Nanopore genome sequencing is the key to enabling personalized medicine, global food security, and virus surveillance. The state-of-the-art base-callers adopt deep neural networks (DNNs) to translate electrical signals generated by nanopore sequencers to digital DNA symbols. A DNN-based base-caller consumes $44.5\%$ of total execution time of a nanopore sequencing pipeline. However, it is difficult to quantize a base-caller and build a power-efficient processing-in-memory (PIM) to run the quantized base-caller. In this paper, we propose a novel algorithm/architecture co-designed PIM, Helix, to power-efficiently and accurately accelerate nanopore base-calling. From algorithm perspective, we present systematic error aware training to minimize the number of systematic errors in a quantized base-caller. From architecture perspective, we propose a low-power SOT-MRAM-based ADC array to process analog-to-digital conversion operations and improve power efficiency of prior DNN PIMs. Moreover, we revised a traditional NVM-based dot-product engine to accelerate CTC decoding operations, and create a SOT-MRAM binary comparator array to process read voting. Compared to state-of-the-art PIMs, Helix improves base-calling throughput by $6\times$, throughput per Watt by $11.9\times$ and per $mm^2$ by $7.5\times$ without degrading base-calling accuracy.

中文翻译：

---

Helix：加速纳米孔基因组碱基调用的算法/架构协同设计

纳米孔基因组测序是实现个性化医疗、全球食品安全和病毒监测的关键。最先进的碱基调用器采用深度神经网络 (DNN) 将纳米孔测序仪生成的电信号转换为数字 DNA 符号。基于 DNN 的碱基调用程序消耗了纳米孔测序管道总执行时间的 44.5 美元/%。但是，很难量化碱基调用程序并构建节能的内存处理 (PIM) 来运行量化的碱基调用程序。在本文中，我们提出了一种新的算法/架构协同设计的 PIM Helix，以高效且准确地加速纳米孔碱基调用。从算法的角度来看，我们提出了系统错误感知训练，以最大限度地减少量化碱基调用者中的系统错误数量。从架构的角度来看，我们提出了一种基于低功耗 SOT-MRAM 的 ADC 阵列来处理模数转换操作并提高先前 DNN PIM 的电源效率。此外，我们修改了传统的基于 NVM 的点积引擎来加速 CTC 解码操作，并创建一个 SOT-MRAM 二进制比较器阵列来处理读取投票。与最先进的 PIM 相比，Helix 将碱基识别吞吐量提高了 6 美元，每瓦的吞吐量提高了 11.9 美元，每毫米 ^ 2 美元提高了 7.5 美元，而不会降低碱基识别的准确性。