as such chips bring very high profit.

According to preliminary information from unofficial sources, the mainstream line of twelve-core AMD Opteron 6000-series processors will consist of three chips operating at 1.90GHz, 2.10GHz and 2.20GHz. Besides, AMD will also release highly efficient (HE) and special edition (SE) AMD Opteron 6000 microprocessors with twelve processing engines functioning at 1.70GHz and 2.30GHz, respectively. In addition, AMD plans to launch three standard-voltage eight-core chips at 2.0GHz, 2.30GHz and 2.40GHz frequencies along with two HE eight-core processors at 1.80GHz and 2.0GHz clock-speeds. In order to ensure maximum stability, all AMD’s twelve-core processors will come with reduced clock-speed of integrated memory controller and L3 cache (1.80GHz) compared to six-core and quad-core products.

Even though clock-speeds of AMD Opteron 6000-series processors are not high, AMD will still increase thermal design power of Maranello server platform. Based on preliminary information, AMD G34 (1944-pin) CPUs will have 85W, 115W or 140W TDP, which is somewhat higher compared to TDPs supported by existing multi-processor platforms.

More here: xbitlabs.com


AMD Emphasizes Energy Efficient Opterons


Share
This week's Server Den steps back from the systems side to take a look at one of the processors which powers it all. I'm talking about AMD's Opteron, which famously shook up the category when it launched in 2003 as the industry's first 32/64-bit architecture.
This week's Server Den steps back from the systems side to take a look at one of the processors which powers it all. I'm talking about AMD's Opteron, which famously shook up the category when it launched in 2003 as the industry's first 32/64-bit architecture. Opteron is even more notable for its groundbreaking jettisoning of the front-side bus in favor of direct connectivity between the CPU and memory and I/O.

I'm going to dive into my interview with Nigel Dessau [picture at right], AMD's chief marketing officer, soon, but first some background. The middle years of the last decade, when AMD was widely acknowledged to have achieved a lead in server processor performance, has since receded into a more traditional neck-in-neck battle. In 2009, Intel reset the bar with Nehalem. AMD parried with its new "Istanbul" Opterons.

Currently, AMD is attacking the server space on both the performance and energy efficiency fronts. At the high end, AMD is readying its Opteron 6100 series processor, aka Magny-Cours, which will come in eight- and 12-core versions. Power savings are spotlighted in the Opteron 4100 series, due this quarter. As I discussed in my recent interview with HP, reining in electricity costs may not be sexy, but it's the largest--and most easily addressed--item on the checklist for anyone buying servers, so this is a smart play on AMD's part.

It's good to see AMD moving forward as a continuing processor player. Its ongoing and healthy market presence might not have been predicted if one had been paying close attention to its challenged financial results over the past several years. However, the company put itself on a revived footing in 2009. That was accomplished by spinning off its chip manufacturing operation into a separate company called GlobalFoundries.

More here: informationweek.com


18 February, 2010

Intel Planning Faster Core i3/Core i7 CPUs For Q2?


Share
Fudzilla believes Intel plans to offer faster Core i3 and Core i7 (Lynnfield) CPUs sometime next quarter. On the Core i3 front, the site claims that Intel plans to offer a third Core i3 SKU, the Core i3-550, which will be clocked at 3.2GHz. Other key specs will carry over unchanged.
Fudzilla believes Intel plans to offer faster Core i3 and Core i7 (Lynnfield) CPUs sometime next quarter.

On the Core i3 front, the site claims that Intel plans to offer a third Core i3 SKU, the Core i3-550, which will be clocked at 3.2GHz. Other key specs will carry over unchanged.

When the new i3 CPU arrives, Fudzilla expects the 540 will finally displace Intel's Core 2 Duo E8600, pushing the Wolfdale processors into the bargain bin of the CPU market.

For enthusiasts, Fudzilla says Intel will release the Core i7-880 next quarter. The chip will supposedly be clocked at 3.06GHz, with Turbo Mode taking speeds as high as 3.73GHz.

With these kind of specs, the Core i7-880 could potentially step on the toes of the Bloomfield-based Core i7-950 and 960, but remember that Intel plans to introduce the first 6-core desktop parts shortly.

Source: firingsquad.com


AMD To Launch Four Six-Cores In Q2


Share
We just received word that AMD plans to launch a total of four six-core CPUs and while some of them will share the same specification, it will not be the case for the TDP. The top one is going to be called Phenom II X6 1075T and it will have 125W. Some people have suggested that there will be a faster version of this CPU with 140W but we are not aware of that at press time.
95 to 125W TDP

We just received word that AMD plans to launch a total of four six-core CPUs and while some of them will share the same specification, it will not be the case for the TDP.

