Datacenter technology has been evolving to address the constantly increasing demands of applications as well as that of datacenter operators aiming for high performance, cost and power efficiency, easy manageability as well as improved reliability. In this talk, we introduce a novel hardware accelerated datacenter platform closely integrating analytics with storage and utilizing on numerous technological advances to achieve industry leading SQL query execution performance on big data. The above mentioned platform incorporates numerous performance boosting hardware and software techniques while in the same time increases the overall cost-efficiency of the system. The platform also serves as the foundation of several additional datacenter applications to be introduced that can be executed in a high-performance and cost-efficient manner.

Norbert Egi is a Staff Researcher in the IT Research Department at Huawei Technologies. His expertise lies in system architectures of compute, network as well as storage systems. He is currently focusing on accelerating big data query execution and amongst others has previously worked on cost-efficient micro-servers, data center infrastructure virtualization and software-based networking. He holds a PhD and MSc in Computer Science and has co-authored numerous patents and has published research papers in highly ranked conferences such as NSDI, SOSP, OSDI, ACM HotNets, CoNext.