Search for: All records

Award ID contains: 1253024

« Prev Next »

Total Resources

1

Resource Type
Conference Paper

1

Conference Proceeding

0

Dataset

0

Journal Article

0

Workshop Report

0

Availability
Full Text / Resource Available

1

Citation Only

0

Save Results
Excel (limit 2000)
CSV (limit 5000)
XML (limit 5000)

Have feedback or suggestions for a way to improve these results?
!

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

UPTPU: Improving Energy Efficiency of a Tensor Processing Unit through Underutilization Based Power-Gating

https://doi.org/10.1109/DAC18074.2021.9586224

Pandey, Pramesh ; Gundi, Noel Daniel ; Chakraborty, Koushik ; Roy, Sanghamitra ( December 2021 , 2021 58th ACM/IEEE Design Automation Conference (DAC))

The AI boom is bringing a plethora of domain-specific architectures for Neural Network computations. Google’s Tensor Processing Unit (TPU), a Deep Neural Network (DNN) accelerator, has replaced the CPUs/GPUs in its data centers, claiming more than 15X rate of inference. However, the unprecedented growth in DNN workloads with the widespread use of AI services projects an increasing energy consumption of TPU based data centers. In this work, we parametrize the extreme hardware underutilization in TPU systolic array and propose UPTPU: an intelligent, dataflow adaptive power-gating paradigm to provide a staggering 3.5X - 6.5X energy efficiency to TPU for different input batch sizes.
more » « less
Full Text Available