Fracturable DSP block for multi-context reconfigurable architectures

Multi-context architectures like NATURE enable low-power applications to leverage fast context switching for improved energy efficiency and lower area footprint. The NATURE architecture incorporates 16-bit reconfigurable DSP blocks for accelerating arithmetic computations, however, their fixed precision prevents efficient re-use in mixed-width arithmetic circuits. This paper presents an improved DSP block architecture for NATURE, with native support for temporal folding and run-time fracturability. The proposed DSP block can compute multiple sub-width operations in the same clock cycle and can dynamically switch between sub-width and full-width operations in different cycles. The NanoMap tool for mapping circuits onto NATURE is extended to exploit the fracturable multiplier unit incorporated in the DSP block. We demonstrate the efficiency of the proposed dynamically fracturable DSP block by implementing logic-intensive and compute-intensive benchmark applications. Our results illustrate that the fracturable DSP block can achieve a 53.7% reduction in DSP block utilization and a 42.5% reduction in area with a 122.5% reduction in power-delay product without exploiting logic folding. We also observe an average reduction of 6.43% in power-delay product for circuits that utilize NATURE’s temporal folding compared to the existing full precision DSP block in NATURE, leading to highly compact, energy efficient designs