Toward Efficient Logic-in-Memory Computing With Magnetic Reconfigurable Logic Circuits

Logic-in-memory (LIM) structures are promising candidates to obviate limitations of the conventional von Neumann architecture, especially in big data applications, such as image processing. In this paradigm, simple logic operations are embedded in memory to perform basic processes and consequently decrease the workload of the main processor. This letter presents an efficient hybrid fin field-effect transistor and magnetic tunnel junction (MTJ) logic structure compatible with all kinds of memory and which performs nor/or and nand/and operations. The design utilizes MTJs to obtain different voltage levels and two sense amplifiers to generate the outputs. Simulation results assert that the design improves the delay and power by 33% and 20%, respectively, compared to its state-of-the-art counterparts. Moreover, the magnetic LIM structure is appropriately utilized in image processing applications, such as minimum and maximum image filters, for preparing intermediate data. In the case study, high-level simulations indicate that the design reduces the delay and power by 31% and 21%, respectively.

Automated summary

Logic-in-memory (LIM) structures are promising solutions for overcoming limitations of the traditional von Neumann architecture in big data applications. These structures embed simple logic operations in memory to reduce the workload on the main processor. The presented hybrid fin field-effect transistor and magnetic tunnel junction (MTJ) logic structure is compatible with various types of memory and performs nor/or and nand/and operations. Simulation results show that this design improves delay and power consumption by 33% and 20%, respectively, compared to existing counterparts. Additionally, the magnetic LIM structure is effectively utilized in image processing applications, such as minimum and maximum image filters, for optimizing intermediate data. High-level simulations in a case study demonstrate a reduction in delay and power consumption of 31% and 21%, respectively.