MACRO 2020, MAESTRO - A Data-Centric Approach to Understand Reuse, Performance, and Hardware Cost of DNN Mappings
This article presented a methodology to enable fast cost-benefit estimation of a DNN accelerator on a given DNN model and mapping, which consists of a compiler-friendly data-centric representation of mappings and an analytical cost-benefit estimation framework that exploits the explicit data reuse in data space in data-centric representations.
![](/post/macro2020-maestro/featured_hubfbe6edf6f535c43e90c325fa3c4069f_188389_1200x0_resize_lanczos_2.png)