Author

Lorenzo Pazienza

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Accelerator Choice Is Not Enough: AlphaFold2 Inference on Cloud TPUs

A large hardware advantage for the TPU is found, 0.47 s per call in steady state on a single chip against 13.1 s on the T4 in the same measurement campaign, and three ways in which the software layer decides how much of it a user actually gets are shown.

Lorenzo Pazienza, Ihab El Bani · 0 citations