120 citations · 141 across the 5 of their papers we have counts for
5 papers · 1 filter
Composable and Modular Code Generation in MLIR: A Structured and Retargetable Approach to Tensor Compiler Construction
Nicolas Vasilache, Oleksandr Zinenko, Aart J. C. Bik +9
Despite significant investment in software infrastructure, machine learning systems, runtimes and compilers do not compose properly. We propose a new design aiming at providing unp…
MLIR: A Compiler Infrastructure for the End of Moore's Law
Chris Lattner, Mehdi Amini, Uday Bondhugula +7
This work presents MLIR, a novel approach to building reusable and extensible compiler infrastructure. MLIR aims to address software fragmentation, improve compilation for heteroge…
On the Representation of Partially Specified Implementations and its Application to the Optimization of Linear Algebra Kernels on GPU
Ulysse Beaugnon, Basile Clément, Nicolas Tollenaere +1
Traditional optimizing compilers rely on rewrite rules to iteratively apply program transformations. This iterative approach hides optimization opportunities behind intermediate tr…
Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
Nicolas Vasilache, Oleksandr Zinenko, Theodoros Theodoridis +6
Deep learning models with convolutional and recurrent networks are now ubiquitous and analyze massive amounts of audio, image, video, text and graph data, with applications in auto…
PENCIL: Towards a Platform-Neutral Compute Intermediate Language for DSLs
Riyadh Baghdadi, Albert Cohen, Serge Guelton +9
We motivate the design and implementation of a platform-neutral compute intermediate language (PENCIL) for productive and performance-portable accelerator programming.