Skip to main content

GRAMARCH: A GPU-ReRAM based Heterogeneous Architecture for Neural Image Segmentation

Publication ,  Conference
Joardar, BK; Kannappan Jayakodi, N; Doppa, JR; Li, H; Pande, PP; Chakrabarty, K
Published in: Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020
March 1, 2020

Deep Neural Networks (DNNs) employed for image segmentation are computationally more expensive and complex compared to the ones used for classification. However, manycore architectures to accelerate the training of these DNNs are relatively unexplored. Resistive random-access memory (ReRAM)-based architectures offer a promising alternative to commonly used GPU-based platforms for training DNNs. However, due to their low-precision storage capability, these architectures cannot support all DNN layers and suffer from accuracy loss of the learned models. To address these challenges, we propose GRAMARCH, a heterogeneous architecture that combines the benefits of ReRAM and GPUs simultaneously by using a high-throughput 3D Network-on-Chip. Experimental results indicate that by suitably mapping DNN layers to processing elements, it is possible to achieve up to 53X better performance compared to conventional GPUs for image segmentation.

Duke Scholars

Published In

Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020

DOI

ISBN

9783981926347

Publication Date

March 1, 2020

Start / End Page

228 / 233
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Joardar, B. K., Kannappan Jayakodi, N., Doppa, J. R., Li, H., Pande, P. P., & Chakrabarty, K. (2020). GRAMARCH: A GPU-ReRAM based Heterogeneous Architecture for Neural Image Segmentation. In Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020 (pp. 228–233). https://doi.org/10.23919/DATE48585.2020.9116273
Joardar, B. K., N. Kannappan Jayakodi, J. R. Doppa, H. Li, P. P. Pande, and K. Chakrabarty. “GRAMARCH: A GPU-ReRAM based Heterogeneous Architecture for Neural Image Segmentation.” In Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020, 228–33, 2020. https://doi.org/10.23919/DATE48585.2020.9116273.
Joardar BK, Kannappan Jayakodi N, Doppa JR, Li H, Pande PP, Chakrabarty K. GRAMARCH: A GPU-ReRAM based Heterogeneous Architecture for Neural Image Segmentation. In: Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020. 2020. p. 228–33.
Joardar, B. K., et al. “GRAMARCH: A GPU-ReRAM based Heterogeneous Architecture for Neural Image Segmentation.” Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020, 2020, pp. 228–33. Scopus, doi:10.23919/DATE48585.2020.9116273.
Joardar BK, Kannappan Jayakodi N, Doppa JR, Li H, Pande PP, Chakrabarty K. GRAMARCH: A GPU-ReRAM based Heterogeneous Architecture for Neural Image Segmentation. Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020. 2020. p. 228–233.

Published In

Proceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020

DOI

ISBN

9783981926347

Publication Date

March 1, 2020

Start / End Page

228 / 233