“AI chips commonly employ SRAM memory as buffers for their reliability and speed, which contribute to high performance. However, SRAM is expensive and demands significant area and energy consumption.

“This memory can store light and operate at speeds beyond the reach of its electrical counterpart memory,” said Jaiswal.

Chinese researchers have developed super-fast non volatile flash memory Graphene channel enables 400 picosecond write speed and persistent storage "PoX" device targets AI bottlenecks with low power, ...

Memory has become an increasingly vital ingredient of the ultra-low-power Internet of Things (IoT) chip designs, and that’s apparent from Nordic Semiconductor’s acquisition of low-voltage embedded ...

This work describing a low power write scheme which reduces SRAM power by using seven – transistor sense-amplifying memory cell. By reducing the bit line swing and amplifying the voltage swing by a ...

The very first all-electronic memory was the Williams-Kilburn tube, developed in 1947 at Manchester University. It used a cathode ray tube to store bits as dots on the screen’s surface. The evolution ...

IBM Research has been working on new non-volatile magnetic memory for over two decades. Non-volatile memory is wonderful for retaining data without power, but it is extremely slow, and does not last ...