在CGLA上实现Whisper ASR的节能硬件加速
Energy-Efficient Hardware Acceleration of Whisper ASR on a CGLA
AI总结：
本文在通用CGLA加速器IMAX上实现并评估了Whisper ASR核心内核，通过软硬件协同设计，预测28nm ASIC能效比NVIDIA Jetson AGX Orin高1.90倍、RTX 4090高9.83倍，为边缘设备可持续ASR提供高能效可编程平台。
摘要：
用于自动语音识别（ASR）等任务的生成式AI的兴起带来了关键的能耗挑战。虽然ASIC提供了高效率，但缺乏适应不断演进算法的可编程性。为了解决这种权衡，我们在IMAX（一种通用粗粒度线性阵列（CGLA）加速器）上实现并评估了Whisper的核心计算内核。据我们所知，这是首次在CGRA上执行Whisper内核并将其性能与CPU和GPU进行比较的工作。我们采用硬件/软件协同设计，通过FPGA原型评估系统，并预测28 nm ASIC的性能。结果表明其具有卓越的能效。预测的ASIC在Q8_0模型上比NVIDIA Jetson AGX Orin能效高1.90倍，比NVIDIA RTX 4090高9.83倍。这项工作将CGLA定位为在功率受限边缘设备上实现可持续ASR的有前景平台。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
