Skip to Main content Skip to Navigation
Conference papers

Progressive Raising in Multi-level IR

Abstract : Multi-level intermediate representations (IR) show great promise for lowering the design costs for domain-specific compilers by providing a reusable, extensible, and non-opinionated framework for expressing domain-specific and high-level abstractions directly in the IR. But, while such frameworks support the progressive lowering of high-level representations to low-level IR, they do not raise in the opposite direction. Thus, the entry point into the compilation pipeline defines the highest level of abstraction for all subsequent transformations, limiting the set of applicable optimizations, in particular for general-purpose languages that are not semantically rich enough to model the required abstractions. We propose Progressive Raising, a complementary approach to the progressive lowering in multi-level IRs that raises from lower to higher-level abstractions to leverage domain-specific transformations for low-level representations. We further introduce Multi-Level Tactics, our declarative approach for progressive raising, implemented on top of the MLIR framework, and demonstrate the progressive raising from affine loop nests specified in a general-purpose language to high-level linear algebra operations. Our raising paths leverage subsequent high-level domain-specific transformations with significant performance improvements.
Document type :
Conference papers
Complete list of metadata
Contributor : Timothy Bourke Connect in order to contact the contributor
Submitted on : Friday, February 12, 2021 - 11:59:08 AM
Last modification on : Friday, January 21, 2022 - 3:19:38 AM
Long-term archiving on: : Thursday, May 13, 2021 - 6:43:33 PM


Files produced by the author(s)


  • HAL Id : hal-03139764, version 1



Lorenzo Chelini, Andi Drebes, Oleksandr Zinenko, Albert Cohen, Nicolas Vasilache, et al.. Progressive Raising in Multi-level IR. CGO 2021 : International Symposium on Code Generation and Optimization, Feb 2021, Seoul / Virtual, South Korea. ⟨hal-03139764⟩



Les métriques sont temporairement indisponibles