H2020Индивидуална стипендия2015–2017

DataLocAbstractions · Advanced Programming Environments for Exascale Data-Centric Computing

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период: 2015-04-01 → 2017-03-31
Финансиране от ЕС: 145 846 €
Участници: 1
Схема: MSCA-IF

Линиите свързват координатора с партньорите.

Накратко на български

Нови програмни инструменти оптимизират начина, по който данните се преместват в суперкомпютри, например чрез по-ефективно управление на паметта при сложни симулации. Това е важно, защото при хиляди процесорни ядра преносът на информация консумира повече енергия и време от самите изчисления.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

Advanced Programming Environments for Exascale Data-Centric Computing

Parallel programming environments have been designed to optimize for arithmetic operations because computation has been traditionally the most expensive component of a computing system over more than 30 years. Technology trends in the computer architecture break our existing assumptions because moving data has become the most costly component of computing in terms of power consumption and performance. Moreover, we already have 240 cores chip today and within 5 years it is projected that 1000-core chips will be available in Exascale systems (next generation high performance computing systems), which means even more increase in parallelism on the chip. These changes have created an urgent need to redesign the programming environments because none of the prevalent programming languages provide interfaces to support data locality. Dr. Unat proposed simple programming abstractions for data locality and created advanced programming environments that encapsulate these abstractions to enable the transition of codes from a compute-centric to a data-centric paradigm. The project provides a rich interface to express parallelism and data locality through tiling, data layout and loop traversal abstractions. These abstractions are applied to adaptive mesh refinement applications and enabled them to scale on multicore architectures. In the first objective, Dr. Unat designed the new programming abstractions and tiling based programming model that hides the details of data decomposition, cache locality and memory affinity management from the programmer. In the second objective, we developed an accompanying runtime system to support the programming abstractions on distributed memory environment. The runtime system leverages the metadata embedded in the programming model and enables runtime optimizations, which is otherwise not possible. In the third objective, we reached our ultimate goal and integrated the abstractions and runtime system into the real-life scientific applications. We tested and demonstrated the performance, productivity, and scalability of the proposed programming environments on applications with various complexities. Finally, the success of the project allowed us to receive further grants from the national funding agency and 6 publications at prestigious conferences and journals.

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

Power efficiency has emerged as the primary design constraint for the next generation of computing systems and the dominant source of energy consumption has shifted from computing elements to the movement of data. This shift will make locality of data the new programming challenge of the decade. However, current programming environments take a compute-centric approach and do not reflect the realities of the architectural trends. For performance and energy efficiency reasons, there is a critical need for a new data-centric programming paradigm that takes data locality as a primary criterion. Moreover the next generation of high performance systems (Exascale Systems) will be equipped with 2048-core chips, requiring applications to expose over a thousand-way concurrency. For a smooth transition to these advanced technologies, this project proposes a theoretical foundation and programming abstractions; embodied in an API (Application Programming Interface) that provides a rich interface to address the dual challenges of data locality and increased on-chip parallelism for emerging parallel computing systems. The ultimate goal of the project is to integrate the proposed API into real-life applications that are of great interest to Europe. The project will study Turbulent Combustion as a motivating application class because of its importance in energy production. The proposed research, by reinventing the programming environment to better reflect the realities of future platforms, will facilitate the transition to Exascale of applications that are critical for strengthening European leadership in HPC.

Оригинален текст от CORDIS (на английски).

Участници

KOC UNIVERSITY · IstanbulКоординаторТурция