Two challenges pave the path to the future of AI and digital communications: escalating processing power to accelerate computation of fast-growing algorithms, and widening memory bandwidth to handle unprecedented amounts of data with minimal latency. Today’s systems are inflexible and cannot meet the challenges. What's needed is a system that can handle today’s memory bandwidth and tomorrow’s new algorithms without changing hardware. VSORA provides a future-proof, highly efficient solution that eliminates the need for dedicated hardware accelerators. VSORA gives you the flexibility of an FPGA with the performance of an ASIC.

In October 2020, VSORA unveiled the first PetaFlops computational platform to accelerate Level 4 (L4) and Level 5 (L5) autonomous vehicle designs. The programmable solution, delivered as an IP block called AD1028, combines digital signal processing (DSP) and machine learning (ML) acceleration for the autonomous driving industry. Its powerful multi-core DSP and AI architecture is intended to handle all the heavy AI and signal processing requirements and eliminates the need for DSP co-processors and hardware accelerators to provide a level of flexibility never achieved previously. Implemented on 7-nanometer process technology, the AD1028 logic area measures 35 mm2 and consumes less than 35 watts.