DOE OSTI · 1764336
Using MLIR Framework for Codesign of ML Architectures Algorithms and Simulation Tools
Abstract
MLIR (Multi-Level Intermediate Representation), is an extensible compiler framework that supports high-level data structures and operation constructs. These higher-level code representations are particularly applicable to the artificial intelligence and machine learning (AI/ML) domain, allowing developers to more easily support upcoming heterogeneous AI/ML accelerators and develop flexible domain specific compilers/frameworks with higher-level intermediate representations (IRs) and advanced compiler optimizations. The result of using MLIR within the LLVM compiler framework is expected to yield significant improvement in the quality of generated machine code, which in turn will result in improved performance and hardware efficiency
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Lewis, Cannada, Hughes, Clayton, Hammond, Simon David, Rajamanickam, Sivasankaran. 2021-02-05. Using MLIR Framework for Codesign of ML Architectures Algorithms and Simulation Tools. https://doi.org/10.2172/1764336. https://searchnasa.com/record/osti%3A1764336/using-mlir-framework-for-codesign-of-ml-architectures-algorithms-and-simulation-tools
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.