A research team from the University of Minnesota Twin Cities has developed a new AI technology called CRAM, which significantly reduces energy consumption by eliminating the need for data to travel between memory and processing units. This innovative approach could revolutionize the energy efficiency of AI workloads, addressing the growing concerns about the energy demands of powerful AI systems.
Researchers at the University of Minnesota Twin Cities have developed a new computer memory design called CRAM, which could drastically reduce the energy consumption of AI systems. This innovative design integrates a reconfigurable spintronic compute substrate directly into the memory cell, eliminating the need for data transfer between memory and processors. Tests have shown that CRAM can reduce energy consumption by up to 1,000 times compared to traditional systems.
