L
Luke Hornof
Researcher at Intel
Publications - 18
Citations - 810
Luke Hornof is an academic researcher from Intel. The author has contributed to research in topics: Code generation & Partial evaluation. The author has an hindex of 11, co-authored 18 publications receiving 768 citations. Previous affiliations of Luke Hornof include École des mines de Nantes & University of Pennsylvania.
Papers
More filters
Proceedings Article
Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks
Urs Köster,Tristan J. Webb,Xin Wang,Marcel Nassar,Arjun K. Bansal,William Howard Constable,Oguz H. Elibol,Scott Gray,Stewart Hall,Luke Hornof,Amir Khosrowshahi,Carey K. Kloss,Ruby J. Pai,Naveen G. Rao +13 more
TL;DR: The 16-bit Flexpoint data format as discussed by the authors is a complete replacement of 32-bit floating point format training and inference, designed to support modern deep network topologies without modifications.
Book ChapterDOI
A Uniform Approach for Compile-Time and Run-Time Specialization
TL;DR: As partial evaluation gets more mature, it is now possible to use this program transformation technique to tackle realistic languages and real-size application programs.
Journal ArticleDOI
Tempo: specializing systems applications and beyond
Charles Consel,Luke Hornof,Renaud Marlet,Gilles Muller,Scott Thibault,E.-N. Volanschi,Julia Lawall,Jacques Noyé +7 more
TL;DR: Permission to make digital/hard copy of part or all of this work for personal or classroom use is granted without fee provided that the copies are not made or distributed for profit or commercial advantage.
Proceedings ArticleDOI
Automatic, template-based run-time specialization: implementation and experimental study
TL;DR: The key to this approach is the use of code templates, which are automatically generated from ordinary programs and are optimized before run time, allowing high quality code to be quickly generated at run time.
Journal ArticleDOI
Certifying Compilation and Run-Time Code Generation
Luke Hornof,Trevor Jim +1 more
TL;DR: The goal is to combine certifying compilation with run-time code generation to produce programs that are both fast and verifiably safe, and to achieve this goal, two new languages are presented: Cyclone, a type safe dialect of C, and TAL/T, atype safe assembly language.