Today, Thursday, Intel unveiled a new way of making transistors on semiconductors, a method that the company’s chief engineer said: It could boost the performance of next-generation Intel processors by up to 20%.
The American company is one of the few remaining companies in the world that designs and manufactures its own chips. But its manufacturing operations have become a source of concern among investors after Intel said last month that its next-generation manufacturing process, called the 7 nano-scale processing node, would be delayed.
Analysts believe the delays may reinforce the lead rivals, such as Taiwan’s TSMC, have achieved in making smaller, more energy-efficient chips. Intel shares have fallen nearly 20% since the delay was announced.
Today, the company sought to reverse the notion that the odd-numbered names given to each generation of the processing node were the most important thing in performance, and announced a new method for making what it now calls SuperFin transistors, which are expected to boost the performance of upcoming Intel processors, along with new material. It is used to improve capacitors on chips.
Intel’s chief architect, Raja Kodori, said of the performance gains in an interview with Reuters: “It’s 20%, which is the largest intra-node jump ever in our history.” “It’s actually the same as what you’ll get with a whole Moore’s Law node of performance,” he added.
It will not be possible to test these claims in the real world until the new Intel chips are released, but the Tiger Lake laptop chips scheduled for release this fall will use the chips.
Even with the new transistor technology, Kodori said: Intel has restarted its chip design process to be able to use its own chip mills or external chip factories with greater ease, whichever is needed to create the best chips. He added, “Whatever makes us offer these products on time, with pioneering performance, we are flexible and we will use that.”