Intel Announced Plans To Add Its Supercomputer 72-Core Processor To Workstations

Intel plans to equip its workstations with its superfast 72-core supercomputer chip.

Intel announced on Monday it will add the 72-core Knights Landing processor—which is the company's most powerful chip to date—to a limited number desktop workstations, with shipments beginning in the first half of next year.

Charles Wuischpard, the general manager of the HPC Platform Group at Intel, said the company hopes that including the supercomputer chip on desktops would allow more PC makers to follow suit.

However, it's important to add that Intel's new workstation will be more of an experiment as it continues to innovate the way workstations are designed. Workstations are business desktops aimed for film editors, graphic designers, programmers, engineers and pretty much any job that demands a heavy workload. Workstations are typically larger than most conventional desktops, such as Apple's Mac Pro. Most of the current workstations on the market feature Intel's Core desktop or Xeon chips.

The supercomputer Xeon Phi chip that is code-named Knights Landing differs from desktop chips used now by having all of its cores in one single piece of silicon, including 6 GB of MCDRAM memory that are stacked and connected through a wire, with a bandwidth around 500 GB per second. The memory has five times more bandwidth than DDR4 memory, and Intel claims that the stacked memory is five times more power efficient than GDDR.

The 72-core processor mixes x86 CPUs with specialized processing units to enable heavy workloads, and will deliver over 3 teraflops of performance.

The chip will be integrated into the system (which would make it hard to add more memory), load the OS, and power performance. There will be no need for co-processors.

The workstation will also include preloaded programming tools and other software programs.

Source: Intel
Via: PC World

ⓒ 2024 TECHTIMES.com All rights reserved. Do not reproduce without permission.
Join the Discussion
Real Time Analytics