The top one is going to be called Phenom II X6 1075T and it will have 125W. Some people have suggested that there will be a faster version of this CPU with 140W but we are not aware of that at press time.

The runner up is Phenom II X6 1055T and this one will come in 125 and 95W variants. The last one is named Phenom II X6 1035T and comes with lower frequency and 95W. We heard that the entire line-up will end up at lower than 3GHz clock speed but we don’t know the exact values, at least not at press time.

The launch date is Q2 2010 but we don’t have any better date than that.

Source: fudzilla.com


Intel 65nm CPUs production To Stop In Q3 10


Share
Intel has revealed to its special few that in Q1 2010 65nm CPUs are still representing quite low 3 percent of its total shipment. This is set to shrink to 2 percent in Q2 and one percent in Q3 and if all goes well Intel's percentage of 65nm will sink below one percent and probably disappear in Q4 2010.
45nm products dominant

Intel has revealed to its special few that in Q1 2010 65nm CPUs are still representing quite low 3 percent of its total shipment. This is set to shrink to 2 percent in Q2 and one percent in Q3 and if all goes well Intel's percentage of 65nm will sink below one percent and probably disappear in Q4 2010.

In the mean time 45nm is at its peak as in Q1 massive 85 percent of CPUs are 45nm and some 12 percent are being manufactured in 32nm. In Q2 the 45nm process shanks to 78 percent while 32nm grows to 20 percent and in Q3 45nm drops further to 71 percent of all CPUs while 32nm jumps to 28 percent, more than two times of what Intel plans to ship in Q1 2010.

In Q4 Intel plans to churn out some 65 percent of its CPUs in 45nm, while the remaining 35 percent will be manufactured in 32nm. We are sure that the number of 32nm CPUs will overtake 45nm by mid-2011.

Source: fudzilla.com


AMD Receives Grant to Develop Fusion Processors


Share
Advanced Micro Devices has announced that it had entered a memorandum of understanding under which its Canadian subsidiary would be awarded by a five-year grant of $52.8 million to fund research and development activities in the development of the code-named Fusion accelerated processing units (APUs) that combine x86 and graphics processing cores onto the same chips.
Canadian Government Supports Development of AMD Fusion

Advanced Micro Devices has announced that it had entered a memorandum of understanding under which its Canadian subsidiary would be awarded by a five-year grant of $52.8 million to fund research and development activities in the development of the code-named Fusion accelerated processing units (APUs) that combine x86 and graphics processing cores onto the same chips.

Canadian Ontario state expects to make its initial investment of $11.2 million CAD to AMD upon signing the formal agreement, with periodic payments occurring thereafter throughout the grant period. In turn, AMD will commit to substantially invest in AMD Fusion processor-related R&D activities in Markham, and retain and create hundreds of high-value R&D jobs during the grant time frame. AMD also plans to increase collaborative activities with local universities.

AMD’s subsidiary in Canada was obtained back in 2006, when AMD acquired ATI Technologies, the company that specialized on development of graphics processing units (GPUs) as well as core-logic sets. As AMD’s largest R&D center outside the United States, AMD Canada employs more than 1600 people, including an average of 100 engineering student participants in its internship and co-op programs.

“With this partnership, Ontario will be at the forefront of helping to bring this game-changing technology to market, and will deepen the province’s reputation as a seat of technology innovation. AMD Fusion technology is set to enable significant breakthroughs in personal computing and our R&D facility in Markham, Ontario is playing an instrumental role in creating this technology.” said Dirk Meyer, AMD president and chief exec.

Source: xbitlabs.com


AMD’s Twelve-Core Microprocessors Available For Sale


Share
Oakville Mehlville Computers, a maker of custom servers and workstations from Missouri, has started to sell twelve-core AMD Opteron 6174 microprocessors for servers at an Ebay auction. The chips are not officially launched yet, even though the processors do not look like engineering samples and may belong to the first mass-production batch of twelve-core chips.


Company Sells AMD Opteron 6174 Processors at Ebay

Oakville Mehlville Computers, a maker of custom servers and workstations from Missouri, has started to sell twelve-core AMD Opteron 6174 microprocessors for servers at an Ebay auction. The chips are not officially launched yet, even though the processors do not look like engineering samples and may belong to the first mass-production batch of twelve-core chips.

The manufacturer of custom high-end machines sells a set of four AMD Opteron 6174 microprocessors with 2.20GHz clock-speed, 12MB of unified level-three cache and 6MB level-two cache (512KB of cache per core). The central processing units code-named Magny-Cours have quad-channel PC3-10600 (DDR3 1333MHz) memory controller and are designed for socket G34 platform.

