Sign up for our Technology Newsletter 
Intel Gives Exascale A Boost
Intel’s exascale computing efforts have received a boost with the extension of the company’s research collaboration with the Barcelona Supercomputing Center.
Begun in 2011 and now extended to September 2017, the Intel-BSC work is currently looking at scalability issues with parallel applications.
Karl Solchenbach, Intel’s director, Innovation Pathfinding Architecture Group in Europe said it was important to improve scalability of threaded applications on many core nodes through the OmpSs programming model.
The collaboration has developed a methodology to measure these effects separately. “An automatic tool not only provides a detailed analysis of performance inhibitors, but also it allows a projection to a higher number of nodes,” says Solchenbach.
BSC has been making HPC tools and given Intel an instrumentation package (Extrae), a performance data browser (Paraver), and a simulator (Dimemas) to play with.
Charlie Wuischpard, VP & GM High Performance Computing at Intel said that the Barcelona work is pretty big scale for Chipzilla.
“A major part of what we’re proposing going forward is work on many core architecture. Our roadmap is to continue to add more and more cores all the time.”
“Our Knights Landing product that is coming out will have 60 or more cores running at a slightly slower clock speed but give you vastly better performance,” he said.
Intel Releases 16GB Xeon Phi
Intel has announced five Xeon Phi accelerators including a high density add-in card while upping memory capacity to 16GB.
Intel has managed to get its Xeon Phi accelerator cards to power the Tianhe-2 cluster to the summit of the Top 500 list, however the firm isn’t waiting around to bring out new products. At the International Supercomputing show, Intel extended its Xeon Phi range with five new products, all of which have more than one TFLOPS double precision floating point performance, and the Xeon Phi 7120P and 7120X cards, which have 16GB of GDDR5 memory.
Intel’s Xeon Phi 7120P and 7120X cards have peak double precision floating point performance of over 1.2 TFLOPS, with 352GB/s bandwidth to the 16GB of GDDR5 memory. The firm also updated its more modest Xeon Phi 3100 series with the 3120P and 3120A cards, both with more than one TFLOPS of double precision floating point performance and 6GB of GDDR5 memory with bandwidth of 240GB/s.
Intel has also brought out the Xeon Phi 5120D, a high density card that uses mini PCI-Express slots. The firm said that the Xeon Phi 5120D card offers double precision floating point performance of more than one TFLOPS and 8GB of GDDR5 memory with bandwidth greater than 300GB/s.
That Intel is concentrating on double precision floating point performance with its Xeon Phi accelerators highlights the firm’s focus on research rather than graphics rendering or workstation tasks. However the firm’s ability to pack 16GB into its Xeon Phi 7100 series cards is arguably the most important development, as larger locally addressable memory means higher resolution simulations.
Intel clearly seems to believe that there is significant money to be made in the high performance PC market, and despite early reservations from industry observers the firm seems to be ramping up its Xeon Phi range at a rate that will start to give rival GPGPU accelerator designer Nvidia cause for concern.
Intel Shows More Ivy Bridge
June 19, 2013 by admin
Filed under Uncategorized
Comments Off on Intel Shows More Ivy Bridge
Last week Intel officially released Haswell, but there’s still life in good old Ivy Bridge. The chipmaker has announced a range of low-end Ivy parts and even a Sandy Bridge based Celeron.
The Celeron G470 is possibly the last consumer Sandy Bridge we will ever see. It is a single-core 35W part clocked at 2GHz and it’s priced at just $37.
However, Ivy Bridge parts are a bit more interesting. They include the Celeron 1017, a dual-core, dua-thread chip clocked at 1.6GHz, with a TDP of just 17W. It costs $86 and should be a nice part for low-end laptops and nettops. The Celeron 1005M also costs $86, but it has a 35W TDP and a 1.9GHz clock.
There are four new G2000 Pentiums as well. The G2140 and G2030 are 55W parts, clocked at 3GHz and 3.3GHz respectively. The G2120T and G2030T are 35W chips, clocked at 2.6GHz and 2.7GHz. They cost $64 and $75 respectively. Of course, Pentiums don’t feature Hyperthreading and all four of them are dual-core parts.
The Core i3 line-up also got some speed bumps. The Core i3-3245 and 3250 are clocked at 3.4 and 3.5GHz and both have a TDP of 55W. The 3245 features HD 4000 graphics and costs $134, while the 3250 ends up with HD 2500 graphics and a price tag of $138. Lastly, the Core i3-3250T is a 3GHz part with a 35W TDP, it costs $138, just like its 55W sibling.
Ivy Bridge E Delayed Until Fall
y Bridge E, Intel’s ultra-high end chip that is set to replace the Core i7 3970X, has been delayed. It doesn’t look like it was anything major. Our sources tell us that the decision was made by Intel server guys who did not want to launch this chip in Q3 as originally indented.
Since Q3 starts in July, a relatively slow month for IT, the normal time to launch products is late August or September, but at this time there is no confirmation that this will happen at this time.
Sandy Bridge E, or Core i7 3960X, was launched in Q4 2011, November 14th to be precise. This can give you a clue on when to expect the successor.
Originally Ivy Bridge E was supposed to launch in Q3, one quarter after the launch of quad-core Desktop Haswell processors. Ivy Bridge E works in X79 motherboards but we do expect that a few key motherboard vendors will have their newer versions ready for the launch of the new $999 flagship processor.
