Pith. sign in

REVIEW 2 cited by

Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.00768 v1 pith:PUSZ6ZQK submitted 2021-03-01 cs.AR cs.LG

classification cs.ARcs.LG
keywords edgemodelsgooglemensaacceleratoracceleratorsacrosscharacteristics
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

As the need for edge computing grows, many modern consumer devices now contain edge machine learning (ML) accelerators that can compute a wide range of neural network (NN) models while still fitting within tight resource constraints. We analyze a commercial Edge TPU using 24 Google edge NN models (including CNNs, LSTMs, transducers, and RCNNs), and find that the accelerator suffers from three shortcomings, in terms of computational throughput, energy efficiency, and memory access handling. We comprehensively study the characteristics of each NN layer in all of the Google edge models, and find that these shortcomings arise from the one-size-fits-all approach of the accelerator, as there is a high amount of heterogeneity in key layer characteristics both across different models and across different layers in the same model. We propose a new acceleration framework called Mensa. Mensa incorporates multiple heterogeneous ML edge accelerators (including both on-chip and near-data accelerators), each of which caters to the characteristics of a particular subset of models. At runtime, Mensa schedules each layer to run on the best-suited accelerator, accounting for both efficiency and inter-layer dependencies. As we analyze the Google edge NN models, we discover that all of the layers naturally group into a small number of clusters, which allows us to design an efficient implementation of Mensa for these models with only three specialized accelerators. Averaged across all 24 Google edge models, Mensa improves energy efficiency and throughput by 3.0x and 3.1x over the Edge TPU, and by 2.4x and 4.3x over Eyeriss v2, a state-of-the-art accelerator.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Addressing memory bandwidth scalability in vector processors for streaming applications

    cs.AR 2025-05 conditional novelty 6.0 of 10

    A proposed vector-processor memory hierarchy with an ultra-wide register and data shufflers improves compute-to-memory ratio and processing-element utilization for low-reuse CNNs like MobileNet.

  2. New Tools, Programming Models, and System Support for Processing-in-Memory Architectures

    cs.AR 2025-08 conditional novelty 4.0 of 10

    A PhD dissertation contributing DAMOV (data-movement benchmark suite), MIMDRAM and Proteus (processing-using-DRAM designs), and DaPPA (near-memory programming framework), claiming large performance and energy gains fo...

Pith tools