2 papers
cs.AR2026
Bitwise Systolic Array Architecture for Runtime-Reconfigurable Multi-precision Quantized Multiplication on Hardware Accelerators
Yuhao Liu, Salim Ullah, Akash Kumar
Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc. Previous works have explored the quantization t…
cs.AR2025
AxOSyn: An Open-source Framework for Synthesizing Novel Approximate Arithmetic Operators
Siva Satyendra Sahoo, Salim Ullah, Akash Kumar
Edge AI deployments are becoming increasingly complex, necessitating energy-efficient solutions for resource-constrained embedded systems. Approximate computing, which allows for c…