As a result, CS healing in the back-end processor has become the accepted traffic jam in the CS pipeline, which prevents its application in high-speed, real-time signal processing scenarios.Challenges and Innovations in CS RecoveryTo speed up the CS recovery calculation, there have been 2 lines of efforts in the conventional digital domain, using either advanced algorithms (e.g., deep knowing), or parallel processors (e.g., GPU, FPGA, and ASIC). The computing efficiency is fundamentally restricted by the polynomial complexity of matrix operations in digital processors.To this end, analog computing has actually been concerned as an efficient technique for accelerating CS recovery, thanks to its inherent computational parallelism. By connecting this MMVM module with other analog elements to form a feedback loop, the resulting circuit maps properly the local competitive algorithm (LCA), which fixes CS healing in one step without discrete iterations.To validate the circuit, the team fabricated a resistive memory array with a basic semiconductor process, based on which the LCA circuit was built on a PCB for carrying out CS healing.
