Title
Domain-Specific Multi-Level IR Rewriting for GPU: The Open Earth Compiler for GPU-accelerated Climate Simulation
Abstract
AbstractMost compilers have a single core intermediate representation (IR) (e.g., LLVM) sometimes complemented with vaguely defined IR-like data structures. This IR is commonly low-level and close to machine instructions. As a result, optimizations relying on domain-specific information are either not possible or require complex analysis to recover the missing information. In contrast, multi-level rewriting instantiates a hierarchy of dialects (IRs), lowers programs level-by-level, and performs code transformations at the most suitable level. We demonstrate the effectiveness of this approach for the weather and climate domain. In particular, we develop a prototype compiler and design stencil- and GPU-specific dialects based on a set of newly introduced design principles. We find that two domain-specific optimizations (500 lines of code) realized on top of LLVM’s extensible MLIR compiler infrastructure suffice to outperform state-of-the-art solutions. In essence, multi-level rewriting promises to herald the age of specialized compilers composed from domain- and target-specific dialects implemented on top of a shared infrastructure.
Year
DOI
Venue
2021
10.1145/3469030
ACM Transactions on Architecture and Code Optimization
Keywords
DocType
Volume
Weather and climate, stencil computations, intermediate representations
Journal
18
Issue
ISSN
Citations 
4
1544-3566
2
PageRank 
References 
Authors
0.42
0
9
Name
Order
Citations
PageRank
Tobias Gysi131.11
Christoph Müller220.42
Oleksandr Zinenko3101.25
Stephan Herhut420.42
Eddie Davis520.42
Tobias Wicky620.42
Oliver Fuhrer720.42
Torsten Hoefler821.44
Tobias Grosser927116.04