Return to search

Deep: Dependency Elimination Using Early Predictions

Conditional branches have traditionally been a performance bottleneck for most processors. The high frequency of branches in code coupled with expensive pipeline flushes on mispredictions make branches expensive instructions worth optimizing. Conditional branches have historically inhibited compilers from applying optimizations across basic block boundaries due to the forks in control flow that they introduce. This thesis describes a systematic way of generating paths (traces) of branch-free code at compile time by decomposing branching and verification operations to eliminate the dependence of a branch on its preceding compare instruction. This explicit decomposition allows us to move comparison instructions past branches and to merge pre and post branch code. These paths generated at compile time can potentially provide additional opportunities for conventional optimizations such as common subexpression elimination, dead assignment elimination and instruction selection. Moreover, this thesis describes a way of coalescing multiple branch instructions within innermost loops to produce longer basic blocks to provide additional optimization opportunities. / A Thesis submitted to the Department of Computer Science in partial fulfillment of the requirements for the degree of Master of Science. / Summer Semester 2018. / July 20, 2018. / Includes bibliographical references. / David Whalley, Professor Directing Thesis; Xin Yuan, Committee Member; Weikuan Yu, Committee Member.

Identiferoai:union.ndltd.org:fsu.edu/oai:fsu.digital.flvc.org:fsu_647277
ContributorsPenagos, Luis G. (author), Whalley, David B. (professor directing thesis), Yuan, Xin (committee member), Yu, Weikuan (committee member), Florida State University (degree granting institution), College of Arts and Sciences (degree granting college), Department of Computer Science (degree granting departmentdgg)
PublisherFlorida State University
Source SetsFlorida State University
LanguageEnglish, English
Detected LanguageEnglish
TypeText, text, master thesis
Format1 online resource (42 pages), computer, application/pdf

Page generated in 0.0015 seconds