The high demand for fast, energy-efficient, compact computational blocks in digital electronics has led the researchers to use approximate computing in applications where inaccuracy of outputs is tolerable. The purpose of this paper is to present two ultra-high-speed current-mode approximate full adders (FA) by using carbon nanotube field-effect transistors.,Instead of using threshold detectors, which are common elements in current-mode logic, diodes are used to stabilize voltage. Zener diodes and ultra-low-power diodes are used within the first and second proposed designs, respectively. This innovation eliminates threshold detectors from critical path and makes it shorter. Then, the new adders are employed in the image processing application of Laplace filter, which detects edges in an image.,Simulation results demonstrate very high-speed operation for the first and second proposed designs, which are, respectively, 44.7 per cent and 21.6 per cent faster than the next high-speed adder cell. In addition, they make a reasonable compromise between power-delay product (PDP) and other important evaluating factors in the context of approximate computing. They have very few transistors and very low total error distance. In addition, they do not propagate error to higher bit positions by generating output carry correctly. According to the investigations, up to four inexact FA can be used in the Laplace filter computations without a significant image quality loss. The employment of the first and second proposed designs results in 42.4 per cent and 32.2 per cent PDP reduction compared to when no approximate FA are used in an 8-bit ripple adder.,Two new current-mode inexact FA are presented. They use diodes as voltage regulators to design current-mode approximate full-adders with very short critical path for the first time.

中文翻译：

---

用于拉普拉斯变换图像处理应用的高性能 CML 近似全加器

数字电子产品对快速、节能、紧凑的计算块的高需求促使研究人员在可以容忍输出不准确的应用中使用近似计算。本文的目的是通过使用碳纳米管场效应晶体管来展示两个超高速电流模式近似全加器（FA）。,而不是使用阈值检测器，这是电流模式逻辑中的常见元件，二极管用于稳定电压。齐纳二极管和超低功率二极管分别用于第一个和第二个提议的设计中。这一创新消除了关键路径中的阈值检测器并使其更短。然后，新的加法器用于拉普拉斯滤波器的图像处理应用程序，它检测图像中的边缘。仿真结果表明，第一个和第二个提议设计的运行速度非常快，分别比下一个高速加法器单元快 44.7% 和 21.6%。此外，他们在近似计算的背景下，在功率延迟积 (PDP) 和其他重要评估因素之间做出了合理的折衷。它们只有很少的晶体管和非常低的总误差距离。此外，它们不会通过正确生成输出进位将错误传播到更高位的位置。根据调查，在拉普拉斯滤波器计算中可以使用多达四个不精确的 FA，而不会造成显着的图像质量损失。与在 8 位纹波加法器中不使用近似 FA 时相比，采用第一个和第二个提议的设计导致 PDP 减少 42.4% 和 32.2%。介绍了两个新的电流模式不精确 FA。他们首次使用二极管作为电压调节器来设计具有非常短关键路径的电流模式近似全加器。