# 9.3 A 40nm 4.81TFLOPS/W 8b Floating-Point Training Processor for Non-Sparse Neural Networks Using Shared Exponent Bias and 24-Way Fused Multiply-Add Tree

> Research article (2021 IEEE International Solid- State Circuits Conference (ISSCC), 2021) · cited 47× · AI/ML

**Wikidata**: [openalex:W3135859967](https://www.wikidata.org/wiki/openalex:W3135859967)  
**Source**: https://4ort.xyz/entity/9-3-a-40nm-4-81tflops-w-8b-floating-point-training-processor-for-non-sparse-neural-networks-using-shared-exponent-bias-a