Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks

Leopold Cambier, Anahita Bhiwandiwalla, Ting Gong, Oguz H. Elibol, Mehran Nekuii, Hanlin Tang

Keywords: Low-precision training, numerics, deep learning

TL;DR: We propose a novel 8-bit format that eliminates the need for loss scaling, stochastic rounding, and other low precision techniques

Abstract:

Training with larger number of parameters while keeping fast iterations is an increasingly
adopted strategy and trend for developing better performing Deep Neural
Network (DNN) models. This necessitates increased memory footprint and
computational requirements for training. Here we introduce a novel methodology
for training deep neural networks using 8-bit floating point (FP8) numbers.
Reduced bit precision allows for a larger effective memory and increased computational
speed. We name this method Shifted and Squeezed FP8 (S2FP8). We
show that, unlike previous 8-bit precision training methods, the proposed method
works out of the box for representative models: ResNet50, Transformer and NCF.
The method can maintain model accuracy without requiring fine-tuning loss scaling
parameters or keeping certain layers in single precision. We introduce two
learnable statistics of the DNN tensors - shifted and squeezed factors that are used
to optimally adjust the range of the tensors in 8-bits, thus minimizing the loss in
information due to quantization.

Data: [ImageNet](https://paperswithcode.com/dataset/imagenet), [MovieLens](https://paperswithcode.com/dataset/movielens)