Copy Elimination on Data Dependence Graphs

Florian Brandner 1, * Quentin Colombet 1, *
* Corresponding author
1 COMPSYS - Compilation and embedded computing systems
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : Register allocation recently regained much interest due to new decoupled strategies that split the problem into separate phases: spilling, register assignment, and copy elimination. A common assumption of existing copy elimination approaches is that the original ordering of the instructions in the program is not changed. This work presents an extension of a local recoloring technique called Parallel Copy Motion. We perform code motion on data dependence graphs in order to eliminate useless copies and reorder instructions, while at the same time a valid register assignment is preserved. Our results show that even after traditional register allocation with coalescing our technique is able to eliminate an additional 3% (up to 9%) of the remaining copies and reduce the weighted costs of register copies by up to 25% for the SPECINT 2000 benchmarks. In comparison to Parallel Copy Motion, our technique removes 11% (up to 20%) more copies and up to 39% more of the copy costs.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-00761499
Contributor : Alain Darte <>
Submitted on : Wednesday, December 5, 2012 - 3:50:58 PM
Last modification on : Wednesday, November 20, 2019 - 2:44:27 AM

Identifiers

Collections

Citation

Florian Brandner, Quentin Colombet. Copy Elimination on Data Dependence Graphs. 27th Annual ACM Symposium on Applied Computing (SAC'12), Mar 2012, Trento, Italy. pp.1916-1918, ⟨10.1145/2245276.2232091⟩. ⟨hal-00761499⟩

Share

Metrics

Record views

157