The starting bid for the set of four tray microprocessors is $6500, the seller may also sell the central processing units for a total price of $8000 immediately. The seller does not offer an actual mainboard or cooling systems for the chips separately, hence, for the vast majority of potential buyers the chips will be useless, it is even impossible to test whether they work, a not very good thing since no returns are accepted. Interestingly, but Oakville Mehlville Computers also offers complete 48-core server running AMD’s twelve-core microprocessors for $20000.

Considering the fact that the microprocessors carry their official model number and marking, it is possible that those chips are not evaluation or development samples, but are the chips produced by AMD in mass quantities using 45nm SOI fabrication process. When asked for a comment whether the company has already started to ship its next-gen server microprocessors for revenue, AMD decided not to comment on the matter, but to re-emphasize the commitment to start their shipments in Q1 2010.

“What I can confirm for you at this point is that Magny-Cours is on track to launch in the current quarter,” said Phil Hughes, a spokesperson for AMD.

Source: xbitlabs.com


12 February, 2010

AMD Discloses Peculiarities of 32nm Llano Microprocessors.


Share
At the International Solid-State Circuits Conference (ISSCC) Advanced Micro Devices has disclosed peculiarities regarding its x86 microprocessors produced using 32nm silicon-on-insulator process technology with high-K metal gate (HKMG) technology. Apparently, AMD’s first Fusion chip code-named Llano will be able to dynamically scale clock-speeds of its x86 cores in order to boost performance or trim power consumption.
AMD Confirms Dynamic Speed Boost for 32nm SOI x86 Chips

At the International Solid-State Circuits Conference (ISSCC) Advanced Micro Devices has disclosed peculiarities regarding its x86 microprocessors produced using 32nm silicon-on-insulator process technology with high-K metal gate (HKMG) technology. Apparently, AMD’s first Fusion chip code-named Llano will be able to dynamically scale clock-speeds of its x86 cores in order to boost performance or trim power consumption.

As reported, AMD Llano accelerated processing unit (APU) will have four x86 cores based on the current micro-architecture each of which will have 9.69mm² die size (without L2 cache), a little more than 35 million transistors (without L2 cache), 2.5W – 25W power consumption, 0.8V – 1.3V voltage and target clock-speeds at over 3.0GHz clock-speed. The clock-speeds will dynamically scale their clock-speeds and voltages within the designated thermal design power in order to boost performance when a program does not require all four processing engines or trim power consumption when there is no demand for resources.

In order to further reduce power consumption and enable all the aforementioned characteristics, AMD had to implement a number of innovations into the chip on process technology and design levels:

• Core power gating: thanks to the new “power gating-to-ground” approach enabled by SOI manufacturing process, AMD can completely disconnect cores from the power grid. According to AMD, usage of NFET power gating transistor reduces power leakage versus previous power gating solutions by 10 times. Besides, ground-gating can also use the much more conductive chip package for gate supply redistribution rather than a special thick metal layer on the die.
• Digital APM module: each of AMD’s x86 cores feature their own digital power meters which allow to measure actual load of each core very precisely and deliver accurate information to the chip’s power manager that accurately tunes each core’s clock-speed, voltage and other characteristics in accordance with the actual load. As a result, AMD’s Llano processors will be able to overclock select cores within the CPU and disconnect the others to deliver higher performance without increasing power consumption.
• Power aware clock grid design: the new power grid design reduces clock switching power by two times, clock grid metal capacitance by 80% and the number of final clock buffers by 50%.
Interestingly, AMD has not disclosed any details regarding operation of built-in ATI Radeon HD 5000-class graphics core as well as memory controller.

AMD’s and Globalfoundries’ 32nm SOI process will use high-k metal gates, 11 copper metal layers with low-k dielectric, silicon germanium-based strained silicon to improve performance as well as second generation immersion lithography.

More here: xbitlabs.com


Intel to Release Sandy Bridge Processors, New Infrastructure in Q1 2011 – Source.


Share
Intel Corp. plans to release its next-generation microprocessors based on the code-named Sandy Bridge micro-architecture in Q1 2011, sources familiar with Intel Corp.’s plans told X-bit labs. The initial processors based on the new micro-architecture will not aim at the high-end market, but will still not be compatible with current mainstream infrastructure and will require new sockets and chipsets.
Intel’s Initial Sandy Bridge Will Not Target High-End Market

Intel Corp. plans to release its next-generation microprocessors based on the code-named Sandy Bridge micro-architecture in Q1 2011, sources familiar with Intel Corp.’s plans told X-bit labs. The initial processors based on the new micro-architecture will not aim at the high-end market, but will still not be compatible with current mainstream infrastructure and will require new sockets and chipsets.

