202 citations · 257 across the 12 of their papers we have counts for
13 papers
Lossy Checkpoint Compression in Full Waveform Inversion: a case study with ZFPv0.5.5 and the Overthrust Model
Navjot Kukreja, Jan Hueckelheim, Mathias Louboutin +3
This paper proposes a new method that combines check-pointing methods with error-controlled lossy compression for large-scale high-performance Full-Waveform Inversion (FWI), an inv…
Automatic Differentiation for Adjoint Stencil Loops
Jan Hückelheim, Navjot Kukreja, Sri Hari Krishna Narayanan +3
Stencil loops are a common motif in computations including convolutional neural networks, structured-mesh solvers for partial differential equations, and image processing. Stencil…
Towards automatically building starting models for full-waveform inversion using global optimization methods: A PSO approach via DEAP + Devito
Oscar F. Mojica, Navjot Kukreja
In this work, we illustrate an example of estimating the macro-model of velocities in the subsurface through the use of global optimization methods (GOMs). The optimization problem…
Training on the Edge: The why and the how
Navjot Kukreja, Alena Shilova, Olivier Beaumont +4
Edge computing is the natural progression from Cloud computing, where, instead of collecting all data and processing it centrally, like in a cloud computing environment, we distrib…
Combining Checkpointing and Data Compression to Accelerate Adjoint-Based Optimization Problems
Navjot Kukreja, Jan Hueckelheim, Mathias Louboutin +3
Seismic inversion and imaging are adjoint-based optimization problems that process up to terabytes of data, regularly exceeding the memory capacity of available computers. Data com…
Devito (v3.1.0): an embedded domain-specific language for finite differences and geophysical exploration
Mathias Louboutin, Michael Lange, Fabio Luporini +5
We introduce Devito, a new domain-specific language for implementing high-performance finite difference partial differential equation solvers. The motivating application is explora…
Architecture and performance of Devito, a system for automated stencil computation
Fabio Luporini, Michael Lange, Mathias Louboutin +7
Stencil computations are a key part of many high-performance computing applications, such as image processing, convolutional neural networks, and finite-difference solvers for part…
Backpropagation for long sequences: beyond memory constraints with constant overheads
Navjot Kukreja, Jan Hückelheim, Gerard J. Gorman
Naive backpropagation through time has a memory footprint that grows linearly in the sequence length, due to the need to store each state of the forward propagation. This is a prob…
High-level python abstractions for optimal checkpointing in inversion problems
Navjot Kukreja, Jan Hückelheim, Michael Lange +4
Inversion and PDE-constrained optimization problems often rely on solving the adjoint problem to calculate the gradient of the objec- tive function. This requires storing large amo…
Optimised finite difference computation from symbolic equations
Michael Lange, Navjot Kukreja, Fabio Luporini +4
Domain-specific high-productivity environments are playing an increasingly important role in scientific computing due to the levels of abstraction and automation they provide. In t…
Devito: Towards a generic Finite Difference DSL using Symbolic Python
Michael Lange, Navjot Kukreja, Mathias Louboutin +6
Domain specific languages (DSL) have been used in a variety of fields to express complex scientific problems in a concise manner and provide automated performance optimization for…
Devito: automated fast finite difference computation
Navjot Kukreja, Mathias Louboutin, Felippe Vieira +3
Domain specific languages have successfully been used in a variety of fields to cleanly express scientific problems as well as to simplify implementation and performance opti- miza…
Performance prediction of finite-difference solvers for different computer architectures
Mathias Louboutin, Michael Lange, Felix Herrmann +2
The life-cycle of a partial differential equation (PDE) solver is often characterized by three development phases: the development of a stable numerical discretization, development…