[muffles]

Interesting no mention or discussion of FPGAs for DL Neural networks.

"Our enhanced NPU on Stratix 10 NX delivers 24× and 12× higher core compute performance on average compared to the T4 and V100 GPUs at batch-6, despite the smaller NX die size."

"Results show that the Stratix 10 NX NPU running batch 6 inference achieves 12-16× and 8-12× higher average energy efficiency (i.e. TOPS/Watt) on the studied workloads compared to the T4 and V100 GPUs, respectively."

https://users.ece.cmu.edu/~jhoe/distribution/2020/fpt2020.pd...

[buildbot]

FPGAs are awesome, but are even less usable than AMD GPUs for ML by comparison - you may have to write a kernel to get a new net to work, and that really limits adoption. Software is the #1 thing that will enable you to get research done.

Disclaimer - I work on the team that was originally behind Brainwave at Microsoft.

[shaklee3]

V100 is 2 major generations old.