DxPTA is a constraint-aware architecture search algorithm for photonic transformer accelerators that achieves up to 15.2x faster exploration than exhaustive search while meeting area, power, energy, and latency constraints for DeiT and BERT models.
Pendram: Enabling high-performance and energy-efficient pro- cessing of deep neural networks through a generalized dram data mapping policy,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DxPTA: An Architecture Design Space Exploration with Optical Dataflow-guided Strategy for HW/SW Co-Design of Photonic Transformer Accelerators
DxPTA is a constraint-aware architecture search algorithm for photonic transformer accelerators that achieves up to 15.2x faster exploration than exhaustive search while meeting area, power, energy, and latency constraints for DeiT and BERT models.