Improving Communication Patterns in Polyhedral Process Networks

Autor: Alias, Christophe

Embedded system performances are bounded by power consumption. The trend is to offload greedy computations on hardware accelerators as GPU, Xeon Phi or FPGA. FPGA chips combine both flexibility of programmable chips and energy-efficiency of specializ

Externí odkaz: http://arxiv.org/abs/1801.04821

A Polyhedral Approach for Scalar Promotion

Autor: Sadler, Alec, Alias, Christophe, Thievenaz, Hugo

Publikováno v: Conférence francophone d'informatique en Parallélisme, Architecture et Système (COMPAS'22)
Conférence francophone d'informatique en Parallélisme, Architecture et Système (COMPAS'22), Jul 2022, Amiens, France
[Research Report] RR-9437, Institut National de Recherche en Informatique et en Automatique (INRIA). 2021, pp.14

Memory accesses are a well known bottleneck whose impact might be mitigated by using properly the memory hierarchy until registers. In this paper, we address array scalarization, a technique to turn temporary arrays into a collection of scalar variab

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::00c78040a912ceb30b43aa2d79ecb67d
https://inria.hal.science/hal-03862223

Lightweight Array Contraction by Trace-Based Polyhedral Analysis

Autor: Thievenaz, Hugo, Kimura, Keiji, Alias, Christophe

Publikováno v: C3PO 2022-International Workshop on Compiler-assisted Correctness Checking and Performance Optimization for HPC
C3PO 2022-International Workshop on Compiler-assisted Correctness Checking and Performance Optimization for HPC, Jun 2022, Hamburg, Germany

International audience; Array contraction is a compilation optimization used to reduce memory consumption, by reducing the size of temporary arrays in a program while preserving its correctness. The usual approach to this problem is to perform a stat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::183723aecfc9e21e2fe1a0806b4dd5f5
https://inria.hal.science/hal-03862219/document

Towards Trace-Based Array Contraction

Autor: Thievenaz, Hugo, Kimura, Keiji, Alias, Christophe

Publikováno v: [Research Report] RR-9442, Inria; Waseda University. 2021, pp.20

Array contraction is a compilation optimization used to reduce the memory con-sumption, by shrinking the size of temporary arrays while preserving the correctness. The usualapproach to this problem is to perform a static analysis of the given program

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7512413b213a0dd57defb4fccab4fc41
https://hal.inria.fr/hal-03482055/document

On the Verification of Polyhedral Program Transformations

Autor: Alias, Christophe, Iooss, Guillaume, Rajopadhye, Sanjay

Publikováno v: HPCS 2020-18th International Conference on High Performance Computing & Simulation, CADO 2020-3rd Special Session on Compiler Architecture, Design and Optimization
HPCS 2020-18th International Conference on High Performance Computing & Simulation, CADO 2020-3rd Special Session on Compiler Architecture, Design and Optimization, Oct 2020, Barcelona, Spain. pp.1-8

International audience; This paper presents a pragma language to specify a polyhedral program transformation directly in the code and a verification algorithm able to check the correctness of the specified transformation. Our language is general enou

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::4ff519cb84ee3139458d6b9032a0b700
https://hal.science/hal-03106070