AI RESEARCH
The AetherFloat Family: Block-Scale-Free Quad-Radix Floating-Point Architectures for AI Accelerators
arXiv CS.LG
•
ArXi:2603.08741v1 Announce Type: cross The IEEE 754 floating-point standard is the bedrock of modern computing, but its structural requirements -- a hidden leading bit, Base-2 bit-level normalization, and Sign-Magnitude encoding -- impose significant silicon area and power overhead in massively parallel Neural Processing Units (NPUs). Furthermore, the industry's recent shift to 8-bit formats (e.g., FP8 E4M3, OCP MX formats) has The AetherFloat Family is a parameterizable architectural replacement designed from first principles for Hardware/Software Co-Design in AI acceleration.