3 papers
cs.CR2026
Secure eFPGA-Enabled Edge LLM Inference: Architectural and Hardware Countermeasures
Voktho Das, M Zafir Sadik Khan, Jafar Vafaei +2
Edge deployment of transformer-based models increasingly relies on ASIC accelerators due to their high performance and energy efficiency, achieved through optimized dataflows, spec…
cs.AR2024
HPR-Mul: An Area and Energy-Efficient High-Precision Redundancy Multiplier by Approximate Computing
Jafar Vafaei, Omid Akbari
For critical applications that require a higher level of reliability, the Triple Modular Redundancy (TMR) scheme is usually employed to implement fault-tolerant arithmetic units. H…
cs.AR2024
A Quality-Aware Voltage Overscaling Framework to Improve the Energy Efficiency and Lifetime of TPUs based on Statistical Error Modeling
Alireza Senobari, Jafar Vafaei, Omid Akbari +2
Deep neural networks (DNNs) are a type of artificial intelligence models that are inspired by the structure and function of the human brain, designed to process and learn from larg…