A group of engineers at Stanford has developed an iPad-sized, highly power-efficient way of simulating a million neurons and billions of synapses for as low as US$400. The breakthrough could both help our understanding of the brain and help develop a new generation of bionic limbs that are controlled by the patient's brain in real time with little effort at all.

Stanford University

The fervent apostles Nodejs have been very loud promoting server-side JavaScript. And indeed it is light weight, and fast/responsive by avoiding thread blocking by having callbacks passed as the last argument.

However beyond demos when writing 'real' applications you quickly end up indented off the right hand margin. In a sane light there is a huge challenge in readability and maintainability of nodejs applications.

There is also an incredibly active community, including Koa is an expressive middleware for node.js using generators to make web applications and APIs more enjoyable to write and read.

An example: the app.callback method returns a handler that is compatible with Node’s http.createServer method, and uses co:

app.callback = function(){
  var mw = [respond].concat(this.middleware);
  var gen = compose(mw);
  var fn = co(gen);
  var self = this;
 
  return function(req, res){
    var ctx = self.createContext(req, res);
    onSocketError(ctx, ctx.onerror);
    fn.call(ctx, ctx.onerror);
  }
};

This example is from Koa’s source, and allows the following to work:

var koa = require('koa');
var app = koa();
app.listen(3000);
 
// Equivalent: http.createServer(app.callback()).listen(3000);

Boston Limited experts in lower powered servers unveiled the latest release of Viridis Microserver range. Powered by ARM Cortex A15 quad-core processor. Based on six EnergyCore ECX-2000 cards, the Boston Viridis 2.0 hosts two four-core SoC’s (Server-on-Chip) running at 1.8GHz and consuming as little as 6 Watts of power.

The ARM Cortex A15 quad-core processor, ECX-2000 delivers twice the performance, three times the memory bandwidth, and four times the memory capacity of the earlier ground-breaking ECX-1000.

It is highly scalable thanks to the integrated 80GB Fleet Fabric switch. The embedded Fleet Engine simultaneously provides out-of-band control and intelligence for autonomic operation and power optimization.

Cassandra has been the wildly popular key value (nosql) database due to it's performance and scalability. The announcements for Cassandra 2.0 claim offer more traditional database features as well as means to integrate with large event processing engines.

These features include:

• Lightweight transactions allow ensuring operation “linearizability” similar to the serializable isolation level offered by relational databases which prevents conflicts during concurrent requests.
• Triggers which enable pushing performance-critical code close to the data it deals with, and simplify integration with event-driven frameworks like Storm
• CQL (Cassandra Query Language) enhancements such as cursors and improved index support
• Improved compaction, keeping read performance from deteriorating under heavy write load
• Eager retries to avoid query timeouts by sending redundant requests to other replicas if too much time elapses on the original request
• Custom Thrift server implementation based on LMAX Disruptor, a high-performance inter-thread messaging library that achieves lower message processing latencies and better throughput with flexible buffer allocation strategies

Adapteva announced that the first “beta” units of the 16 core 'super computer' are being shipped to the early kicstarter 'developer' backers. Other backers are said to receive their boards by summer's end “after some final refinements.”

Also Adapteva has now opened up general pre-orders for the 16-core version on its website. While all Kickstarter-bought boards will bear a Zynq-7020 SoC, new pre-orders are configured with a 7010 as standard,

However, newcomers will receive “Gen-1” boards, which will offer slight improvements over earlier versions, such as reduced power consumption and an added serial port three-pin header.

The basic 16-core board going for $99 on the online store , with an expected October delivery date. The company tells us the 64-core version will also be available for public consumption, with pre-orders beginning in Q4 this year.

In Sun Tzu terms tech is like fighting in a marsh, where you have to keep moving or sink.

It wasn't that long that MongoDb was the disruptive technology. Now a blizzard of noSql db's are disrupting the disrupters. Google's Sergio Bossa the reasoning for moving from MongoDB to Cassandra:

• the JVM, and we have lots of in-house experience on it.
• It scales in terms of processing and storage capacity.
• Its column-based data model gives us some advanced capabilities
• Its tunable consistency levels provide greater control over high availability and consistency requirements.

As regards what made them look into a different solution:

• We need higher resiliency to faults: MongoDB provides replica sets, but we’re experiencing lots of problems with replication lags and during replica synchronization.
• For scalability: MongoDB global lock and huge memory requirements aren't already going to cope well with our growing data set.

http://metabroadcast.com/blog/looking-with-cassandra-into-the-future-of-atlas

For good measure he is not a big fan of Scala either http://thegeektalk.com/interviews/sergio-bossa/

With data volumes and pressure to reduce power all increasing, it is back to the future with NCSA380 Petabyte High Performance Storage System. The world’s largest automated near-line data repository which has multiple automated tape libraries, dozens of high-performance data movers, a large 40 Gigabit Ethernet network, hundreds of high-performance tape drives, and about a 100,000 tape cartridges.

The system is being used with the petascale Blue Waters supercomputer making it the world’s largest HPSS now in production,

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.