We look forward to seeing you in person on Thursday, March 2, at 12:30pm. Join in person at 1302 Siebel Center for Computer Science, 201 N. Goodwin Ave or via zoom, https://illinois.zoom.us/j/83675834345?pwd=T1l6aXdzK3lOdnNmVUtjZjFzdHZsdz09
Abstract: This is a new golden age for optimizing compilers. We live in a heterogeneous world of domain-specific languages and accelerators, freeing programming language and computer architects from the chains of general-purpose, one-size-fits all designs. [John Hennessy and Dave Patterson’s Turing award lecture, shamelessly adapted.]
The lurking compiler dragons are not going away any time soon. Intrepid scientists and engineers looking for performance continue to struggle with complex processor architectures, orchestrating computations on distributed and heterogeneous systems.
We address these issues by through the design and implementation of MLIR, a large-scale compiler construction effort supporting machine learning systems and beyond. We will survey this initiative and discuss some of the interactions between machine learning and compilation in the never-ending quest for performance, performance portability and productivity. We will take a closer look at code generation abstractions for tensor algebra, and automatically validating the correctness of generated code.
Bio: Albert is a research scientist at Google. An alumnus of École Normale Supérieure de Lyon and the University of Versailles, he has been a research scientist at Inria, a visiting scholar at the University of Illinois, an invited professor at Philips Research, and a visiting scientist at Facebook Artificial Intelligence Research. Albert Cohen works on parallelizing and optimizing compilers, machine learning compilers, parallel and synchronous programming languages, with applications to high-performance computing, artificial intelligence and reactive control.