The first Intel Sandy Bridge chips will feature two or four cores with Turbo Boost and Hyper-Threading technology as well as integrated graphics processor that will actually be on the same die as the x86 cores, according to previous reports. The chips will address mainstream market segments currently served by Intel Core i7, Core i5 and Core i3 processors, hence, there will be a lot of different models with 65W (dual-core, quad-core)or 95W (quad-core) thermal design power. The new processors will use LGA1155 form-factor and will be compatible with platforms based on the Intel 6-series chipsets code-named Cougar Point. It is noteworthy that while the new 6-series mainstream chipsets support Serial ATA-600 and some other innovations, the USB 3.0 does not seem to be a capability of the core-logic.

Some reports claim that six-core and eight-core Sandy Bridge-based designs will become available in Q2 2011 or later, hence, Intel is taking the same strategy as with Westmere micro-architecture and plans to initiate production of less complex processors first with higher-end models following later.

The key feature of Sandy Bridge Intel AVX (Advanced Vector Extensions) which, when used by software programmers, will increase performance in floating point, media, and processor intensive software, according to the Intel. Key features of Intel AVX include wider vectors, increasing from 128 bit to 256 bit wide, resulting in up to 2x peak FLOPs output. Enhanced data rearrangement, resulting in allowing data to be pulled more efficiently, and three operand, non-destructive syntax for a range of benefits. Intel AVX can also increase energy efficiency beyond the increases brought by the micro-architectural innovations, and is backwards compatible to existing Intel processors.

Intel did not comment on the news-story.

Source: xbitlabs.com


Intel to Launch Three Six-Core “Gulftown” Processors for Desktops


Share
Even though Intel Corp. plans to release its six-core processors already in Q1 2010, even a year from now the Core i7 chips code-named Gulftown will hardly become more or less mass solution even for high-end desktops. In fact, only three desktop six-core models are planned.
Intel’s Six-Core Chips Will Hardly Get Mass

Even though Intel Corp. plans to release its six-core processors already in Q1 2010, even a year from now the Core i7 chips code-named Gulftown will hardly become more or less mass solution even for high-end desktops. In fact, only three desktop six-core models are planned.

Intel’s plans to release Core i7-980X Extreme Edition microprocessor with six processing engines functioning at 3.33GHz for top-of-the-range desktop systems at $999 or higher price-point in the first quarter in an attempt to offer a truly unbeatable solution in the desktop space. In Q3 2010 the world’s largest maker of microprocessor plans to release another six-core Core i7-970 central processing unit that will run at 3.20GHz clock-speed and will cost lower compared to the older brother, sources familiar with Intel’s roadmap told X-bit labs. In addition, Intel mulls launching another six-core Core i7 Extreme chip in Q1 2011 to refresh the lineup and present the fastest solution for the LGA1366 platform. At present nothing exact is known about this processor, but it is highly likely that it will simply have frequency higher than 3.33GHz.

All six-core processors from Intel that will be available within the next twelve months will be based on the code-named Westmere micro-architecture, will be compatible with existing LGA1366 micro-architecture and will be made using 32nm HKMG process technology. Thanks to thinner fabrication process, despite the increased amount of cores, thermal design power of the new products will remain in the 130W range.

Although Intel has been vocal about benefits of multi-core microprocessors, it looks like the company does not see any tangible advantages for consumers that such chips can bring. Three models – Core i7-970, Core i7-980X and Intel Core i7-9xxX – which cost will be from $500 to over $1000 will hardly make six-core Gulftown central processing units truly popular on the market. Moreover, since Intel positions the six-core chips only for high-end desktops or workstations, the company does not plan to enable such technologies as TXT or AES-NI that are needed for commercial systems.

Intel’s motives to keep six-cores chips exclusivein the premium range are crystal clear: at present the company has no competition on the high-end desktop market and even AMD’s forthcoming six-core Phenom II X6 “Thuban” product will hardly change that. As a result, the company will comfortably sell its six-core CPUs to enthusiasts at maximum possible price.

Intel did not comment on the news-story.

Source: xbitlabs.com


AMD Releases A Benchmarking Tool


Share
CHIP DESIGN HOUSE AMD has released a benchmark selector tool that's designed to allow customers to sort and filter benchmark and performance data for servers using its four-core and six-core Opteron processors. Andy Parma, an AMD product marketing manager for servers and workstations said the tool will be enhanced soon to include data for servers using the 8-core and 12-core AMD Opteron 6100 Series processors.
Quad and hexa cores revealed

CHIP DESIGN HOUSE AMD has released a benchmark selector tool that's designed to allow customers to sort and filter benchmark and performance data for servers using its four-core and six-core Opteron processors.

