A 28nm 4.96 TOPS/W End-to-End Diffusion Accelerator with Reconfigurable Hyper-Precision and Unified Non-Matrix Processing Engine
Authors:
- 9 September 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 253-256
Abstract
This paper presents Picasso, an end-to-end diffusion accelerator. Picasso proposes a novel hyper-precision data type and reconfigurable architecture that can maximize hardware efficiency with extended dynamic range, with no compromise in accuracy. Picasso also proposes a unified engine operating all non-matrix operations in a streamlined processing flow and minimizes the end-to-end latency by sub-block pipeline scheduling. The accelerator is fabricated in 28 nm CMOS technology and achieves an energy efficiency of 4.96 TOPS/W and a peak performance of 9.83 TOPS. Compared with prior works, Picasso achieves speedups of $8.4 \times-26.8 \times$ while improving energy and area efficiency by $1.1 \times-2.8 \times$ and $3.6 \times-30.5 \times$, respectively.
Keywords
This publication has 5 references indexed in Scilit:
- 22.9 A 12nm 18.1TFLOPs/W Sparse Transformer Processor with Entropy-Based Early Exit, Mixed-Precision Predication and Fine-Grained Power Management2023
- 16.2 A 28nm 53.8TOPS/W 8b Sparse Transformer Accelerator with In-Memory Butterfly Zero Skipper for Unstructured-Pruned NN and CIM-Based Local-Attention-Reusable Engine2023
- A 16-nm SoC for Noise-Robust Speech and NLP Edge AI Inference With Bayesian Sound Source Separation and Attention-Based DNNsIEEE Journal of Solid-State Circuits, 2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- A 28nm 27.5TOPS/W Approximate-Computing-Based Transformer Processor with Asymptotic Sparsity Speculating and Out-of-Order Computing2022