A new 3-D chip that combines computing and data storage can store large amounts of data and translate this into useful information, according to researchers at Stanford University and MIT.
MIT News describes the prototype chip in a blog post. The work is also published today in the journal Nature.
Traditionally, computers have separate chips for computing and data storage. Connections between the chips are limited, and as big-data driven applications increase, the slow rate at which data can be moved between chips creates a communications bottleneck.
The new 3-D chip uses nanotechnologies instead of silicon.
“The chip uses carbon nanotubes, which are sheets of 2-D graphene formed into nanocylinders, and resistive random-access memory (RRAM) cells, a type of nonvolatile memory that operates by changing the resistance of a solid dielectric material,” the blog says. “The researchers integrated over 1 million RRAM cells and 2 million carbon nanotube field-effect transistors, making the most complex nanoelectronic system ever made with emerging nanotechnologies.”
Additionally, the RRAM and carbon nanotubes are built vertically over one another, creating a 3-D chip with interleaving layers of logic and memory.
“The new 3-D computer architecture provides dense and fine-grained integration of computing and data storage, drastically overcoming the bottleneck from moving data between chips,” explained Subhasish Mitra, professor of electrical engineering and computer science at Stanford, who worked on the project. “As a result, the chip is able to store massive amounts of data and perform on-chip processing to transform a data deluge into useful information.”
This new approach may be well suited for alternative learning-based computational paradigms such as brain-inspired systems and deep neural nets, said Jan Rabaey, a professor of electrical engineering and computer science at the University of California at Berkeley, who was not involved in the research.
Max Shulaker, lead author of the report and an assistant professor of electrical engineering and computer science at MIT, is now working with Massachusetts-based semiconductor company Analog Devices. They plan to develop new versions of the system that perform both sensing and data processing on the same chip.
“The technology could not only improve traditional computing, but it also opens up a whole new range of applications that we can target,” Shulaker said. “My students are now investigating how we can produce chips that do more than just computing.”
In other efforts to build smarter, faster networks, Nokia last month debuted its FP4 silicon chipset that has a 2.4 Tb/s network processor. Nokia also built intelligent memory, instrumentation, and analytics into the chip.
“It uses very interesting chip technology and crams so much into a single chip,” said IHS Markit analyst Michael Howard, who called Nokia’s FP4 “the hottest chip around.”
Photo Credit: MIT