APOLLO: Automatic speculative POLyhedral Loop Optimizer

Abstract : A few weeks ago, we were glad to announce the first release of Apollo, the Automatic speculative POLyhedral Loop Opti-mizer. Apollo applies polyhedral optimizations on-the-fly to loop nests, whose control flow and memory access patterns cannot be determined at compile-time. In contrast to existing tools, Apollo can handle any kind of loop nest, whose memory accesses can be performed through pointers and in-directions. At runtime, Apollo builds a predictive polyhedral model, which is used for speculative optimization including parallelization. Being a dynamic system, Apollo can even apply the polyhedral model to nonlinear loops. This paper describes Apollo from the perspective of a user, as well as some of its main contributions and mechanisms, including the just-in-time polyhedral compilation, that significantly extends the scope of polyhedral techniques.
Document type :
Conference papers
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

Contributor : Philippe Clauss <>
Submitted on : Tuesday, June 6, 2017 - 5:08:49 PM
Last modification on : Tuesday, January 1, 2019 - 5:36:01 PM
Long-term archiving on : Thursday, September 7, 2017 - 1:55:54 PM


Files produced by the author(s)


  • HAL Id : hal-01533692, version 1


Juan Manuel Martinez Caamaño, Aravind Sukumaran-Rajam, Artiom Baloian, Manuel Selva, Philippe Clauss. APOLLO: Automatic speculative POLyhedral Loop Optimizer. IMPACT 2017 - 7th International Workshop on Polyhedral Compilation Techniques, Jan 2017, Stockholm, Sweden. pp.8. ⟨hal-01533692⟩



Record views


Files downloads