Intel has announced its latest and fastest processor chip ever, code named ‘Knights Landing,” which will reach super computers early next year.
The Xeon Phi processor, is also a springboard for new memory, I/O and storage technologies destined to reach in the short term, commercial markets such as desktops and laptops .
Furthermore, Intel’s previous generation of Xeon Phi chips, which were traditionally co-processors, are deployed in the world’s fastest supercomputers such as the supercomputer code-named Tianhe-2, which is installed in China. However, Intel say that the latest version of its chip – Knights Landing – will exceed the current version of the Xeon Phi co-processor – named Knights Corner.
Like its predecessors, Knights Landing will be a co-processor, which will perform alongside the CPU and assist in complex mathematical calculations. However, it is different in design from specialist graphics, mathematical and video co-processors. Knights Landing will deliver the same high performance as some of the graphics chips used in some of the worlds fastest super computers.
As an example of how Kights Landing’s inherent power will enhance computing power, it comes with 16GB of on-package MCDRAM memory. Such on-board capacity allows software modules to be stacked. That in built capacity will provide off-the-shelf computer systems with power in the same range of some other graphics chips used in the world’s fastest supercomputers.
Knights Landing also claims to offer five times more bandwidth than emerging DDR4 memory technology, which is based on the fact that memory is five times more power efficient and three times denser than GDDR5, which is traditionally used on other vendors graphics cards.
In addition Intel also claims to support Double-precision, which is very important for co-processors as it is vital in the fields of supercomputing due to the higher accuracy rates in floating-point calculations than single-precision calculations