IBM has announced that from now on it will put its energies in the open source code project, Apache Spark, and defines is at the most important project of its kind in the next decade. The uniqueness of the Apache Spark is in that it is a very fast processing engine for Big Data applications on top of cluster-like systems in large computerization arrays. The system offers fast, easy, highly durable and applicable work in Agile format. This open source code, like the one being used in the project, gives the system constant improvement through the users’ community. The concept is to eventually corporate the Apache Spark into the IBM analytical analyses platforms and e-trade, and to offer it as service around its development cloud. For the development of this code, IBM will allocate 3500 of its employees around the world and will establish a center for this sort of technology in San Francisco, U.S. The company will also develop a training alignment to integrate the system in at least a million professional personnel.
Some of the Israeli company employees are also taking part n the development project, says Dalit Naor, manager of the department for cloud computerization platforms in the IBM research lab in Haifa. She states that Israeli researchers have been able to combine the Spark with Softlayer’s objective storing capability, which allows the system to manage advanced analytics with stored information in the OpenStack swift system. The system’s ability to analyze at such high level massive amounts of resources gives the Spark an advantage in an environment that requires just such processing such as social networks and Internet of Things, as it can simplify data and make it accessible to any client.
Fuente e imagen: i-hls.com