HKUST Professor Qiming Shao Shares MRAM Technologies for Unconventional Computing
Prof. Qiming Shao, Assistant Professor, Department of Electronic & Computer Engineering, The Hong Kong University of Science and Technology (HKUST) shared his research on spin-orbit torque magnetoresistive random-access memory (SOT-MRAM) with UMEC’s research teams today.
In-memory computing is an emerging technology that provides super-fast computing performance by storing data in RAM and processing it in parallel. Today’s primary memory technologies, such as SRAM, DRAM and flash memory – all have certain drawbacks, in terms of power consumption, complexity and costs. Therefore, Prof. Shao conducts research in MRAM, which stores data in magnetic domains. It could store greater amount of data than existing electronic memory, enabling faster access and lower power consumption. The SOT-MRAM with high resistance magnetic tunnel junction (MTJ) can further enhance the energy efficiency and minimise IR drop effects.
The technologies can be used in different applications, for example, CMOS image sensors, display driver ICs, edge AI accelerator chips, etc. Much collaboration could be done between HKUST and UMEC to facilitate the adoption of MRAM in edge AI chips, which energy efficiency is of utmost important.