IBM To Spend $3 Billion On Semiconductor Research, Envisions Post-Silicon Future
Say it loud and clear with us: "Seven nanometers." That's pretty much a pipe dream right now, both in terms of how far removed we are from that achievement -- 7nm represents a chip technology that's three generations away -- and the technological hurdles required to get there. Nevertheless, IBM wants to make sure we get there, and help accelerate the process, the company announced plans to invest a hearty $3 billion over the next 5 years into chip R&D efforts.
IBM's investment will be split into two broad research and early stage development programs, both of which are intended to push the limits of chip technology to meet the emerging demands of cloud computing and Big Data systems. The first of those is a research program focused on 7nm and beyond silicon technology, while the second one is intended to develop alternative technologies that look beyond the use of silicon.
As we approach the physical limitations of silicon, engineers are looking at alternative solutions such as carbon nanotubes and graphene.
"The question is not if we will introduce 7 nanometer technology into manufacturing, but rather how, when, and at what cost?," said John Kelly, senior vice president, IBM Research. "IBM engineers and scientists, along with our partners, are well suited for this challenge and are already working on the materials science and device engineering required to meet the demands of the emerging system requirements for cloud, big data, and cognitive systems. This new investment will ensure that we produce the necessary innovations to meet these challenges."
Up to this point, engineers have been successful in shrinking silicon transistors (think of them as tiny switches that carry information on a chip) each year, but looming on the horizon is a point of physical limitation and diminishing returns. According to IBM, classical scaling and shrinkage will no longer yield big benefits in terms of lower power consumption, lower cost, and higher speed processors.
Click image to view the full infographic
IBM believes the solution is to look beyond complementary metal-oxide-semiconductor (CMOS) technology and into new materials and circuit architecture designs. This might include carbon nano-tubes and non-traditional computational approaches like like neuromorphic computing, cognitive computing, machine learning techniques, and quantum computing.
IBM's investment will be split into two broad research and early stage development programs, both of which are intended to push the limits of chip technology to meet the emerging demands of cloud computing and Big Data systems. The first of those is a research program focused on 7nm and beyond silicon technology, while the second one is intended to develop alternative technologies that look beyond the use of silicon.
As we approach the physical limitations of silicon, engineers are looking at alternative solutions such as carbon nanotubes and graphene.
"The question is not if we will introduce 7 nanometer technology into manufacturing, but rather how, when, and at what cost?," said John Kelly, senior vice president, IBM Research. "IBM engineers and scientists, along with our partners, are well suited for this challenge and are already working on the materials science and device engineering required to meet the demands of the emerging system requirements for cloud, big data, and cognitive systems. This new investment will ensure that we produce the necessary innovations to meet these challenges."
Up to this point, engineers have been successful in shrinking silicon transistors (think of them as tiny switches that carry information on a chip) each year, but looming on the horizon is a point of physical limitation and diminishing returns. According to IBM, classical scaling and shrinkage will no longer yield big benefits in terms of lower power consumption, lower cost, and higher speed processors.
;)
Click image to view the full infographic
IBM believes the solution is to look beyond complementary metal-oxide-semiconductor (CMOS) technology and into new materials and circuit architecture designs. This might include carbon nano-tubes and non-traditional computational approaches like like neuromorphic computing, cognitive computing, machine learning techniques, and quantum computing.
