VOBLA: a vehicle for optimized basic linear algebra

Ulysse Beaugnon 1 Alexey Kravets 2 Sven Van Haastregt 2 Riyadh Baghdadi 1 David Tweed 2 Javed Absar 2 Anton Lokhmotov 2
1 Parkas - Parallélisme de Kahn Synchrone
CNRS - Centre National de la Recherche Scientifique : UMR 8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : We present VOBLA, a domain-specific language designed for programming linear algebra libraries. VOBLA is compiled to PENCIL, a domain independent intermediate language designed for efficient mapping to accelerator architectures such as GPGPUs. PENCIL is compiled to efficient, platform-specific OpenCL code using techniques based on the polyhedral model. This approach addresses both the programmer productivity and performance portability concerns associated with accelerator programming. We demonstrate our approach by using VOBLA to implement a BLAS library. We have evaluated the performance of OpenCL code generated using our compilation flow on ARM Mali, AMD Radeon, and AMD Opteron platforms. The generated code is currently on average 1.9x slower than highly hand-optimized OpenCL code, but on average 8.1x faster than straightforward OpenCL code. Given that the VOBLA coding takes significantly less effort compared to hand-optimizing OpenCL code, we believe our approach leads to improved productivity and performance portability.
Liste complète des métadonnées

Contributor : Timothy Bourke <>
Submitted on : Thursday, April 13, 2017 - 9:57:40 PM
Last modification on : Wednesday, January 30, 2019 - 11:07:34 AM




Ulysse Beaugnon, Alexey Kravets, Sven Van Haastregt, Riyadh Baghdadi, David Tweed, et al.. VOBLA: a vehicle for optimized basic linear algebra. Proceedings of the 2014 SIGPLAN/SIGBED conference on Languages, compilers and tools for embedded systems (LCTES'14), Jun 2014, Edinburgh, United Kingdom. pp.115-124, ⟨10.1145/2666357.2597818⟩. ⟨hal-01508181⟩



Record views