English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We present a new open-source cosmological code, called SWIFT, designed tosolve the equations of hydrodynamics using a particle-based approach (SmoothParticle Hydrodynamics) on hybrid shared/distributed-memory architectures.SWIFT was designed from the bottom up to provide excellent strong scaling onboth commodity clusters (Tier-2 systems) and Top100-supercomputers (Tier-0systems), without relying on architecture-specific features or specializedaccelerator hardware. This performance is due to three main computationalapproaches: (1) Task-based parallelism for shared-memory parallelism, whichprovides fine-grained load balancing and thus strong scaling on large numbersof cores. (2) Graph-based domain decomposition, which uses the task graph todecompose the simulation domain such that the work, as opposed to just thedata, as is the case with most partitioning schemes, is equally distributedacross all nodes. (3) Fully dynamic and asynchronous communication, in whichcommunication is modelled as just another task in the task-based scheme,sending data whenever it is ready and deferring on tasks that rely on data fromother nodes until it arrives. In order to use these approaches, the code had tobe re-written from scratch, and the algorithms therein adapted to thetask-based paradigm. As a result, we can show upwards of 60% parallelefficiency for moderate-sized problems when increasing the number of cores512-fold, on both x86-based and Power8-based architectures.

cornell university

SWIFT: Using task-based parallelism, fully asynchronous communication,  and graph partition-based domain decomposition for strong scaling on more  than 100,000 cores