2 papers
cs.AR2025
NX-CGRA: A Programmable Hardware Accelerator for Core Transformer Algorithms on Edge Devices
Rohit Prasad
The increasing diversity and complexity of transformer workloads at the edge present significant challenges in balancing performance, energy efficiency, and architectural flexibili…
cs.AR2025
An ultra-low-power CGRA for accelerating Transformers at the edge
Rohit Prasad
Transformers have revolutionized deep learning with applications in natural language processing, computer vision, and beyond. However, their computational demands make it challengi…