GPU-accelerated combinational equivalence checking via dataflow-driven parallelism and LRU-aware memory optimization

doi:10.1016/j.suscom.2026.101422

GPU-accelerated combinational equivalence checking via dataflow-driven parallelism and LRU-aware memory optimization

2026-07-25

0

PRE

AI

DOI：10.1016/j.suscom.2026.101422

Original

Original request for help

Save

Abstract

En 中文

• Reformulate EPS as a dataflow-driven computational graph for parallel GPU propagation. • Design loop-unrolled CUDA kernels with lightweight shared-memory LRU caching. • Introduce hierarchical memory coalescing and constant broadcast for data reuse.

GPU-accelerated combinational equivalence checking via dataflow-driven parallelism and LRU-aware memory optimization

Abstract

Journal

Organization