Monday, November 24, 2014

Intel's Knights Hill in 2017


___________________________  
99% BAD HARDWARE WEEK: Omni PAth is Intel's fiber optics based network. Knights Landing will support  Omni Scale interfaces directly on a chip.

Sunday, November 23, 2014

Japan can't reach exaflops by 2020 ?


But Akinori Yonezawa, deputy director at the Riken Advanced Institute for Computational Science, said, in an interview Tuesday, that the goal is to now build a 200- to 600-petaflop system by 2020, not an exascale system.
Not a merchant product, the new Sparc64 XIfx will appear only in Fujitsu supercomputers. The company has withheld the die size, power consumption, cost, package details, and production schedule, but we estimate the chip measures 500mm2, consumes 200W (typical), and will begin production in 1H15. Using the new processor, Fujitsu hopes to build a system that can execute more than 100 petaflops—three times better than today’s fastest supercomputer.  Hopefully in 2016.
___________________________  
99% BAD HARDWARE WEEK: Then 200 PFlops in 2018. And 600 PFlops in 2020. EXA only in 2023.

Friday, November 21, 2014

Intel goes 3D NAND 10 TB drive




Intel plans to ship 3D NAND flash chips next year that will allow it to cram more bits into solid-state storage.
___________________________  
99% BAD HARDWARE WEEK: 2 mm high NAND stack at 1 TB, 10 such stacks for PCI4.0 10 TB drive above

Sunday, November 16, 2014

Five-year-old passes Microsoft exam !

Ayan Qureshi is now a Microsoft Certified Professional after passing the tech giant's exam when he was just five years old.
___________________________  
99% BAD HARDWARE WEEK: But do you have to help Microsoft's pro too ?
Any way, clever way to tame trined pros shortage for Microsoft's amititious gola to take world's company worth number 1 title form Apple :)

Friday, November 14, 2014

Robots will not do only jobs dangerous for them !


Then, who will ? Humans !
___________________________  
99% BAD HARDWARE WEEK: :)

Data centric Coral supercomputer to reach 150 PFlops



The DoE announced today it has chosen IBM's "data centric" architecture for Oak Ridge National Lab's new "Summit" and Lawrence Livermore National Lab's new "Sierra," both to be completed by 2017.
 Summit and Sierra will operate at 150 petaflops and 100 petaflops, respectively, compared to the world's current top supercomputer, the Tianhe-2 in China, which performs at 55 petaflops, Nvidia said in a separate news release. Summit will feature more than 3,400 nodes. The combination of very large memory per node and the powerful IBM POWER and NVIDIA processors provides an ideal platform for data analysis as well as computation.
Argonne National Labs will choose a different architecture (yet to be announced) for its pre-exascale supercomputer, reaching some 150 PFlops.
Perhaps the most interesting bit about these two computers, though, is their incredible power efficiency. Summit and Sierra are about five times more efficient than Titan, Sequoia, or Tianhe-2. 150 petaflops at 13.1 MW is about 11,000 megaflops per watt  — way, way beyond any supercomputer currently in operation. Bluegene Q have had 1700 megaflops per watt efficiency,  some 6.5 times less 6  years earlier.
To be precise. Then in 2022, IBM should be able to obtain some 55 GFlops per watt. That will be quite enough for EXAFLOPS level. Provided it will be able to calculate something else than the number of failures.                
Anyway, 150 PFlops  x 6.5 = 1020 PetaFlops under the same power consumption. Or even earlier to Exaflops goal at higher 20 MW power envelope.
___________________________  
99% BAD HARDWARE WEEK: 
Summit will have a hybrid architecture, and each node will contain multiple IBM POWER9 CPUs and NVIDIA Volta GPUs all connected together with NVIDIA’s high-speed NVLink. Each node will have over half a terabyte of coherent memory (high bandwidth memory + DDR4) addressable by all CPUs and GPUs plus 800GB of non-volatile RAM that can be used as a burst buffer or as extended memory. To provide a high rate of I/O throughput, the nodes will be connected in a non-blocking fat-tree using a dual-rail Mellanox EDR InfiniBand interconnect. 

.

Thursday, November 13, 2014

SUCESSS: EU probe has landed on comet, but doesn't know where exactly

.

___________________________
99% BAD HARDWARE WEEK: Or perhaps which one comet ? For project worth some staggering  1,7 B euros isn't it literally too little too late ? Nobody seems ever heard on old good fireworks upon Philae probe landindg ? Then everyone should see and know. :) Cheers !

LATEST UPDATE: BAD HARDWARE is  clairvoyant !
13.15
Dr Holger Sierks who has been operating the OSIRIS camera on board Rosetta has said the team has checked the crater where they thought Philae was...BUT IT ISN'T THERE!



Wednesday, November 12, 2014

US Postal Service Suspends Telecommuting Following Massive Data Breach


The United States Postal Service (USPS) has suspended telecommuting for employees while it works to remediate a network intrusion that has exposed data on some 800,000 postal workers and an additional 2.9 million customers.
The virtual private network (VPN) service for postal employees was taken down this weekend and will not be brought back up until a version with more robust security features can be installed, USPS spokesman David Partenheimer said in an emailed comment to Dark Reading.
___________________________  
99% BAD HARDWARE WEEK:

This page is powered by Blogger. Isn't yours?