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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

High Performance Computing (HPC) platforms allow scientists to modelcomputationally intensive algorithms. HPC clusters increasingly useGeneral-Purpose Graphics Processing Units (GPGPUs) as accelerators; FPGAsprovide an attractive alternative to GPGPUs for use as co-processors, but theyare still far from being mainstream due to a number of challenges faced whenusing FPGA-based platforms. Our research aims to make FPGA-based highperformance computing more accessible to the scientific community. In this workwe present the results of investigating the acceleration of a particularatmospheric model, Flexpart, on FPGAs. We focus on accelerating the mostcomputationally intensive kernel from this model. The key contribution of ourwork is the architectural exploration we undertook to arrive at a solution thatbest exploits the parallelism available in the legacy code, and is alsoconvenient to program, so that eventually the compilation of high-level legacycode to our architecture can be fully automated. We present the three differenttypes of architecture, comparing their resource utilization and performance,and propose that an architecture where there are a number of computationalcores, each built along the lines of a vector instruction processor, works bestin this particular scenario, and is a promising candidate for a genericFPGA-based platform for scientific computation. We also present the results ofexperiments done with various configuration parameters of the proposedarchitecture, to show its utility in adapting to a range of scientificapplications.

A Reconfigurable Vector Instruction Processor for Accelerating a Convection Parametrization Model on FPGAs