The unprecedented growth in DNN model complexity, size, and amount of training data has
led to a commensurate increase in demand for computing and a search for minimal …

The wide adoption of DNNs has given birth to unrelenting computing requirements, forcing
datacenter operators to adopt domain-specific accelerators to train them. These accelerators …

Training deep neural networks (DNNs) with half-precision floating-point formats is widely
supported on recent hardware and frameworks. However, current training approaches using …

Block Floating Point (BFP) can efficiently support quantization for Deep Neural Network
(DNN) training by providing a wide dynamic range via a shared exponent across a group of …

When training deep neural networks (DNNs), expensive floating point arithmetic units are
used in GPUs or custom neural processing units (NPUs). To reduce the burden of floating …

Training Deep Neural Networks (DNNs) can be computationally demanding, particularly
when dealing with large models. Recent work has aimed to mitigate this computational …

Fixed-point quantization techniques have attracted considerable attention in deep neural
network (DNN) inference acceleration. Nevertheless, they often require time-consuming fine …

Training Deep Neural Networks (DNN) with high efficiency can be difficult to achieve with
native floating-point representations and commercially available hardware. Specialized …

Deep Neural Networks (DNNs) have transformed the field of artificial intelligence and
achieved extraordinary success in many areas. The training of DNNs is commonly compute …

Deep neural network (DNN) accelerators targeting training need to support the resource-
hungry floating-point (FP) arithmetic. Typically, the additions (accumulations) are performed …