If Intel continues at this pace, it will take quite a while before we see Haswell E in action.
Intel Changes Course
Intel has changed its strategy when it comes to talking about its next generation technology. Back at IDF 2012, the company mentioned Haswell second generation 22nm CPUs and even explained some of its core technology, although it didn’t actually show any demos.
People got excited about Core i5 and Core i7 next generation Haswell parts that can ship with 10W TDP, but Intel hasn’t actually shown anything. When we asked a few people inside the company, they said that Intel isn’t planning on revealing too much, as they want to surprise the competition a bit more than they used to.
It’s quite clear that Haswell has every chance to beat AMD’s including 2013 Vishera successors. Intel obviously wants to see the market’s reaction to many ARM competitors, since some of them run Windows 8 RT just fine.
Intel Going High-Performance
Intel has been hinting that it is developing high-performance lower power server chips to speed up cloud services or data-intensive applications like analytic.
Apparently this will involve the integration of a converged fabric controller inside future server chips. This will make server communication faster while helping data centers operate at peak efficiency.
Raj Hazra, vice president of the Intel Architecture Group said that Fabric virtualises I/O and ties together storage and networking in data centres. If you add in an integrated controller you get a wider pipe to scale performance on cloud platforms. He said that the integrated fabric controller will appear in the company’s Xeon server chips in a few years as part of Intel’s cunning plan to bring the controller to the transistor layer.
Intel Goes Wireless
Maho Bay is a desktop platform wrapped around the recently launched Ivy Bridge desktop processor and Intel plans to enrich this platform with a Wireless mini card offer of its own.
The plan is to make new SKUs based on half Minicard (mPCIe) standard and offer it with its boards that have support for PCIe 1X or faster. Maho Bay also allows some combinations with Sandy Bridge processors and will allow the use of these mini Wireless cards on older processors with new boards. It looks like the Panther Point chipset is necessary even for older Sandy Bridge processors on Maho Bay platform.
The top range card with premium performance is Intel Centrino Ultimate N 6300, and the card has virtually the same specification like its mobile brother. It supports Intel Wireless Display as well as Intel My Wifi technology and quick driver connect.
Since it is using 3×3 antennas and MIMO standard it us capable of achieving speeds of 450Mbits per second and it does support multiple streams. It supports dual band 2.4 + 5 GHz and Intel Vpro. This is still a 802.11n based product as Intel hasn’t really jumped the gun to support 802.11ac in 2012.
It looks like it is too early for Intel to embrace this new standard due to its very limited market penetration.
Intel Increasing Supplier Audits
Intel has audited almost five times as many of its suppliers in 2011 than it did the previous year.
Chipzilla set itself a target of visiting 50 on-site, third-party audits of its suppliers during the last year. It had that target last year as well, but missed it by only carrying out 49 audits, while one had to be rescheduled.
In comparison Intel only carried out eight visits in 2010. The company also conducted 249 in-depth assessments and 289 self-assessments by suppliers.
But the findings were not that great. Intel found 426 priority and major findings, the highest class of non-compliance as defined by the company.
Most of the non-compliance related to management systems such as a lack of documentation and systems for CSR, inadequate communication with workers or suppliers and a lack of audits. But there were also 112 instances of labour abuse, which included working hours of more than 60 hours per week, and workers not being given at least one day off a week. There were also 28 issues relating to ethics, such as not having an anonymous reporting line for employees to raise issues or concerns through.
The report was interesting because it must have covered Foxconn, which has been the subject of criticism over its treatment of workers. During 2011, Intel carried out audits at three Foxconn facilities and found them about as bad as others in the region. Most of the breaches of rules were in the areas of labour conditions, safety systems, and management systems.
Is Ivy Bridge Better Than Llano?
Ivy Bridge notebook and desktop chips will start to surface in late April. It all starts with quad cores on April 29th and in late May early June it expands to dual cores.
Since Anand already benchmarked Ivy Bridge desktop 3770K, we got quite a nice glimpse of what to expect from Ivy Bridge graphics. Still, our sources are telling us that the final graphics scores will end up significantly faster, once the new launch driver gets ready.
You should expect Llano-class performance from Ivy Bridge we were told. Llano scales from HD 6370 integrated graphics all the way to the HD 6550 DirectX 11 core, and Ivy Bridge scores should come very close to this.
Ivy Bridge Chips May Cost Under $100
March 15, 2012 by admin
Filed under Uncategorized
Comments Off on Ivy Bridge Chips May Cost Under $100
We still don’t know the official branding of Ivy Bridge Pentium chips, but we are aware of plans for at least one SKU.
Intel plans to launch a Pentium branded Ivy Bridge and replace the G860 Pentium that currently holds the key position in L3 Legacy market. This 3.0GHz 32nm Sandy Bridge dual-core with two treads is currently available and sells for $86. Let’s not forget the 3MB cache size.
In Q2 2012 the Pentium family gets a new member, the 3.1GHz clocked G870, and both G870 and G860 get replaced in L3 market segment by an unnamed Ivy Bridge Pentium. We know that it should start selling for $86 and that this will be the cheapest of 22nm based desktop Ivy Bridge.