Big Data and Dark Silicon: Taming Two IT Inflection Points on a Collision Course
發布時間:2017-05-11 09:18:13

時間:2014814日(周四),上午 10:00-11:30

地點:計算所446會議室

摘要: 

Information technology is now an indispensable pillar of a modern-day society, thanks to the proliferation of digital platforms in the past several decades. We are now witnessing two inflection points, however, that are about to change IT as we know it. First, we are entering the Big Data era where demand on robust and economical data processing, communication and storage is growing faster than technology can sustain. Second, while forecasts indicate that chip density scaling will continue for another decade, the diminishing returns in supply voltage scaling and the impending "energy wall", is leading server designers towards energy-centric solutions and eventually Dark Silicon. In this talk, I will motivate these two IT trends and present promising research avenues for server chip design including specialized scale-out processors, on-chip networks and die-stacked DRAM cache hierarchies.

個人簡介: 是瑞士EPFL計算機系的教授,也是面向未來高能效與綠色云技術的EcoCloud研究中心的創始人與主任。Falsafi教授在計算機系統設計與評估方面做出了許多貢獻,包括已經被Sun(現Oracle)采用的一種可擴展多處理體系結構、應用于IBM BlueGene/PBlueGene/QCache偵聽過濾器以及流預取部件、已被AMD/HP研究與產品部門使用的系統模擬采樣技術等。Falsafi教授最值得一提的工作是“發現現代系統中流行的多處理器內存編程模型——即內存一致性模型,對于提高計算性能既不必要也不充分”,這顛覆了傳統的觀點。最近幾年Falsafi教授關注云計算技術,并因為云計算基準測試集CloudSuite相關工作獲2012ASPLOS最佳論文獎。Falsafi教授獲得了很多獎,包括NSF CAREER AwardIBM Faculty Partnership AwardAlfred P. Sloan Research Fellowship,同時也是IEEE Fellow

Babak Falsafi