Publications

From GPUs to RRAMs: Distributed In-Memory Primal-Dual Hybrid Gradient Method for Solving Large-Scale Linear Optimization Problems

Published in 2026 SIAM Conference on Parallel Processing for Scientific Computing (PP26), 2026

We present a distributed primal-dual hybrid gradient (PDHG) method co-designed for resistive random-access memory (RRAM) in-memory computing, enabling large-scale linear optimization with dramatically reduced energy and latency compared to GPU baselines.

Recommended citation: Huynh Q. N. Vo, Md Tawsif Rahman Chowdhury, Paritosh Ramanan, Gozde Tutuncuoglu, Junchi Yang, Feng Qiu, and Murat Yildirim. (2026). From GPUs to RRAMs: Distributed In-Memory Primal-Dual Hybrid Gradient Method for Solving Large-Scale Linear Optimization Problems. In: Proceedings of the 2026 SIAM Conference on Parallel Processing for Scientific Computing (PP26).

Harnessing the Full Potential of RRAMs through Scalable and Distributed In-Memory Computing with Integrated Error Correction

Published in arXiv preprint, 2025

We introduce MELISO+: a distributed, full-stack RRAM in-memory computing framework with integrated two-tier error correction for scalable, high-dimensional matrix computations.

Recommended citation: Huynh Q. N. Vo, Md Tawsif Rahman Chowdhury, Paritosh Ramanan, Murat Yildirim, and Gozde Tutuncuoglu. (2025). Harnessing the Full Potential of RRAMs through Scalable and Distributed In-Memory Computing with Integrated Error Correction. arXiv preprint arXiv:2508.13298.

SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problems

Published in 2024 IEEE International Conference on Big Data (BigData), 2024

We present SplitVAE, a decentralized scenario generation framework that leverages variational autoencoders to generate high-quality scenarios without moving stakeholder data.

Recommended citation: H. M. M. Islam, H. Q. N. Vo and P. Ramanan, "SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problems", in 2024 IEEE International Conference on Big Data (BigData), Washington, DC, USA, 2024, pp. 938-948.

The Lynchpin of In-Memory Computing: A Benchmarking Framework for Vector-Matrix Multiplication in RRAMs

Published in 2024 International Conference on Neuromorphic Systems (ICONS'24), 2024

We introduce MELISO (In-Memory Linear Solver), a comprehensive end-to-end VMM benchmarking framework tailored for RRAM-based systems. MELISO evaluates the error propagation in VMM operations, analyzing the impact of RRAM device metrics on error magnitude and distribution.

Recommended citation: M. T. Rahman Chowdhury, H. Q. Nguyen Vo, P. Ramanan, M. Yildirim and G. Tutuncuoglu, "The Lynchpin of In-Memory Computing: A Benchmarking Framework for Vector-Matrix Multiplication in RRAMs," 2024 International Conference on Neuromorphic Systems (ICONS), Arlington, VA, USA, 2024, pp. 336-342.

Measurement setup for differential spectral responsivity of solar cells

Published in Optical Review, 2020

We present a setup for measuring differential spectral responsivities of unifacial and bifacial solar cells under bias light conditions.

Recommended citation: Kärhä, P., Baumgartner, H., Askola, J. et al. Measurement setup for differential spectral responsivity of solar cells. Opt Rev 27, 195–204 (2020).