Andy Parma, an AMD product marketing manager for servers and workstations said the tool will be enhanced soon to include data for servers using the 8-core and 12-core AMD Opteron 6100 Series processors.

The tool can filter for integer throughput performance of servers using low-power six-core AMD Opteron processors, sort data for mainstream processor models, higher performance SE processor models, and energy efficient HE and EE processor models.

It can also benchmark data by workload application, including virtualisation and compute-intensive high performance computing (HPC) applications.

An updated AMD website also includes data on the energy efficiency of servers using AMD Opteron processors and feature set comparisons and performance summaries.

Parma could not resist reminding people that some compilers, which he would not name but said began with the letter I, had a nasty habit of identifying some AMD chips as faster than others when they clearly were not.

He also said there is more involved in selecting a new server than just looking at the benchmark numbers. With that in mind, he encouraged customers to also consider the information available on other parts of the company's website, including its latest virtualization webinar.

AMD's benchmarking tool can be found here. ยต

Source: theinquirer.net


Intel’s Server King For 2010 Is Xeon X5680


Share
The game of chasing the latest and fastest CPU is getting quite boring. What most of you guys know as Gulftown Core i7 980X Extreme in the enthusiast desktop market will get a different brand in the server market.
Six cores, 3.33GHz

The game of chasing the latest and fastest CPU is getting quite boring. What most of you guys know as Gulftown Core i7 980X Extreme in the enthusiast desktop market will get a different brand in the server market.

Intel calls this six-core CPU generation simply Westmere EP and the fastest CPU throughout 2010 will be Xeon X5680 clocked at 3.33GHz with massive 12MB of cache, six-cores and twelve threads support. Apart of the different socket, it is the same CPU as Core i7 980X but the server one will sell for even more than $999 [Ridiculous. -Ed.] price.

The CPU supports DDR3 800, 1066 and 1333MHz as well as Intel’s Turbo boost. It is quite interesting seeing how Intel now thinks that controller overclocking is OK even for servers. TDP is 130W, so nothing new there, as this is always Intel’s top TDP at least with this kind of product.

As we already said, this market segment won’t initially be replaced by Sandy Bridge in Q1 2011, as Sandy designs are only dual or quad core. We are quite sure that Intel is working hard on a brand new next generation 32nm architecture for servers and for more than four cores, but we are not aware of any specifics.

Source: fudzilla.com


AMD To Sample Out First Fusion Chip In First Half


Share
Advanced Micro Devices will sample its first "Fusion" core microprocessor to OEMs and channel partners in the first half of 2010, the company said this week at the International Solid State Circuits Conference (ISSCC) in San Francisco. The mainstream PC processor, codenamed Llano, is the chip maker's first "Accelerated Processor Unit," or APU, said Samuel Naffziger, an AMD Senior Fellow presenting at ISSCC.
Advanced Micro Devices will sample its first "Fusion" core microprocessor to OEMs and channel partners in the first half of 2010, the company said this week at the International Solid State Circuits Conference (ISSCC) in San Francisco.
The mainstream PC processor, codenamed Llano, is the chip maker's first "Accelerated Processor Unit," or APU, said Samuel Naffziger, an AMD Senior Fellow presenting at ISSCC. Llano marks the first step in Sunnyvale, Calif.-based AMD's march towards a processor architecture that incorporates both x86-based central processor functionality and a graphics processor on the same CPU die, he said.

AMD has targeted 2011 for a pair of new x86 CPU core architectures, codenamed Bulldozer and Bobcat. Those new cores will be used in traditional CPUs, but will also be a big part of the development of APUs, processors that wed central processing with graphics processing in the future architecture that AMD has dubbed Fusion.

AMD has long held that it is in a unique position to create a Fusion product, claiming its main CPU rival Intel lacks leading graphics while its biggest graphics competitor Nvidia does not make x86 CPUs at all. That said, Intel has already released an early form of an APU with its latest client processors featuring graphics processing in a CPU package, but not on a single silicon die as AMD intends.

Llano, though it will ultimately be made available in 2011, will be based on AMD's current Phenom microarchitecture, rather than the Bulldozer and Bobcat cores coming out that same year, Naffziger said. But the Llano chips will be among AMD's first to utilize the 32-nanometer fabrication process, which will deliver several advantages over the chip maker's current 45nm process.

