Optimizing the Whole-life Cost in End-to-end CNN Acceleration
This addresses the challenge of high whole-life costs in CNN acceleration for developers and users, offering a more general and efficient solution.
The paper tackles the problem of accelerating CNNs efficiently across diverse layers by proposing GCONV Chain, which converts entire CNN computations into a chain of standard convolutions, resulting in average performance and energy efficiency improvements of 3.4x and 3.2x respectively on existing accelerators.
The acceleration of CNNs has gained increasing atten-tion since their success in computer vision. With the heterogeneous functional layers that cannot be pro-cessed by the accelerators proposed for convolution layers only, modern end-to-end CNN acceleration so-lutions either transform the diverse computation into matrix/vector arithmetic, which loses data reuse op-portunities in convolution, or introduce dedicated functional unit to each kind of layer, which results in underutilization and high update expense. To enhance the whole-life cost efficiency, we need an acceleration solution that is efficient in processing CNN layers and has the generality to apply to all kinds of existing and emerging layers. To this end, we pro-pose GCONV Chain, a method to convert the entire CNN computation into a chain of standard general convolutions (GCONV) that can be efficiently pro-cessed by the existing CNN accelerators. This paper comprehensively analyzes the GCONV Chain model and proposes a full-stack implementation to support GCONV Chain. On one hand, the results on seven var-ious CNNs demonstrate that GCONV Chain improves the performance and energy efficiency of existing CNN accelerators by an average of 3.4x and 3.2x re-spectively. On the other hand, we show that GCONV Chain provides low whole-life costs for CNN accelera-tion, including both developer efforts and total cost of ownership for the users.