Google released a new version of the Dart2js compiler, whose generated JavaScript which they claim outperforms a “hand-written JavaScript” in the DeltaBlue benchmark. Skipping for a moment the difficulty of defining “hand written” Dart is still dragging it's heels in other benchmarks for the Richards benchmark, the other benchmark that the Dart site publishes, the Dart-generated JavaScript performance for the Richards benchmark is still 26% slower than hand-written JavaScript.

Perhaps more interestingly is to compare Dart with other languages in which it is doing pretty well

http://www.dartlang.org/performance/

Data Warehousing used to be be the place were legacy data went to die. Now Big Data means that the data warehouse has become the center of online data analysis and a key part of strategic direction.

Teradata is now blending it's Hadoop “best of breed component” approach that honors the best component developers with a well engineered package. This includes:

• A fabric-based networking backbone from Mellanox InfiniBand
• SUSE Linux Enterprise Server, NetApp and Intel's Xeon processors.
• Software to allow analysts to browse and move between Teradata and Hadoop data for business intelligence.

The Teradata Enterprise Teradata Studio with Smart Loader for Hadoop Access supports Hortonworks and Cloudera.

Teradata SQL-H, which blends Hadoop with standard SQL databases. SQL-H, which supports Hortonworks, is designed to allow analysts to query data anywhere it resides.

Our Raspberry Pi's are are quietly working away as build monitors saving power and money.
3 more options that are popping up offering a variety of other features.

→ Read more...

“Resistance is futile ..!!” The major leading memory makers, namely Micron, Samsung and Hynix are co-developing the technology development efforts backed by the Hybrid Memory Cube Consortium (HMC). The technology, called a Hybrid Memory Cube, will stack multiple volatile memory dies on top of a DRAM controller.

These 3 dimensional chips will rely on the relatively new silicon VIA (Vertical Interconnect Access) technology as their inter connect.

The first Hybrid Memory Cube specification will deliver 2GB and 4GB of capacity, providing aggregate bi-directional bandwidth of up to 160GBps compared with DDR3′s 11GBps of aggregate bandwidth and DDR4, with 18GB to 20GB of aggregate bandwidth.

HP as reported before have been hinting at super-dense Arm servers. However instead of just offering ARM HP have announced that their will offer a variety of low power processors from AMD, AppliedMicro, Calxeda (Arm), Intel, and Texas Instruments. All of which will allow the customer to mix and match their performance to energy efficiency needs.

Intel has released its own version of open source software platform Hadoop. This version naturally supports optimization at for intel based processors to boost performance (and sell more intel servers). It will also include Intel Distribution for Pentaho’s range of analytics software, bringing new data mining, analysis, interactive reporting and other capabilities to the distro.

The move is interesting in that it also demonstrates how open-source software like Hadoop helps drive the success of profit-making companies that make the commercial products and provide the technical support that enterprise needs to run it. We've seen similar announcements from Cloudera, Hortonworks, which has just put out a Windows version of HDP, and EMC’s Greenplum. With Hadoop becoming a corporate standard.

Some could see this as a new move by Intel and threaten startups like Hortonworks and Cloudera, but Davis says that this is far from the case. Instead, the company is planning to share these advancements with the Hadoop community at large, having already announced a team up with Red Hat, and so eventually everyone should be able to benefit – providing yet more evidence that Intel is getting into this game solely to find new customers for its chips.

Bina Genomic Analysis Platform, which helps pharmaceutical companies, biotech companies, researchers, and clinicians analyze large amounts of genomic sequencing data. The DNA sequence data from one person taking up half a terabyte of space, drastically increasing the number of datasets requires not only more space, but new software to compare samples to each other and draw conclusions.

The Bina Genomic Analysis Platform works with existing sequencing systems, taking the data produced by those systems and assembling it into a format that is usable for medical discovery and patient care. The product is a combination of hardware and software and pay an annual subscription fee for the software.

No it is not (what I thought) a raspberry Pi Cloud, rather PiCloud is a python orientated parallel cloud based service aimed at Scientific computing tasks.

PiCloud Python interface makes it easy to access the resources:

import cloud; cloud.call(yourfunction). 

piCloud is oriented towards making long running parallel calls typically used in scientific number crunching. They provide automatic scaling of the service to match the computational needs from no load to peak usage. You can also control the number of real cores you wish to use through the configuration options.

PiCloud had an interesting announcement, they support non-Python things in custom environments, but R is pre-built in a new Base Environment.

http://blog.picloud.com/2012/10/24/new-base-environment-ubuntu-precise/

The Vice President of Engineering at Red Hat/JBoss (Mark Little) and Alexis Richardson, senior director at VMware made a joint statement of vert.x the exciting async non-blocking java framework.

Little says that both Red Hat and VMware are “in active discussion” over how to support the project and options include the possibility of moving it to an open source software foundation. and it is seen as “an essential component to the success of the project”

In the wake of Little's statement, Apache Software Foundation President Jim Jagielski invited Fox and the vert.x community to, if they were interested, discuss moving vert.x under the foundation's structures. Fox himself, says that forking the project has not yet been ruled out. Fellow vert.x developer Stuart (Pid) Williams, said he believed that an “outcome that involves the minimum disruption, a single community and the support of both companies is preferable and achievable”.

Oracle's has release their details of Project Nashorn which will allow JavaScript to be embedded in Java applications and to develop standalone JavaScript applications.

With the ubiquity of JavaScript engine there has been a badly needed refresh and a welcome report of five times speed up on performance than the current Rhino implementation and a much smaller footprint.

Unfortunately the planned release is for Java 8 in late 2013. Hopefully it will be competitive with the planned nodejs 2.

According to Wired the NSA have a new facility of staggering proportions.

Created in Bluffdale Utah, the new facility will have 25,000-square-foot(2322 sq meters) of server space.
The water storage no doubt for cooling is cabble of pumping 1.7 million gallons of liquid per day

The facility has it's electricity sub-station to provide 65-megawatt power . with an expected energy bill of $40 million a year.

The vast facility is designed to the explosion of data that needs to be managed with current estimates in the Yottabytes (A yottabyte is a septillion bytes—so and is currently the largest term of storage with no next higher magnitude.)

The facility is fed from a number of different sources some generating “20 terabytes of intercept data a minute”. This data then needs to be managed and turned into useful information including building complex social graphs.

All of which will no doubt spawn a new generation of research, tools and capabilities.

Intel is facing much stiffer competition on the mobile and low power end from Arm and in the high end HPC from GPU vendors. As a result of purchasing the Qlogic infiniband team and Cray fabric teams, Intel have launched Xeon Phi.

The Xeon Phi consists of 64 x86 cores (256 threads), each with a 512-bit vector unit. The vector unit can dispatch 8 double precision SIMD operations. The Xeon Phi runs at 2 GHz (more or less, probably more soon) and thus delivers (2 GHz x 64 cores x 8 FLOPs) 1 TFlops.

Although NVIDIA and AMD GPUs can deliver similar FLOPs, programming the Xeon Phi should be a lot easier to use than CUDA- or OpenCL. The same development tools as the regular Xeons are available: OpenMP, Intel's Threading Building Blocks, MPI, the Math Kernel Library (MKL)