Low Power LDPC Decoding by Reliable Voltage Down-Scaling

J Valkama, M Safarpour, H Dicander… - 2023 IEEE Nordic …, 2023 - ieeexplore.ieee.org
Low-Density Parity-Check (LDPC) decoder is among the power hungry building blocks of
wireless communication systems. Voltage scaling down to Near-Threshold (NT) voltages …

Towards resilient and energy efficient scalable Krylov solvers

Z Miao, JC Calhoun, R Ge - Parallel Computing, 2025 - Elsevier
Exascale computing must simultaneously address both energy efficiency and resilience as
power limits impact scalability and faults are more common. Unfortunately, energy efficiency …

Shavette: Low Power Neural Network Acceleration via Algorithm-level Error Detection and Undervolting

M Rinkinen, L Koskinen, O Silven… - arxiv preprint arxiv …, 2024 - arxiv.org
Reduced voltage operation is an effective technique for substantial energy efficiency
improvement in digital circuits. This brief introduces a simple approach for enabling reduced …

Energy-Aware Synchronization of Hardware Tasks in Virtualized Embedded Systems

C Wulf, G Akgün, M Safarpour… - … Conference on Field …, 2024 - ieeexplore.ieee.org
Dynamic Voltage and Frequency Scaling (DVFS) is an effective means to reduce the energy
dissipation of digital designs. While on most commodity FPGAs, memory and processor …

NTHPC: Embracing Near-Threshold Operation for High Performance Multi-core Systems

S Chakraborty, M Safarpour, O Silvén - International Conference on …, 2023 - Springer
Abstract System-on-Chip (SoC) manufacturers use Core Level Redundancy (CLR) scheme
to cope with fabrication defects. By providing redundancy with extra cores and logic blocks …

[PDF][PDF] Shavette: Algorithm-Based Error Detection for Low Voltage Neural Network Acceleration

M Rinkinen, L Koskinen, O Silvén, M Safarpour - researchgate.net
This brief introduces an easy-to-integrate approach to enable significant power savings from
reduced voltage operation of Graphic Processing Units (GPUs) used for acceleration of …

Модель програмно-апаратної реалізації для обчислення спектру сигналу за допомогою швидкого перетворення Фур'є

ОЮ Васильєв - 2025 - openarchive.nure.ua
Анотація Метою роботи є розробка апаратно-програмної моделі для обчислення
спектру сигналу за допомогою ШПФ на ПЛІС з урахуванням вимог до точності …

[CITATION][C] Shavette: Simple and Robust Low Voltage Neural Network Acceleration

M Rinkinen, M Safarpour, L Koskinen, O Silvén

[CITATION][C] Shavette: Algorithm-Based Low Voltage Neural Network Acceleration

M Rinkinen, L Koskinen, O Silvén, M Safarpour