Holzle U . Brawny cores still beat wimpy cores,most of the time . IEEE Micro , 2010 , 30 ( 4 )

Hamilton J . Cooperative expendable micro-slice servers (CEMS): low cost , low power servers for Internet scale services . http://mvdirona.com/jrh/TalksAndPapers/JamesHamilton_CEMS.pdf, http://mvdirona.com/jrh/TalksAndPapers/JamesHamilton_CEMS.pdf, 2009

Chen T S , Du Z D , Sun N H , et al . Diannao: a small-footprint high-throughput accelerator for ubiquitous machine-learning . ACM Sigplan Notices , 2014 , 49 ( 4 ): 269 ～ 284

Mittal S , Vetter J S , Li D J . A survey of architectural approaches for managing embedded DRAM and non-volatile on-chip caches . IEEE Transactions on Parallel and Distributed Systems , 2014 , 26 ( 6 ): 1524 ～ 1537

Dong Y , Yin X S , Lian C , et al . Unleash the architecture power to accelerate big data processing . Journal of Computer Science and Technology , 2014

Halevy A , Norvig P , Pereira F . The unreasonable effectiveness of data . IEEE Intelligent Systems , 2009 , 24 ( 2 ): 8 ～ 12

Ho Q R , Cipar J , Cui H , et al . More effective distributed ml via a stale synchronous parallel parameter server . Advances in Neural Information Processing Systems , 2014 : 1223 ～ 1231