Composability rather than computation sets the cost of an analog EML hardware fabric

2026-09-15

AI Summary

研究通过网络模型、电路仿真和布局设计，探讨了基于eml(x, y)运算符的模拟EML硬件架构的成本与效率问题。

Abstract

The operator eml(x, y) = exp(x) - ln(y) with the constant 1 generates the elementary functions, a continuous counterpart to NAND. Whether it yields a useful fabric had not been asked of hardware. We ask in network models, circuit simulation and SkyWater 130 nm layout. Four bipolar junctions evaluate the operator for 13 fJ, beating a width-matched digital datapath by 4-134x. The fabric assembled from them is not cheap: it loses to resource-matched baselines, and over the reals its grammar excludes trigonometry. Amplifiers holding those junctions' operating points take 74.5% of a cell's current, so a cell costs 3000 times what they spend. Extracted non-idealities cost 2.6x when a cell must hold a value and nothing when it need only be repeatable. Sharing them across cells recovers two of the three orders. The premise was that a universal primitive licenses a uniform machine. It survives in the primitive and fails in the machine.

Problem

• analog EML hardware
• composability
• elementary functions
• cost efficiency
• hardware fabric

Innovation

• analog EML
• exp(x) - ln(y)
• energy efficiency
• bipolar junctions
• hardware fabric