Intel released its first 32nm chips earlier this year and generally remains between a year to two years ahead of AMD on process technology.

Moving to 32nm involves the adoption of the high-K metal gate technology that Intel moved to in its own 45nm generation of products, Naffziger said. That, combined with AMD's leadership in immersion lithography for silicon fabrication and some design tweaks to the Phenom architecture will deliver advantages such as a 10x reduction in power leakage.

Llano will also have core-level power gating, delivering better power management on multi-core processors through the throttling up or down of individual cores as needed for a particular workload -- a feature that might be compared to Intel's Turbo Boost technology on many of its current-generation chips.

Source: crn.com


08 February, 2010

AMD Phenom II X6 “Thuban” Processors To Get Dynamic Speed Boost Technology


Share
In an attempt to provide maximum possible performance for enthusiasts, Advanced Micro Devices plans to implement a dynamic performance boost technology into its six-core processors known as Phenom II X6 “Thuban”.


AMD Phenom II X6 “Thuban” Processors to Get Dynamic Speed Boost Technology.

In an attempt to provide maximum possible performance for enthusiasts, Advanced Micro Devices plans to implement a dynamic performance boost technology into its six-core processors known as Phenom II X6 “Thuban”.

There is a clear trend towards increase of the number of cores inside central processing units (CPUs), just five years ago a dual-core chip was a dream, whereas now we are approaching six-core microprocessors. The software is, unfortunately, seriously behind the hardware and many applications still cannot take advantage of additional cores, but fully depend on clock-speeds. In order to provide maximum possible performance in such programs, developers of CPUs implement special dynamic performance boosting technologies that disable certain cores and overclock the rest.

At present only select Intel Corp.’s microprocessors feature Turbo Boost technology that can accelerate certain cores when they are needed while slowing down the unneeded cores. However, with the introduction of AMD Phenom II X6 “Thuban” processors similar capability will also be available on chips from Advanced Micro Devices, sources close to the company revealed to X-bit labs....

More here: xbitlabs.com


05 February, 2010

Intel Begins To Ship Next-Generation Itanium Processors For Revenue


Share
Intel Corp. this week announced that it had initiated shipments of the quad-core Intel Itanium processor code-named Tukwila. The chip that was delayed by years will be formally unveiled sometime in the first half of the year.
Intel Initiates Revenue Shipments of Itanium Tukwila Processors

Intel Corp. this week announced that it had initiated shipments of the quad-core Intel Itanium processor code-named Tukwila. The chip that was delayed by years will be formally unveiled sometime in the first half of the year.

“The newest Itanium processor has begun revenue shipments. The most advanced Itanium processor yet, ‘Tukwila’ more than doubles the performance of its predecessor and adds a range of new scalability, reliability, and virtualization features. […] The launch of this Itanium mission-critical processor is part of a major push Intel is making into the server processor arena, with several announcements slated for the first half of the year,” an official statement by Intel reads.

The new Itanium 2 is made using 65nm technology process and features four physical processing engines with Intel Hyper-Threading technology. The new chip has onboard memory controller and supports Intel QuickPath Interconnect (QPI) bus (previously known as common serial interconnect or CSI) in order to be compatible with platform elements developed for Intel Xeon processors. It is unknown whether quad-core Intel Itanium “Tukwila” chip is compatible with octa-core Intel Xeon “Beckton” processor.

Intel once stated that the first quad-core Itanium processors would be released “towards the middle of the decade” (which should probably mean 2005 - 2007) and then an executive from Sun Microsystems said that in 2007 Intel would present a platform that supports both IA32 and IA64 microprocessors (Tukwila will be the first chip to share infrastructure technologies with Xeon). However, in 2007 Intel itself said that it would launch the Tukwila in late 2008. Still, in early 2009 the world’s largest maker of chips said that Tukwila faces further delay till mid-2009 because Intel decided to add DDR3 support and change form-factor so that to ensure compatibility with future generations of Itanium chips.

Source: xbitlabs.com


Intel Announces Core i5, Core i7 With vPro


Share
Businesses looking to upgrade to the latest 32nm Intel CPU technology will be pleased to know that Intel today rolled out its fourth generation of vPro-enabled Core i5 and Core i7 chips. Key features of vPro include Intel Anti-Theft Technology, which frustrates thieves by locking access to a PC if a central server or built-in intelligence concludes it is lost or stolen.
Businesses now have special Westmere parts made just for them.

Businesses looking to upgrade to the latest 32nm Intel CPU technology will be pleased to know that Intel today rolled out its fourth generation of vPro-enabled Core i5 and Core i7 chips.

