Improving performance by branch reordering

Yang, Menglong; Uh, Gang-Ryung; Whalley, David

doi:10.1145/277650.277711

Cited by 12 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Five of the test programs have fewer mispredictions after condition merging and the remaining ones exhibited increases. A similar phenomenon was discovered when reordering contiguous sequences of branches [9,10]. While condition merging may sometimes adversely affect branch prediction performance, the average execution time of the test programs still decreases.…”

Section: Resultssupporting

confidence: 63%

“…For instance, Figure 4 shows an example of eliminating a logically redundant condition using technique A that could not be eliminated using static analysis alone [6]. Technique B eliminates conditions that are separated by other intervening branches, which is also not feasible using a non-path based approach [9,10]. Note that techniques A, B, and C merge sets of conditions that compare a single variable and technique D merges sets of conditions that can compare multiple variables.…”

Section: Resultsmentioning

confidence: 99%

“…Conditional branches have been coalesced together into an indirect jump from a jump table [8]. Sequences of branches have been reordered to allow the sequence to be exited earlier, which reduces the number of branches executed [9,10]. A technique, which shares some similarities to the work described in this paper, applies conjunctions to selection conditions for records in database queries [11].…”

Section: Related Workmentioning

confidence: 99%

“…Figure 5(b) depicts the flow graph representing these tests. It is often the case that a variable involved in such tests is not equal to any of the constants [9,10]. Profile data are collected to determine not only the paths that are frequent, but also the reason that a particular transition was taken.…”

Section: Merging Not Equal Tests Using Range Checksmentioning

confidence: 99%

“…Note that when the merged condition is not satisfied, the original set of branches must be tested since the variable could still be equal to any of the specified constants. By performing condition merging on frequent paths, we can merge conditions separated by other intervening branches, which is not possible using a non-path based approach [9,10].…”

Section: Merging Not Equal Tests Using Range Checksmentioning

confidence: 99%

See 4 more Smart Citations

Branch elimination by condition merging

Kreahling

Whalley

Bailey

et al. 2005

Softw: Pract. Exper.

Self Cite

View full text Add to dashboard Cite

Conditional branches are expensive. Branches require a significant percentage of execution cycles since they occur frequently and cause pipeline flushes when mispredicted. In addition, branches result in forks in the control flow, which can prevent other code-improving transformations from being applied. In this paper we describe profile-based techniques for replacing the execution of a set of two or more branches with a single branch on a conventional scalar processor. These sets of branches can include tests of multiple variables. For instance, the test if (p1 != 0 && p2 != 0), which is testing for NULL pointers, can be replaced with if (p1 & p2 != 0). Program profiling is performed to target condition merging along frequently executed paths. The results show that eliminating branches by merging conditions can significantly reduce the number of conditional branches executed in non-numerical applications.

show abstract

Section: Resultssupporting

confidence: 63%

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Merging Not Equal Tests Using Range Checksmentioning

confidence: 99%

Section: Merging Not Equal Tests Using Range Checksmentioning

confidence: 99%

See 3 more Smart Citations

Branch elimination by condition merging

Kreahling

Whalley

Bailey

et al. 2005

Softw: Pract. Exper.

Self Cite

View full text Add to dashboard Cite

show abstract

Generalized Index-Set Splitting

Barton

Tal

Blainey

et al. 2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper introduces Index-Set Splitting (ISS), a technique that splits a loop containing several conditional statements into several loops with less complex control flow. Contrary to the classic loop unswitching technique, ISS splits loops when the conditional is loop variant. ISS uses an Index Sub-range Tree (IST) to identify the structure of the conditionals in the loop and to select which conditionals should be eliminated. This decision is based on an estimation of the code growth for each splitting: a greedy algorithm spends a pre-determined code growth budget. ISTs separate the decision about which splits to perform from the actual code generation for the split loops. The use of ISS to improve a loop fusion framework is then discussed. ISS opportunity identification in the SPEC2000 benchmark suite and three other suites demonstrate that ISS is a general technique that may benefit other compilers.

show abstract

Program decision logic optimization using predication and control speculation

2001

View full text Add to dashboard Cite

Abstract-The mainstream arrival of predication, a means other than branching of selecting instructions for execution, has required compiler architects to reformulate fundamental analyses and transformations. Traditionally, the compiler has generated branches straightforwardly to implement control flow designed by the programmer and has then performed sophisticated "global" optimizations to move and optimize code around them. In this model, the inherent tie between the control state of the program and the location of the single instruction pointer serialized runtime evaluation of control and limited the extent to which the compiler could optimize the control structure of the program (without extensive code replication). Predication provides a means of control independent of branches and instruction fetch location, freeing both compiler and architecture from these restrictions; effective compilation of predicated code, however, requires sophisticated understanding of the program's control structure. This article explores a representational technique which, through direct code analysis, maps the program's control component into a canonical database, a reduced ordered binary decision diagram (ROBDD), which fully enables the compiler to utilize and manipulate predication. This abstraction is then applied to optimize the program's control component, transforming it into a form more amenable to instruction-level parallel (ILP) execution.

show abstract

Improving performance by branch reordering

Cited by 12 publications

References 14 publications

Branch elimination by condition merging

Branch elimination by condition merging

Generalized Index-Set Splitting

Program decision logic optimization using predication and control speculation

Contact Info

Product

Resources

About