Transformers have transformed the field of natural language processing. This performance is largely attributed to the use of stacked self-attention layers, each of which consists of matrix multiplies as well as softmax operations. As a result, unlike other neural networks, the softmax operation accounts for a significant fraction of the total run-time of Transformers. To address this, we propose Softermax, a hardware-friendly softmax design. Softermax consists of base replacement, low-precision softmax computations, and an online normalization calculation.

Package-level integration using multi-chip-modules (MCMs) is a promising approach for building large-scale systems. Compared to a large monolithic die, an MCM combines many smaller chiplets into a larger system, substantially reducing fabrication and design costs. Current MCMs typically only contain a handful of coarse-grained large chiplets due to the high area, performance, and energy overheads associated with inter-chiplet communication.

Latency-insensitive design mitigates increasing interconnect delay and enables productive component reuse in complex digital systems. This design style has been adopted in high-level design flows because untimed functional blocks connected through latency-insensitive interfaces provide a natural communication abstraction. However, latency-insensitive design with high-level languages also introduces a unique set of verification challenges that jeopardize functional correctness.