Key features of vPro include Intel Anti-Theft Technology, which frustrates thieves by locking access to a PC if a central server or built-in intelligence concludes it is lost or stolen. New Intel Anti-Theft Technology version 2.0 enables encryption solutions to disable access to cryptographic keys through hardware to completely block access to data, and also makes it simpler to reactivate a PC once in rightful hands. Also, a custom message can be displayed in a pre-OS screen of the disabled PC for anyone who tries to access the computer.

vPro also packs a new Intel Keyboard-Video-Mouse Remote Control (KVM Remote Control), features available with dual-core Intel Core i5 and i7 vPro processors work in conjunction with Intel integrated graphics, bringing a stop to IT administrators' frustration with having to ask users, "What do you see?" Instead, they will see users' displays just as the users do and have full control of the PC, even if the operating system is inoperative. Previously, KVM functionality required appliances that cost as much as $200 and more per PC.

"Businesses, particularly those that haven't purchased PCs for several years, face a computing environment that no longer handles the applications many workers and IT are adopting," said Rick Echevarria, vice president, Intel Architecture Group, and general manager, Business Client Platform Division. "The integration of intelligent performance along with smart security and cost-saving manageability features in the Intel Core vPro processor family provide IT and SMBs a no-compromise platform. We also are excited about how Intel vPro Technology gives IT the flexibility to look at client virtualization, consumerization and rich cloud applications."

Source: tomshardware.com


Fastest Sandy Bridge To Replace i7 930


Share
Intel's Core i7 930 is supposed to launch inQ1 2010 and this 2.8GHz quad-core should last all 2010 as the king of Intel’s MS3 fastest Mainstream category in the company's nomenclature. This should change in early 2011 as Sandy Bridge is supposed to replace this product.
2.8GHz mainstream quad core

Intel's Core i7 930 is supposed to launch inQ1 2010 and this 2.8GHz quad-core should last all 2010 as the king of Intel’s MS3 fastest Mainstream category in the company's nomenclature.

This should change in early 2011 as Sandy Bridge is supposed to replace this product. It is way too early to hear about any concrete clock speeds but we can confirm it’s a quad-core with improved performance clock to clock with Nehalem generation.

Sandy Bridge will also be the first quad-core to get a monolithic CPU with graphics, as today you can only get integrated graphics with Clarkdale / Arrandale 32nm CPUs which feature a stitched 45nm graphics core. Sandy Bridge will also be the first monolithic dual core, with totally integrated graphics into same die as the CPU.

Source: fudzilla.com


Gulftown i7 980X To Last All 2010


Share
Intel doesn’t have plans to introduce anything faster than the six-core Core i7 980X clocked 3.33GHz, at least not in 2010. This is the current plan that would only change if Intel feels challenged by AMD.
Sandy Bridge not for six cores

Intel doesn’t have plans to introduce anything faster than the six-core Core i7 980X clocked 3.33GHz, at least not in 2010. This is the current plan that would only change if Intel feels challenged by AMD.

Since we know that this is highly unlikely, the soon to be introduced Gulftown-based 3.33GHz six-core i7 980X will be the fastest CPU throughout 2010. Only in early 2011, in Q1, Intel plans to replace this CPU with something better and faster.

The interesting part is that Sandy Bridge won't replace the six-core CPUs, but we expect a six or more core CPU to take its place, of course in 32nm.

Sandy Bridge, like any Intel generation since 2006, is designed with the mobile segment in mind and these CPUs don’t even need quad cores. The market is happy with two cores as we don’t see much sense in quads for mobile computing.

Source: fudzilla.com


New Westmere Details Emerge: Power Efficiency And 4/6 Core Plans


Share
Today Intel started talking about its ISSCC plans and included in the conference call were some details on Westmere that I previously didn't know. Most of it has to do with power savings, but also some talk about 32nm quad-core Westmere derivatives!




Today Intel started talking about its ISSCC plans and included in the conference call were some details on Westmere that I previously didn't know. Most of it has to do with power savings, but also some talk about 32nm quad-core Westmere derivatives!

Westmere is Intel’s 32nm Nehalem derivative. Take Nehalem with all of its inherent goodness, add AES instructions, build it using 32nm transistors and you’ve got Westmere.

Westmere's Secret: Power Gated Un-Core

We just recently met the first incarnation of Westmere - Clarkdale, the dual-core processor that’s been branded the Core i3 and Core i5. Later this quarter we’ll meet Gulftown, a six-core Westmere that’ll be sold under the Core i7 label. All of that is old news, now for the new stuff.

