Rambus, a company which develops cutting-edge semiconductor and IP products, yesterday announced its expanded partnership with Microsoft Research to develop a system that improves memory performance in cryogenic temperatures. They will also be working to enhance memory capabilities, reduce energy consumption, technologies will enable high-speed SerDes links to operate efficiently in cryogenic and superconducting domains and improve overall system performance.
According to Rambus Labs, the systems they have developed along with Microsoft Research will improve energy efficiency for DRAM and logic operation at cryogenic temperatures (below ?180 °C or ?292.00 °F or 93.15 K). You may wonder why do you need memory performances in such low temperatures. The reason is cryogenic temperatures are ideal for high-performance super computers and quantum computers.
“We’re excited to continue working with Rambus and broaden our partnership to further develop technologies for memory optimization in cryogenic temperatures,” said Doug Carmean, partner architect at Microsoft Research. “Rambus’ expertise in memory systems has helped us identify new memory architectures to meet our future requirements.”
“With the increasing challenges in conventional approaches to improving memory capacity and power efficiency, our early research indicates that a significant change in the operating temperature of DRAM using cryogenic techniques may become essential in future memory systems,” Dr. Gary Bronner, vice president of Rambus Labs explained. “Our strategic partnership with Microsoft has enabled us to identify new architectural models as we strive to develop systems utilizing cryogenic memory. The expansion of this collaboration will lead to new applications in high-performance super computers (HPC) and quantum computers.”
You can learn more about cryogenic memory here. Microsoft last year announced that they are doubling down on its quantum computing research. They are making a strong bet that it is possible to create a scalable quantum computer using what is called a topological qubit.