用近似计算与存内计算结合，提升图像与机器学习中的运算能效。
IMPLY-based Approximate Full Adders for Efficient Arithmetic Operations in Image Processing and Machine Learning
- 提出两种串行近似IMPLY全加器，融合近似计算与存内计算优势。
- 在流水线加法器中减少39%-41%步骤，能耗降低39%-42%。
- 适用于图像处理与神经网络，可在保持精度前提下节省20%计算量。
为突破现代计算的性能瓶颈（如功耗墙），新兴计算范式日益重要。近似计算通过牺牲部分精度显著提升能效与降低延迟；存内计算（IMC）则有望克服冯·诺依曼瓶颈。本文结合二者，提出两种串行近似IMPLY全加器（SAPPI）。嵌入进涟波加法器（RCA）后，相比精确算法，计算步数减少39%-41%，能耗降低39%-42%。电路级评估显示，相较于最先进近似方法，速度提升达10%，能效提高最多13%。将设计应用于三种常见图像处理任务，实现可接受图像质量且仅需原约一半的近似加法器。案例研究证明其在机器学习中的适用性：应用于基于MNIST训练的卷积神经网络（CNN），实现最高296 mJ（21%）能耗节省和13亿（20%）计算步骤减少，同时保持模型精度。
原文摘要 · Abstract (English)
To overcome the performance limitations in modern computing, such as the power wall, emerging computing paradigms are gaining increasing importance. Approximate computing offers a promising solution by substantially enhancing energy efficiency and reducing latency, albeit with a trade-off in accuracy. Another emerging method is memristor-based In-Memory Computing (IMC) which has the potential to overcome the Von Neumann bottleneck. In this work, we combine these two approaches and propose two Serial APProximate IMPLY-based full adders (SAPPI). When embedded in a Ripple Carry Adder (RCA), our designs reduce the number of steps by 39%-41% and the energy consumption by 39%-42% compared to the exact algorithm. We evaluated our approach at the circuit level and compared it with State-of-the-Art (SoA) approximations where our adders improved the speed by up to 10% and the energy efficiency by up to 13%. We applied our designs in three common image processing applications where we achieved acceptable image quality with up to half of the RCA approximated. We performed a case study to demonstrate the applicability of our approximations in Machine Learning (ML) underscoring the potential gains in more complex scenarios. The proposed approach demonstrates energy savings of up to 296 mJ (21%) and a reduction of 1.3 billion (20%) computational steps when applied to Convolutional Neural Networks (CNNs) trained on the MNIST dataset while maintaining accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。