The Convergence of HPC, AI and Big Data in Rapid-Response to the COVID-19 Pandemic

Sukumar, Sreenivas R.; Balma, Jacob; Rickett, Christopher D.; Maschhoff, Kristyn J.; Landman, Yosef; Yates, Charles R.; Chittiboyina, Amar G.; Peterson, Yuri K.; Vose, Aaron; Byler, Kendall G.; Baudry, Jérôme; Khan, Ikhlas A.

doi:10.1007/978-3-030-96498-6_9

Cited by 3 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modern supercomputers are an essential tool for today's scientists and engineers, enabling them to simulate larger and more complex systems than ever before. The availability of largescale computing resources has enabled numerous breakthroughs in scientific knowledge in areas such as quantum computing (Doi et al 2019, Liu et al 2021c, Mandrà et al 2021, computational chemistry (De Jong et al 2010, Kowalski et al 2021, drug discovery (Ge et al 2013, Schmidt and Hildebrandt 2017, Bharadwaj et al 2021, Sukumar et al 2021, biology (McFarlane andBiktasheva 2008, Bukowski et al 2010), and plasma physics (Bhattacharjee andWells 2021, Fedeli et al 2022). While the increased number of floating-point operations per second has enabled larger and more challenging problems to be solved in reasonable amounts of time, applications are increasingly becoming bottlenecked by limited memory of computing systems-especially those applications dealing with big data (Imani et al 2019, Denis et al 2022.…”

Section: Introductionmentioning

confidence: 99%

An autoencoder compression approach for accelerating large-scale inverse problems

Wittmer,

Badger,

Sundar

et al. 2023

Inverse Problems

View full text Add to dashboard Cite

PDE-constrained inverse problems are some of the most challenging and computationally demanding problems in computational science today. Fine meshes that are required to accurately compute the PDE solution introduce an enormous number of parameters and require large scale computing resources such as more processors and more memory to solve such systems in a reasonable time. For inverse problems constrained by time dependent PDEs, the adjoint method that is often employed to efﬁciently compute gradients and higher order derivatives requires solving a time-reversed, so-called adjoint PDE that depends on the forward PDE solution at each timestep. This necessitates the storage of a high dimensional forward solution vector at every timestep. Such a procedure quickly exhausts the available memory resources. Several approaches that trade additional computation for reduced memory footprint have been proposed to mitigate the memory bottleneck, including checkpointing and compression strategies. In this work, we propose a close-to-ideal scalable compression approach using autoencoders to eliminate the need for checkpointing and substantial memory storage, thereby reducing both the time-to-solution and memory requirements. We compare our approach with checkpointing and an off-the-shelf compression approach on an earth-scale ill-posed seismic inverse problem. The results verify the expected close-to-ideal speedup for both the gradient and Hessianvector product using the proposed autoencoder compression approach. To highlight the usefulness of the proposed approach, we combine the autoencoder compression with the data-informed active subspace (DIAS) prior to show how the DIAS method can be affordably extended to large scale problems without the need of checkpointing and large memory.

show abstract