Moore’s Law To Hit A Wall In 2021 As Transistors Stop Shrinking, Study Says
It's a pretty remarkable thing that, for the most part, Moore's Law has been accurate for over 50 years, helping to set the pace for processor design for several decades. However, Moore's Law is in serious trouble of being broken if, as a group of researchers predict, transistors stop shrinking within the next five years.
The Semiconductor Industry Association (SIA) recently put the final touches on its 2015 International Technology Roadmap for Semiconductors (ITRS), a collaborative report that surveys the technological hurdles and opportunities for the semiconductor industry through 2030. In it researchers surmise that companies will no longer find that it makes good fiscal sense to continue pouring money into R&D aimed at shrinking transistors in microprocessors.
In case you're not familiar, Moore's Law is an observation made by Gordon Moore, co-founder of Intel and Fairchild Semiconductor, who wrote a paper in 1965 stating that the number of transistors in a dense integrated circuit would double every year for at least the next decade. He revised his forecast in 1975 to a doubling approximately every two years, and that's held true through the years. It's also guided companies like Intel in processor design.
"Like a metronome of the modern world, for 50 years Gordon’s prediction has set the pace for innovation and development. This foresight laid a fertile foundation from which all modern technology could spring, including the broad rise of digitization and personal electronics," Intel states on a webpage celebrating 50 years of Moore's Law.
Though it will no longer be economically viable for companies to continue shrinking transistors after 2021, it doesn't necessarily mean the end of Moore's Law. However, it does mean that chip makers will have to find other ways of boosting density. It's already started happening—for example, the memory industry has already adopted 3D architectures, such as 3D V-NAND flash memory. ITRS predicts that processor design will also move to a vertical structure after tapping out all it can from FinFET.
The Semiconductor Industry Association (SIA) recently put the final touches on its 2015 International Technology Roadmap for Semiconductors (ITRS), a collaborative report that surveys the technological hurdles and opportunities for the semiconductor industry through 2030. In it researchers surmise that companies will no longer find that it makes good fiscal sense to continue pouring money into R&D aimed at shrinking transistors in microprocessors.
In case you're not familiar, Moore's Law is an observation made by Gordon Moore, co-founder of Intel and Fairchild Semiconductor, who wrote a paper in 1965 stating that the number of transistors in a dense integrated circuit would double every year for at least the next decade. He revised his forecast in 1975 to a doubling approximately every two years, and that's held true through the years. It's also guided companies like Intel in processor design.
"Like a metronome of the modern world, for 50 years Gordon’s prediction has set the pace for innovation and development. This foresight laid a fertile foundation from which all modern technology could spring, including the broad rise of digitization and personal electronics," Intel states on a webpage celebrating 50 years of Moore's Law.
Though it will no longer be economically viable for companies to continue shrinking transistors after 2021, it doesn't necessarily mean the end of Moore's Law. However, it does mean that chip makers will have to find other ways of boosting density. It's already started happening—for example, the memory industry has already adopted 3D architectures, such as 3D V-NAND flash memory. ITRS predicts that processor design will also move to a vertical structure after tapping out all it can from FinFET.
