42 citations · 77 across the 13 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.AR2023★ 24 cited
ITA: An Energy-Efficient Attention and Softmax Accelerator for Quantized Transformers
Gamze İslamoğlu, Moritz Scherer, Gianna Paulin +4
Transformer networks have emerged as the state-of-the-art approach for natural language processing tasks and are gaining popularity in other domains such as computer vision and aud…
cs.AR2023
SALSA: Simulated Annealing based Loop-Ordering Scheduler for DNN Accelerators
Victor J. B. Jung, Arne Symons, Linyan Mei +2
To meet the growing need for computational power for DNNs, multiple specialized hardware architectures have been proposed. Each DNN layer should be mapped onto the hardware with th…