2018 IEEE 36th VLSI Test Symposium (VTS) 2018
DOI: 10.1109/vts.2018.8368656
|View full text |Cite
|
Sign up to set email alerts
|

Analyzing and mitigating the impact of permanent faults on a systolic array based neural network accelerator

Abstract: Due to their growing popularity and computational cost, deep neural networks (DNNs) are being targeted for hardware acceleration. A popular architecture for DNN acceleration, adopted by the Google Tensor Processing Unit (TPU), utilizes a systolic array based matrix multiplication unit at its core. This paper deals with the design of faulttolerant, systolic array based DNN accelerators for high defect rate technologies. To this end, we empirically show that the classification accuracy of a baseline TPU drops si… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

1
94
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 136 publications
(95 citation statements)
references
References 29 publications
1
94
0
Order By: Relevance
“…(a) Hardware design optimization/enhancements for permanent fault mitigation Figure 6c shows the hardware optimization proposed in [8] for mitigating permanent faults, where an additional multiplexer is inserted in the datapath for bypassing the MAC computation in the PEs in case of faults. The baseline systolic array architecture and the design of the conventional processing element are shown in figures 6a,b, respectively.…”
Section: Salvagednns: a Methodology For Salvaging Dnn Accelerators Usmentioning
confidence: 99%
See 4 more Smart Citations
“…(a) Hardware design optimization/enhancements for permanent fault mitigation Figure 6c shows the hardware optimization proposed in [8] for mitigating permanent faults, where an additional multiplexer is inserted in the datapath for bypassing the MAC computation in the PEs in case of faults. The baseline systolic array architecture and the design of the conventional processing element are shown in figures 6a,b, respectively.…”
Section: Salvagednns: a Methodology For Salvaging Dnn Accelerators Usmentioning
confidence: 99%
“…Similarly, in Case 4 (figure 9e) the mapping is defined based on its fault map. It is important to clarify here that, similar to the state-ofthe-art FAP technique [8], our proposed technique also requires adaptation for each faulty chip based on its fault map. However, unlike the state of the art, our technique can avoid retraining, and, therefore requires much less time for the adaptation compared to the retraining-based approaches, as will be shown in §4b(v).…”
Section: (F) Salvagednn Under Changing Fault Mapsmentioning
confidence: 99%
See 3 more Smart Citations