Accurate static estimators for program optimization

Wagner, Tim A.; Maverick, Vance; Graham, Susan L.; Harrison, Michael A.

doi:10.1145/178243.178251

Cited by 69 publications

(16 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graham et al have noted that an execution profiler must attribute execution time in a way that is significant for the logical structure of a program as well as for its textual decomposition [7]. Wagner et al have used quantitative metrics to compare estimates from static analysis to those derived from profiles, and found that simple techniques for predicting branches and loop counts suffice to estimate intraprocedural frequency patterns with high accuracy [16]. A Markov model can also be combined with functionlevel information to produce the interprocedural frequency information.…”

Section: Related Workmentioning

confidence: 99%

Platform independent analysis of probabilities on execution paths of multithreaded programs

Chen

2013

2013 IEEE/ACIS 12th International Conference on Computer and Information Science (ICIS)

View full text Add to dashboard Cite

A concurrent program is intuitively associated with probability. In this paper we propose a platform independent approach, called ProbPP, to analyzing the probabilities on the execution paths of the multithreaded programs. The main idea of ProbPP is to calculate the probabilities on the basis of two kinds of probabilities: Primitive Dependent Probabilities (PDPs) representing the control dependent probabilities among the program statements and Thread Execution Probabilities (TEPs) representing the probabilities of threads being scheduled to execute. We have also conducted two preliminary experiments to evaluate the effectiveness and performance of ProbPP, and the experimental results show that ProbPP can provide engineers with acceptable accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Platform independent analysis of probabilities on execution paths of multithreaded programs

Chen

2013

2013 IEEE/ACIS 12th International Conference on Computer and Information Science (ICIS)

View full text Add to dashboard Cite

show abstract

“…A Markov process [38] is adopted to estimate the execution frequency of each basic block. Our analysis algorithm is executed based on these statically estimated execution frequencies.…”

Section: Probabilistic Alias Analysis Based On Static-assigned Probabmentioning

confidence: 99%

Probabilistic Alias Analysis of Executable Code

Chen

2010

Int J Parallel Prog

View full text Add to dashboard Cite

In this paper we present a method for flow-sensitive, context-insensitive probabilistic alias analysis at the assembly level. A memory disambiguation algorithm is also developed for revealing the probability of two registers holding the same memory location. The alias analysis and memory disambiguation algorithms are implemented based on the Diablo post-link optimizer. Experimental results show that the technique can estimate the probabilities that registers refer to the same memory address in benchmark programs with an overall average error of about 6.8%. The post-link optimizer can leverage the obtained quantitative information to facilitate aggressive analyses and optimizations.

show abstract

“…We sort basic blocks in the order of their execution frequency. For each basic block B, this can be estimated from both the loop nesting level of B and the execution frequency of B within its acyclic region based on the probability of each conditional branch [Wagner et al 1994]. Additionally, we use the profile information collected for conditional branches by our combined interpreter and dynamic compiler [Suganuma et al 2001] in order to enhance the accuracy of branch probabilities.…”

Section: Order Determination For Eliminationmentioning

confidence: 99%

Effective sign extension elimination for java

Kawahito

Komatsu

Nakatani

2006

ACM Trans. Program. Lang. Syst.

View full text Add to dashboard Cite

Computer designs are shifting from 32-bit architectures to 64-bit architectures, while most of the programs available today are still designed for 32-bit architectures. Java, for example, specifies the frequently used "int" as a 32-bit signed integer. If such Java programs are executed on a 64-bit architecture, many 32-bit signed integers must be sign-extended to 64-bit signed integers for correct operations. This causes serious performance overhead. In this article, we present a fast and effective algorithm for eliminating sign extensions. We implemented this algorithm in the IBM Java Just-in-Time (JIT) compiler for IA-64. Our experimental results show that our algorithm effectively eliminates the majority of sign extensions. They also show that it improves performance by 6.9% for jBYTEmark and 3.3% for SPECjvm98 over the previously known best algorithm, while it increases JIT compilation time by only 0.11%.

show abstract

Accurate static estimators for program optimization

Abstract: Determining the relative execution frequency of program regions is essential for many important optimization techniques, including register allocation, function inlining, and instruction scheduling. Estechniques, we identify 76% of the most frequently executed call sites.

Cited by 69 publications

References 12 publications

Platform independent analysis of probabilities on execution paths of multithreaded programs

Platform independent analysis of probabilities on execution paths of multithreaded programs

Probabilistic Alias Analysis of Executable Code

Effective sign extension elimination for java

Contact Info

Product

Resources

About