Score: 1

Energy-Efficient Hardware Acceleration of Whisper ASR on a CGLA

Published: November 4, 2025 | arXiv ID: 2511.02269v1

By: Takuto Ando , Yu Eto , Ayumu Takeuchi and more

Potential Business Impact:

Makes AI speech recognition use less power.

Business Areas:
Application Specific Integrated Circuit (ASIC) Hardware

The rise of generative AI for tasks like Automatic Speech Recognition (ASR) has created a critical energy consumption challenge. While ASICs offer high efficiency, they lack the programmability to adapt to evolving algorithms. To address this trade-off, we implement and evaluate Whisper's core computational kernel on the IMAX, a general-purpose Coarse-Grained Linear Arrays (CGLAs) accelerator. To our knowledge, this is the first work to execute a Whisper kernel on a CGRA and compare its performance against CPUs and GPUs. Using hardware/software co-design, we evaluate our system via an FPGA prototype and project performance for a 28 nm ASIC. Our results demonstrate superior energy efficiency. The projected ASIC is 1.90x more energy-efficient than the NVIDIA Jetson AGX Orin and 9.83x more than an NVIDIA RTX 4090 for the Q8_0 model. This work positions CGLA as a promising platform for sustainable ASR on power-constrained edge devices.

Page Count
7 pages

Category
Computer Science:
Hardware Architecture