| E. Feigin, "A Case for Automatic Run-Time Code Optimization," Senior thesis, Harvard College, Division of Engineering and Applied Sciences, 1999. |
....profiling information that is used to trigger reoptimization of frequently executed code at higher levels. Self [19] uses a similar adaptive optimization scheme. Staged dynamic compilers postpone a portion of compilation until runtime, when code can be specialized based on runtime values [11, 17, 24, 25, 16]. These systems usually focus on spending as little time as possible in the dynamic compiler, performing extensive offline pre computations to avoid needing any intermediate representation at runtime. API less dynamic optimization systems include Dynamo [4] for PA RISC; Wiggins Redstone [12] ....
E. Feigin. A Case for Automatic Run-Time Code Optimization. Senior thesis, Harvard College, Division of Engineering and Applied Sciences, Apr. 1999.
....profiling information that is used to trigger reoptimization of frequently executed code at higher levels. Self [21] uses a similar adaptive optimization scheme. Staged dynamic compilers postpone a portion of compilation until runtime, when code can be specialized based on runtime values [11, 19, 27, 28, 18]. These systems usually focus on spending as little time as possible in the dynamic compiler, performing extensive offline pre computations to avoid needing any intermediate representation at runtime. Dynamic instrumentation can be used to build runtime code analyzers and, to some degree, runtime ....
E. Feigin. A Case for Automatic Run-Time Code Optimization. Senior thesis, Harvard College, Division of Engineering and Applied Sciences, Apr. 1999. http://www.eecs.harvard.edu/hube/ publications/feigin-thesis.pdf.
....On the other hand, the operating system has access to low level hardware statistics and controls the execution of applications. For these reasons, the operating system is the only sensible place to implement our technique. Run time optimization systems have been developed in recent years [7]. They postpone some optimizations until the execution of an application. The behavior of the application is monitored, and it can trigger speci c optimizations that depend on speci c run time values. We simply applied these ideas to power and temperature rather than performance. We modi ed the ....
E. Feigin. A case for automatic run-time code optimization. Bachelor of Arts Thesis, Harvard College, April 1999.
....amount of redundant work in the run time optimization system. Such a system should be able to automatically identify repetitious program behavior and dynamically optimize the appropriate code segment for that behavior. We currently have pieces of a prototype of such a system running at Harvard [11]. It is a software based approach that uses extremely lightweight mechanisms to identify when the dominant program behavior changes. More sophisticated (and thus more run time expensive) observation and optimization techniques are invoked only when the lightweight mechanisms deem these more ....
E. Feigin. A Case for Automatic Run-Time Code Optimization. Senior Thesis, Harvard College, Div. of Eng. and Applied Sciences, April 1999.
No context found.
E. Feigin, "A Case for Automatic Run-Time Code Optimization," Senior thesis, Harvard College, Division of Engineering and Applied Sciences, 1999.
No context found.
Eric Feigin. A Case for Automatic Run-Time Code Optimization. Undergraduate thesis, Harvard University, April 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC