Shrinking transistors, which powered the advancement of computing in the past half century, has stalled due to power wall; now extreme heterogeneity is promised to be the next driving force to feed the needs of ever-increasingly diverse scientific domains. To unlock the potentials of such supercomputers, we identify eight potential challenges in three categories: First, one needs fast data movement since extreme heterogeneity will inevitably complicate the communication circuits -- thus hampering the data movement. Second, we need to intelligently schedule suitable hardware for corresponding applications/stages. Third, we have to lower the programming complexity in order to encourage the adoption of heterogeneous computing.
@article{arxiv.1804.09738,
title = {Challenges Towards Deploying Data Intensive Scientific Applications on Extreme Heterogeneity Supercomputers},
author = {Hang Liu and Yufei Ding and Da Zheng and Seung Woo Son and Da Yan},
journal= {arXiv preprint arXiv:1804.09738},
year = {2018}
}