Using Large Input Sets with Hardware Performance Monitoring for Profile Based Compiler Optimizations
2004-09-17
Loading...
View/Download File
Persistent link to this item
Statistics
View StatisticsJournal Title
Journal ISSN
Volume Title
Title
Using Large Input Sets with Hardware Performance Monitoring for Profile Based Compiler Optimizations
Authors
Published Date
2004-09-17
Publisher
Type
Report
Abstract
Traditional Profile Guided Optimization (PGO) uses program instrumentation with one or more small training input data sets to generate edge or value profiles to guide compiler optimizations. This approach has been effective in predicting branch directions for many applications. However, for optimizations that are more dependent on the performance characteristics and the accuracy of the profiles, it is not clear whether profiles generated with small input data sets can reliably predict the program behavior under different input sets.
We studied the frequent execution paths, IPC, and the stall cycles breakdown of the test, train and different reference input sets of the SPEC2000Int benchmarks. Our studies indicate that small input sets are less effective in predicting the program behavior for larger input data sets. We propose to use hardware performance monitor (HPM) sampling based profiles to guide optimizations, because it can work with larger input sets and gather information on important performance events.
As a proof of concept, we have implemented one type of HPM sampling based PBO. We use the dynamic call path sampled by HPM to automatically guide procedure inlining in the ORC Compiler. Our results show that this approach has much lower profiling overhead, and offers significant performance gains.
Keywords
Description
Related to
Replaces
License
Series/Report Number
Technical Report; 04-033
Funding information
Isbn identifier
Doi identifier
Previously Published Citation
Other identifiers
Suggested citation
Dalvi, Sagar; Hsu, Wei-Chung; Yew, Pen-Chung. (2004). Using Large Input Sets with Hardware Performance Monitoring for Profile Based Compiler Optimizations. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/215627.
Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.