[an error occurred while processing this directive]

Skip to Content

Computer Science Colloquia

Monday July 11, 2011
Dan Upton
Advisor: Kim Hazelwood
Attending Faculty: Mary Lou Soffa, Chair; Kevin Skadron, Bhanu Shankar, and Malathi Veeraraghavan

Olsson Hall, Room 236D, 1:00 PM

Ph.D. Seminar Presentation
Enabling Efficient Online Profiling of Homogeneous and Heterogeneous Multicore Systems    

Using profiling tools is a common way to understand computer systems and software and to achieve the best performance.  Profiling becomes more important as computing technology advances and makes it more difficult to intuitively reason about system characteristics.    
However, the recent shift in computing technology to multicore systems and heterogeneous systems requires new profiling methods that are more suited to the challenges of profiling multiple processing elements and multiple types of resources.  In this dissertation, we focus on an important profiling problem for each of three application classes on modern hardware: multithreaded applications, multiprogrammed workloads, and heterogeneous systems.                            
For multithreaded applications, we target reducing the overhead of collecting a trace of application characteristics such as memory references.  Reducing the overhead reduces the impact on thread interleavings in a multithreaded application.  We reduce the overhead by buffering gathered profile data in a dynamic binary instrumentation system to decouple collection of profile data from processing of profile data.  By controlling the code that is generated to fill the buffer and using a variety of methods to empty the buffer, we reduce the overhead by half compared to the previous best implementation the system.