English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

BERT is the most recent Transformer-based model that achievesstate-of-the-art performance in various NLP tasks. In this paper, weinvestigate the hardware acceleration of BERT on FPGA for edge computing. Totackle the issue of huge computational complexity and memory footprint, wepropose to fully quantize the BERT (FQ-BERT), including weights, activations,softmax, layer normalization, and all the intermediate results. Experimentsdemonstrate that the FQ-BERT can achieve 7.94x compression for weights withnegligible performance loss. We then propose an accelerator tailored for theFQ-BERT and evaluate on Xilinx ZCU102 and ZCU111 FPGA. It can achieve aperformance-per-watt of 3.18 fps/W, which is 28.91x and 12.72x over Intel(R)Core(TM) i7-8700 CPU and NVIDIA K80 GPU, respectively.

Hardware Acceleration of Fully Quantized BERT for Efficient Natural Language Processing