A High-Performance Accelerator for Super-Resolution Processing on Embedded GPU
This work addresses the problem of real-time super-resolution processing for embedded systems, representing an incremental advancement in hardware acceleration.
The paper tackles the challenge of real-time super-resolution inference on embedded GPUs by implementing a full-stack acceleration framework, achieving significant performance improvements over NVIDIA TensorRT on devices like NVIDIA NX and 2080Ti.
Recent years have witnessed impressive progress in super-resolution (SR) processing. However, its real-time inference requirement sets a challenge not only for the model design but also for the on-chip implementation. In this paper, we implement a full-stack SR acceleration framework on embedded GPU devices. The special dictionary learning algorithm used in SR models was analyzed in detail and accelerated via a novel dictionary selective strategy. Besides, the hardware programming architecture together with the model structure is analyzed to guide the optimal design of computation kernels to minimize the inference latency under the resource constraints. With these novel techniques, the communication and computation bottlenecks in the deep dictionary learning-based SR models are tackled perfectly. The experiments on the edge embedded NVIDIA NX and 2080Ti show that our method outperforms the state-of-the-art NVIDIA TensorRT significantly, and can achieve real-time performance.