At the beginning of April this year, the U.S. Department of Energy announced that it will make $200 million available to Argonne National Laboratory with the understanding that it will make a high-performance supercomputer designed to be up to seven times faster than any of the current top supercomputers. So it seems that now we are getting back to an era where bigger is better.
This should really come as no surprise; with the amount of data being collected around the world it is easy to see that the need to analyze, understand and know how to use it becomes a very important factor. Intel (News - Alert) appears to be going in this direction with its new line of Xeon E7 v3 server chips based on the Haswell microarchitecture. This is Intel’s fastest chipset containing up to 18 CPU cores. It is designed for databases, enterprise resource planning (ERP) systems and analytics related to machine learning, the science of getting computers to act without being explicitly programmed. It evolved from the study of pattern recognition and computational learning theory in artificial intelligence. Machine learning explores the construction and study of algorithms that can learn from and make predictions on data.
In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective Web search, and a vastly improved understanding of the human genome. Such algorithms operate by building a model from example inputs in order to make data-driven predictions or decisions, rather than following strictly static program instructions.
As you can imagine, this is a procedure that requires the necessary processing power to reach the end result. Ron Kasabian, who is the general manager of big data solutions at Intel, remarked that “To create an algorithm to look across thousands of genomes and to look for correlations is not the sort of workload that existed a few years ago.”
Cloud services and the popular distributed computing environments use a cluster of smaller servers commonly referred to as a Hadoop installation. This is an open-source software framework written in Java for distributed storage and distributed processing of very large data sets on computer clusters built from already available hardware.
SAP (News - Alert) and Intel have formed a partnership in which the software company can adopt its applications to the E7 v3 chip. The combination of improvements to the chipsets along with SAP’s software optimizations has led to performance improvements of the Xeon E7 vs. chips. The fastest chip is the E7-8890v3, which runs at 2.5GHz and has 45MB of cache, while the entry-level eight-core E7-4809v3 has a clock speed of 2.0GHz and 20MB of cache.
Dell (News - Alert), Hewlett-Packard and Lenovo are among the first companies to get on board and will soon be launching servers with the Intel Xeon E7 vs. chips.
Edited by Rory J. Thompson