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

Transformers are one of the most important machine learning workloads today.Training one is a very compute-intensive task, often taking days or weeks, andsignificant attention has been given to optimizing transformers. Despite this,existing implementations do not efficiently utilize GPUs. We find that datamovement is the key bottleneck when training. Due to Amdahl's Law and massiveimprovements in compute performance, training has now become memory-bound.Further, existing frameworks use suboptimal data layouts. Using these insights,we present a recipe for globally optimizing data movement in transformers. Wereduce data movement by up to 22.91% and overall achieve a 1.30x performanceimprovement over state-of-the-art frameworks when training a BERT encoder layerand 1.19x for the entire BERT. Our approach is applicable more broadly tooptimizing deep neural networks, and offers insight into how to tackle emergingperformance bottlenecks.

Data Movement Is All You Need: A Case Study on Optimizing Transformers