Speaker:     Dr. Simon Moore

                                   University of Cambridge

Title:            Does Rigorous Computer Systems Research Demand Open Source Hardware?

Date:            Monday, May 13, 2013          

Time:           12:30 p.m.   (Light lunch will be served.)        

Room:         E-Quad, Room B205

Host:            Prof. Ruby Lee

 

Abstract:  Computer systems research relies heavily on open source software like the LLVM compiler framework, operating systems like FreeBSD and Linux, para virtualisation like Xen, etc.  However, much of this research is bounded by the availability of commodity hardware which provides an unnecessary

fixed point in the design space exploration process.  In this talk I argue that we need more open source and rigorously engineered hardware platforms to facilitate computer systems research which straddles traditional boundaries.  To illustrate the point, the CHERI processor (a 64-bit RISC based capability machine soon to be open sourced) will be introduced together with observations from associated compilation (LLVM based) and operating system (FreeBSD based) research into fine grained sand boxing.  By making changes all the way from the gate-level to the application-level we believe that much more secure computer systems can be constructed whilst providing a migration path for legacy systems.

 

Bio:  Simon Moore is Reader (Associate Professor in USA terms) in Computer Architecture at the University of Cambridge Computer Laboratory in England, where he undertakes research and teaching in the general area of computer design with particular interests in massively parallel secure computer architecture. Dr. Moore is the senior member of the Computer Architecture research group <http://www.cl.cam.ac.uk/research/comparch/>.

 

This work was undertaken in collaboration with SRI International.  Portions of this work were sponsored by the Defense Advanced Research Projects Agency (DARPA) and the Air Force Research Laboratory (AFRL), under contract FA8750-10-C-0237. The views, opinions, and/or findings contained in this report are those of the author and should not be interpreted as representing the official views or policies, either expressed or implied, of the Defense Advanced Research Projects Agency or the Department of Defense.