User Tools

Site Tools


start

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
start [2018/05/12 14:09]
root ↷ Links adapted because of a move operation
start [2018/07/25 14:01] (current)
realstolz [Research Statement]
Line 3: Line 3:
 The institute of parallel and distributed systems (IPADS) conducts research in all aspects of computer systems, with a primary focus on operating systems, system virtualization,​ runtime for multicore, in-memory systems, isolated execution environments and distributed systems. Our research also involves other disciplines such as computer architecture,​ languages and compilers. The research themes of IPADS are improving the performance scalability,​ productivity,​ availability,​ and reliability of centralized and distributed computer systems. The institute of parallel and distributed systems (IPADS) conducts research in all aspects of computer systems, with a primary focus on operating systems, system virtualization,​ runtime for multicore, in-memory systems, isolated execution environments and distributed systems. Our research also involves other disciplines such as computer architecture,​ languages and compilers. The research themes of IPADS are improving the performance scalability,​ productivity,​ availability,​ and reliability of centralized and distributed computer systems.
  
-We have built a number of systems to address the scalability and dependability issues of computer systems. Examples include a trusted cloud platform that addresses the trustworthiness of multi-tenant cloud (CloudVisor),​ a reader-writer lock that provides scalable read-side performance and small writer latency ([[pub:​projects:​Prwlock]]),​ a portable parallel full-system emulator for several hundreds of cores ([[pub:​projects:​COREMU]]), ​ fast graph query and processing frameworks ([[pub:​projects:​wukong]] and [[http://​ipads.se.sjtu.edu.cn/​projects/​powerlyra.html|PowerLyra]]),​ an in-memory transaction processing framework supported by hardware features such as HTM, RDMA and NVM ([[pub:​projects:​DrTM]]),​ and a dependable and hardened hypervisor with small TCB (Nexen).+We have built a number of systems to address the scalability and dependability issues of computer systems. Examples include a trusted cloud platform that addresses the trustworthiness of multi-tenant cloud (CloudVisor),​ a reader-writer lock that provides scalable read-side performance and small writer latency ([[pub:​projects:​Prwlock]]),​ a portable parallel full-system emulator for several hundreds of cores ([[pub:​projects:​COREMU]]), ​ fast graph query and processing frameworks ([[pub:​projects:​wukong|Wukong]] and [[http://​ipads.se.sjtu.edu.cn/​projects/​powerlyra.html|PowerLyra]]),​ an in-memory transaction processing framework supported by hardware features such as HTM, RDMA and NVM ([[pub:​projects:​DrTM]]),​ and a dependable and hardened hypervisor with small TCB (Nexen).
  
 Our current research focus is in providing system support for large-scale computing systems, scaling existing software stack to future computing platforms with ultra-low latency, high-bandwidth networking and non-volatile memory, and providing hardware and software solutions to dependable computing environments in both mobile and cloud platforms. Our current research focus is in providing system support for large-scale computing systems, scaling existing software stack to future computing platforms with ultra-low latency, high-bandwidth networking and non-volatile memory, and providing hardware and software solutions to dependable computing environments in both mobile and cloud platforms.
Line 14: Line 14:
  
 ====== Recent News ====== ====== Recent News ======
 +  * [Publication] July, 2018, our paper "​Deconstructing RDMA-enabled Transaction Processing: Hybrid is Better!"​ was accepted by 2018 Usenix Symposium on Operating System Design and Implementation (**OSDI 2018**). Congratulations to Xingda and Zhiyuan. ​
 +  * [Impact] May, 2018, Haibo was selected to give **a keynote speech at 2018 China National Computer Congress (CNCC)**, the largest conference in computer science that gathers over 5,000 attendees. ​
 +  * [Award] May, 2018, Haibo was awarded the **Green Bamboo Award** (Qingzhu in Pinying) from China Computer Federation, for his excellent academic contribution and high industry impact. ​
   * [Publication] April, 2018, our papers "EPTI: Efficient Defense against Meltdown Attack for Unpatched VMs" and "Fast and Concurrent RDF Queries using RDMA-assisted GPU Graph Exploration"​ were accepted by 2018 USENIX Annual Technical Conference (**USENIX ATC 2018**). Congratulations to Zhichao, Dong, Siyuan and Chang.   * [Publication] April, 2018, our papers "EPTI: Efficient Defense against Meltdown Attack for Unpatched VMs" and "Fast and Concurrent RDF Queries using RDMA-assisted GPU Graph Exploration"​ were accepted by 2018 USENIX Annual Technical Conference (**USENIX ATC 2018**). Congratulations to Zhichao, Dong, Siyuan and Chang.
   * [Publication] February, 2018, our paper "​VButton:​ Practical Attestation of User-driven Operations in Mobile Apps" was accepted by The 16th ACM International Conference on Mobile Systems, Applications,​ and Services (**MobiSys 2018**). Congratulations to Wenhao and Shiyu.   * [Publication] February, 2018, our paper "​VButton:​ Practical Attestation of User-driven Operations in Mobile Apps" was accepted by The 16th ACM International Conference on Mobile Systems, Applications,​ and Services (**MobiSys 2018**). Congratulations to Wenhao and Shiyu.
start.1526105349.txt.gz · Last modified: 2018/05/12 14:09 by root