Search for: All records

In recent years, the number of hardware supported threads in desktop processors has increased dramatically. All but the very lowest cost netbooks and embedded processors now have at least dual cores and soon systems supporting upwards of 8 to 16 hardware threads are likely to be commonplace. Unfortunately, it will be difficult to take full advantage of the parallelism emerging processors will be able to provide. To help address this issue, we are investigating mechanisms to pre-compute function results in separate threads running concurrently with the main program thread. The concurrent threads are forked automatically and without program modification. A critical component for the success of this idea is an ability to build a background thread that can pre-compute usable results in some effective manner. For some support functions (dynamic memory) exact arguments predictions for the function pre-computation are not necessary, for others (trigonometric functions) they are. In work with dynamic memory, we are able to pre-compute memory blocks and show modest speedup: saving approximately 25% of the dynamic memory costs. In studies with predicting argument values to trigonometric functions, we show that learning algorithms are able to successfully predict the next argument values approximately 44% of the time. 

Current trends in desktop processor design have been toward many-core solutions with increased parallelism. As the number of supported threads grows in these processors, it may prove difficult to exploit them on the commodity desktop. This paper presents a study that explores the spawning of the dynamic memory management activities into a separately executing thread that runs concurrently with the main program thread. Our approach works without requiring modifications to the original source program by redefining the dynamic link path to capture malloc and free calls in a threading dynamic memory management library. The routines of this library are setup so that the initial call to malloc triggers the creation of a thread for dynamic memory management; successive calls to malloc and free will trigger coordination with this thread for dynamic memory management activities. Our preliminary studies show that we can transparently redefine the dynamic memory management activities and we have successfully done so for numerous test programs including most of the SPEC CPU2006 benchmarks, Firefox, and other unix utilities. The results of our experiments show that it is possible to achieve 2-3% performance gains in the three most memory-intensive SPEC CPU2006 benchmarks without requiring recompilation of the benchmark source code. We were also able to achieve a 3-4% speedup when using our library with the gcc and llvm compilers.