Showing cs.ARShow all
3 papers · 1 filter
cs.AR2025
PacQ: A SIMT Microarchitecture for Efficient Dataflow in Hyper-asymmetric GEMMs
Ruokai Yin, Yuhang Li, Priyadarshini Panda
Weight-only quantization has been widely explored in large language models (LLMs) to reduce memory storage and data loading overhead. During deployment on single-instruction-multip…
cs.AR2024
LoAS: Fully Temporal-Parallel Dataflow for Dual-Sparse Spiking Neural Networks
Ruokai Yin, Youngeun Kim, Di Wu +1
Spiking Neural Networks (SNNs) have gained significant research attention in the last decade due to their potential to drive resource-constrained edge devices. Though existing SNN…
cs.AR2024
PIVOT- Input-aware Path Selection for Energy-efficient ViT Inference
Abhishek Moitra, Abhiroop Bhattacharjee, Priyadarshini Panda
The attention module in vision transformers(ViTs) performs intricate spatial correlations, contributing significantly to accuracy and delay. It is thereby important to modulate the…