T
Tobias Grosser
Researcher at University of Edinburgh
Publications - 68
Citations - 1706
Tobias Grosser is an academic researcher from University of Edinburgh. The author has contributed to research in topics: Compiler & Computer science. The author has an hindex of 18, co-authored 57 publications receiving 1427 citations. Previous affiliations of Tobias Grosser include ETH Zurich & French Institute for Research in Computer Science and Automation.
Papers
More filters
Journal ArticleDOI
Polly — performing polyhedral optimizations on a low-level intermediate representation
TL;DR: Polly is presented, an infrastructure for polyhedral optimizations on the compiler's internal, low-level, intermediate representation (IR) and an interface for connecting external optimizers and a novel way of using the parallelism they introduce to generate SIMD and OpenMP code is presented.
Polly – Polyhedral optimization in LLVM
Tobias Grosser,Hongbin Zheng,Raghesh Aloor,Andreas Simburger,Armin Grosslinger,Louis-Noël Pouchet +5 more
TL;DR: Polly is presented, a project to enable polyhedral optimizations in LLVM that automatically detects and transforms relevant program parts in a language-independent and syntactically transparent way and supports programs written in most common programming languages and constructs.
Proceedings ArticleDOI
Hybrid Hexagonal/Classical Tiling for GPUs
TL;DR: A time-tiling method for iterative stencil computations on GPUs that favors coalesced global-memory accesses, data reuse in local/shared-memory or cache, avoidance of thread divergence, and concurrency, combining hexagonal tile shapes along the time and one spatial dimension with classical tiling along the other spatial dimensions is proposed.
Polyhedral Extraction Tool
Sven Verdoolaege,Tobias Grosser +1 more
TL;DR: A new library for extracting a polyhedral model from C source based on clang, the LLVM C frontend, and isl, a library for manipulating quasi-ane sets and relations, which allows for an easy construction and a powerful and compact representation of thepolyhedral model.
Proceedings ArticleDOI
PENCIL: A Platform-Neutral Compute Intermediate Language for Accelerator Programming
Riyadh Baghdadi,Ulysse Beaugnon,Albert Cohen,Tobias Grosser,Michael Kruse,Chandan Reddy,Sven Verdoolaege,Adam Betts,Alastair F. Donaldson,Jeroen Ketema,Javed Absar,Sven van Haastregt,Alexey Kravets,Anton Lokhmotov,Robert David,Elnar Hajiyev +15 more
TL;DR: PENCIL, a rigorously-defined subset of GNU C99-enriched with additional language constructs-that enables compilers to exploit parallelism and produce highly optimized code when targeting accelerators, is presented.