查看文章

Hand-sized DNA sequencers have demonstrated excellent scientific utility. They also present exciting opportunities for the expansion of DNA analysis to a diverse range of uses and users. But this potential is currently blunted by mini-sequencers’ lack of on-board computing. In this paper we explore the potential of embedded processors to address this gap. We outline the general hardware and software organization of existing systems and identify a deep learning bioinformatics task as an exemplary workload for processors embedded in miniature sequencers. We then describe a candidate multicore RISC-V arrangement and experimentally study the relative performance, power, and cost trade-offs for alternate configurations of this arrangement. The experiments show no saturation in performance scaling up to at least 6 cores with maximum throughput and efficiency achieved with 512KB and 128KB L2 cache sizes …