法国国家信息与自动化研究所（INRIA）高性能张量计算博士后职位

法国国家信息与自动化研究所（INRIA）高性能张量计算博士后职位

Post-Doctoral Research Visit F/M Scheduling and Combinatorial Tools For High Performance Tensor Computations [Post-Doc Campaign 2021 Lyon]

Inria

Description

2021-03475 - Post-Doctoral Research Visit F/M Scheduling and combinatorial tools for high performance tensor computations Post-Doc Campaign 2021 Lyon

Contract type : Fixed-term contract

Level of qualifications required : PhD or equivalent

Fonction : Post-Doctoral Research Visit

About the research centre or Inria department

Grenoble Rhône-Alpes Research Center groups together a few less than 650 people in 37 research teams and 8 research support departments.

Staff is localized on 5 campuses in Grenoble and Lyon, in close collaboration with labs, research and higher education institutions in Grenoble and Lyon, but also with the economic players in these areas.

Present in the fields of software, high-performance computing, Internet of things, image and data, but also simulation in oceanography and biology, it participates at the best level of international scientific achievements and collaborations in both Europe and the rest of the world.

Context

The post-doc position is at the INRIA team ROMA. The ROMA team is located at the École normale supérieure de Lyon. ROMA is pursuing fundamental research on scheduling strategies and algorithm design for heterogeneous platforms, solvers for sparse linear systems, and tensor computations. The proposed post- doc topic is aligned with the PeachTree Associated Team Project (https:// perso.ens-lyon.fr/bora.ucar/peachtree/) and the post-doc will have the opportunity to interact with PeachTree's local and international partners.

Assignment

Tensors, or multidimensional arrays, have many uses in data analysis applications. The additional dimensions over matrices enable gleaning information that is otherwise unreachable. Graphs and hypergraphs are used to model tensors and (hyper)graph algorithms are used to untangle intricate relations hidden in the tensorial data. The proposed post-doc position explores this correspondence between tensor computations and graph/hypergraph algorithms to develop efficient and effective scheduling and combinatorial tools for high performance shared memory tensor computations. The recruited person will design, analyze, and implement those tools and test their effect on basic tensor computations that are available in open source software.

Main activities

The recruited post-doc will design, analyze, and implement algorithms in C++, collaborate with PeachTree Associated Team partners, write papers, do presentations at conferences and workshops.

Skills

The ideal candidate is enthusiastic and motivated; has background on algorithms and OpenMP programming; is well-versed programmer in C/C++; is familiar with sparse matrices and graphs; enjoys implementing algorithms and eager to develop codes on multi-core machines. Experience with tensor computations is not required, but a plus. Good communication skills in English are required.

Benefits package

  Subsidized meals

  Partial reimbursement of public transport costs

  Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)

  Possibility of teleworking (after 6 months of employment) and flexible organization of working hours

  Professional equipment available (videoconferencing, loan of computer equipment, etc.)

  Social, cultural and sports events and activities

  Access to vocational training

  Social security coverage Remuneration

Gross salary: 2 653 Euros per month.