Cargando…
Training of Deep Learning Pipelines on Memory-Constrained GPUs via Segmented Fused-Tiled Execution
Training models with massive inputs is a significant challenge in the development of Deep Learning pipelines to process very large digital image datasets as required by Whole Slide Imaging (WSI) in computational pathology and analysis of brain fMRI images in computational neuroscience. Graphics Proc...
Autores principales: | Xu, Yufan, Sabin, Gerald, Raje, Saurabh, Sukumaran-Rajam, Aravind, Rountev, Atanas, Sadayappan, P. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9302555/ https://www.ncbi.nlm.nih.gov/pubmed/35876769 http://dx.doi.org/10.1145/3497776.3517766 |
Ejemplares similares
-
Heterogeneous Computing with GPUs for Trigger Decision in CMS Experiment at the LHC
por: Aravind, T S
Publicado: (2022) -
Programming for GPUs
por: vom Bruch, Dorothea
Publicado: (2021) -
GPUs online
por: Concas, Matteo
Publicado: (2022) -
BOA: A partitioned view of genome assembly
por: An, Xiaojing, et al.
Publicado: (2022) -
GPUs in LHCb for Analysis
por: Schreiner, Henry Fredrick
Publicado: (2017)