NERO: A near high-bandwidth memory stencil accelerator for weather prediction modeling

G Singh, D Diamantopoulos… - … Conference on Field …, 2020 - ieeexplore.ieee.org
Ongoing climate change calls for fast and accurate weather and climate modeling. However,
when solving large-scale weather prediction simulations, state-of-the-art CPU and GPU …

Accelerating weather prediction using near-memory reconfigurable fabric

G Singh, D Diamantopoulos, J Gómez-Luna… - ACM Transactions on …, 2022 - dl.acm.org
Ongoing climate change calls for fast and accurate weather and climate modeling. However,
when solving large-scale weather prediction simulations, state-of-the-art CPU and GPU …

[HTML][HTML] JUNGFRAU detector for brighter x-ray sources: Solutions for IT and data science challenges in macromolecular crystallography

F Leonarski, A Mozzanica, M Brückner… - Structural …, 2020 - pubs.aip.org
In this paper, we present a data workflow developed to operate the adJUstiNg Gain detector
FoR the Aramis User station (JUNGFRAU) adaptive gain charge integrating pixel-array …

LEAPER: Fast and accurate FPGA-based system performance prediction via transfer learning

G Singha, D Diamantopoulosb… - 2022 IEEE 40th …, 2022 - ieeexplore.ieee.org
Machine learning has recently gained traction as a way to overcome the slow accelerator
generation and implementation process on an FPGA. It can be used to build performance …

NARMADA: Near-memory horizontal diffusion accelerator for scalable stencil computations

G Singh, D Diamantopoulos… - … Conference on Field …, 2019 - ieeexplore.ieee.org
Real-world weather forecasting applications consist of compound stencil kernels that do not
perform well on conventional architectures. This behavior is due to their complex data …

Low precision processing for high order stencil computations

G Singh, D Diamantopoulos, S Stuijk… - … , and Simulation: 19th …, 2019 - Springer
Modern scientific workloads have demonstrated the inefficiency of using high precision
formats. Moving to a lower bit format or even to a different number system can provide …

A system-level transprecision FPGA accelerator for BLSTM using on-chip memory resha**

D Diamantopoulos, C Hagleitner - … International Conference on …, 2018 - ieeexplore.ieee.org
The large amount of processing and storage of modern neural networks challenges
engineers to architect dedicated and tailored hardware with high energy efficiency. At the …

Designing, modeling, and optimizing data-intensive computing systems

G Singh - arxiv preprint arxiv:2208.08886, 2022 - arxiv.org
The cost of moving data between the memory units and the compute units is a major
contributor to the execution time and energy consumption of modern workloads in …

[PDF][PDF] NERO: accelerating weather prediction using near-memory reconfigurable fabric

G Singh, D Diamantopoulos, J Gómez-Luna… - arxiv preprint, 2021 - academia.edu
Ongoing climate change calls for fast and accurate weather and climate modeling. However,
when solving large-scale weather prediction simulations, state-of-the-art CPU and GPU …

[PDF][PDF] Designing, Modeling, and Optimizing Data-Intensive Computing Systems

G Singh - 2021 - research.tue.nl
The cost of moving data between the memory units and the compute units is a major
contributor to the execution time and energy consumption of modern workloads in …