Memory partitioning is a widely used technique to reduce access conflicts on multi-bank memory in high-level synthesis. Previous memory partitioning methods mainly focus on a given access pattern extracted from stencil applications. Restricted by the pattern shape, these methods are prone to sub-optimal bank numbers or large overhead on address generation. In this work, we propose a pattern-morphing-based memory partitioning method, PMP, that only requires reduced hyperplane families to achieve the minimal bank number. To reduce the side effect of extra data padding, an integer linear programming problem is formulated for pattern morphing. Compared to the previous hyperplane-based memory partitioning, the experimental results show that our approach could achieve the optimal partition factor while saving 22% in LUTs, 21% in FlipFlops, 10% in DSPs, and 40% in memory overhead, on average.

Spatial accelerators enable the pervasive use of energy-efficient solutions for computation-intensive applications. In the mapping of spatial accelerators, a large kernel is usually partitioned into multiple subgraphs for resource constraints, leading to more memory accesses and access conflicts. To minimize the access conflicts, existing works either neglect the interference of multiple subgraphs or pay little attention to data's life cycle along the execution order. To this end, this paper proposes an optimized memory allocation approach for multi-subgraph mapping on spatial accelerators by constructing an optimization problem using Integer Linear Programming (ILP). The experimental results demonstrate that our work can find conflict-free solutions for most kernels and achieve 1.15× speedup, as compared to the state-of-the-art approach.