CogSys: Efficient and Scalable Neurosymbolic Cognition System via Algorithm-Hardware Co-Design

Abstract

Neurosymbolic AI is an emerging compositional paradigm that fuse neural learning with symbolic reasoning to enhance the transparency, interpretability, and trustworthiness of AI. It also exhibits higher data efficiency making it promising for edge deployments. Despite the algorithmic promises and demon- strations, unfortunately executing neurosymbolic workloads on current hardware (CPU/GPU/TPU) is challenging due to higher memory intensity, greater compute heterogeneity and access pattern irregularity, leading to severe hardware underutilization. This work proposes CogSys, a characterization and co-design framework dedicated to neurosymbolic AI system acceleration, aiming to win both reasoning efficiency and cognition scalability. On the algorithm side, CogSys proposes an efficient factorization technique to alleviate compute and memory overhead On the hardware side, CogSys proposes a scalable neurosymbolic archi- tecture with reconfigurable neuro/symbolic processing elements (nsPE) and bubble streaming (BS) dataflow with spatial-temporal (ST) mapping for highly parallel and efficient neurosymbolic computation. On the system side, CogSys features an adaptive workload-aware scheduler (adSCH) to orchestrate heterogeneous kernels and enhance resource utilization. Evaluated across cogni- tive workloads, CogSys enables reconfigurable support for neural and symbolic kernels and exhibits >75× speedup over TPU-like systolic array with only <5% area overhead. CogSys achieves 4×-96× speedup compared to desktop and edge GPUs. For the first time, CogSys enables real-time abduction reasoning towards human fluid intelligence, requiring only 0.3 s per reasoning task with 4 mm2 area and 1.48 W power consumption