With Nehalem Intel started power gating parts of the chip. Stick a power gate transistor in front of the supply voltage to each core and you can effectively shut off power (including leakage power) to the core when it’s not in use. This was a huge step in increasing power efficiency, something that’s evident when you look at Nehalem idle power numbers.

When you shut off a core you need to save the core’s state so that when it wakes back up it knows what to do next. Remember that power down these cores can happen dozens of times in the course of a second. The cores can’t wake up in a reboot state, they need to simply shut off when they’re not needed and wake back up to continue work when they are needed.

In Nehalem the core’s state (what instruction it’s going to work on next, data in its registers, etc...) is saved in the last level cache - L3. Unfortunately this means that the L3 cache can’t be powered down when the cores are idle, because that’s where they store their state information. Take this one step further and it also means that Nehalem’s L3 cache wasn’t power-gated.

In Westmere, Intel has added a dedicated SRAM to store core state data. Each core dumps its state information into the dedicated SRAM and then shuts off. With the state data kept out of the L3 cache, Westmere takes the next logical step and power gates the L3.

Intel lists this dedicated SRAM as a Westmere-mobile feature, there’s a chance it’s not present on the desktop chips. But it makes sense. Without a way of powering down the L3 cache, Westmere would be a very power hungry mobile CPU. Westmere appears to make it mobile-friendly...

More here: anandtech.com


01 February, 2010

AMD And Intel Preparing To Launch Six-Core Processors


Share
AMD plans to launch three six-core desktop processors (Thuban) under its new Phenom II X6 1000T series in May 2010, while Intel plans to launch its six-core desktop processors (Gulftown) beginning at the end of March, according to sources from motherboard makers. Three processors from AMD, the Phenom II X6 1075T, 1055T and 1035T, will each adopt a 45nm process.
AMD plans to launch three six-core desktop processors (Thuban) under its new Phenom II X6 1000T series in May 2010, while Intel plans to launch its six-core desktop processors (Gulftown) beginning at the end of March, according to sources from motherboard makers.

Three processors from AMD, the Phenom II X6 1075T, 1055T and 1035T, will each adopt a 45nm process. AMD will also launch the quad-core Phenom II X4 960T alongside the six-core models, the sources noted.

AMD will launch compatible 890FX (RD890) and 890GX(RS880D) chipsets that pair with its SB850 southbridge, a month prior to introducing the CPUs, the sources added.

Intel's six-core desktop offering will kick off with the Core i7-980X, which is expected to be priced more than US$1,000, the sources said.

Both AMD and Intel declined the opportunity to respond to this report saying they do not comment on unannounced products.

Source: digitimes.com


AMD Has New 45nm Quad Core – Zosma


Share
Delta Leonis is a star in the constellation of Leo and natives calls it Zosma. Some even calls it Zozma or Duhr. This science class is less important than the fact that AMD’s next generation 45nm quad core is codenamed Zosma.
Phenom II X4 960T is the name

Delta Leonis is a star in the constellation of Leo and natives calls it Zosma. Some even calls it Zozma or Duhr. This science class is less important than the fact that AMD’s next generation 45nm quad core is codenamed Zosma.

You can expect it as early as Q2 2010, probably the middle part of it, and it is set to launch together with three new Hexa cores. We have a strong reason to suspect that Phenom II X4 960T 95W TDP quad-core is a six-core with two cores disabled, but we cannot confirm this at press time.

We don’t know any clock speeds but we can tell you that it is a 45nm SOI (what else) part, that it supports DDR3 1333 and fits in AM3 motherboards. We still wonder what T stands for but we are quite sure it's not Terrestrial. Thuban perhaps?

More here: fudzilla.com


Intel Plans Core i7 970


Share
Intel plans a few new CPUs in the next quarters and now we've found out that the six-core Core i7 980X won't be the only 32nm Westmere based new high-end CPU to come in early 2010. We still don’t know whether Core i7 970 will have six-cores as Intel is keeping its mouth shut, but we highly suspect that this might be the slower version of yet another six-core high end CPU.
Westmere 32nm based

Intel plans a few new CPUs in the next quarters and now we've found out that the six-core Core i7 980X won't be the only 32nm Westmere based new high-end CPU to come in early 2010.

We still don’t know whether Core i7 970 will have six-cores as Intel is keeping its mouth shut, but we highly suspect that this might be the slower version of yet another six-core high end CPU.

If it would launch as quad core, which would make it the first 32nm quad core, but we still highly suspect that this is a six-core. Intel will probably update its plans in the next few weeks and we hope to get you updated as soon as we find that out.

It also uses a well known LGA 1366 socket and will match with X58 chipset based motherboards.

More here: fudzilla.com


Random Post