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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

For many, Graphics Processing Units (GPUs) provides a source of reliablecomputing power. Recently, Nvidia introduced its 9th generation HPC-grade GPUs,the Ampere 100, claiming significant performance improvements over previousgenerations, particularly for AI-workloads, as well as introducing newarchitectural features such as asynchronous data movement. But how well doesthe A100 perform on non-AI benchmarks, and can we expect the A100 to deliverthe application improvements we have grown used to with previous GPUgenerations? In this paper, we benchmark the A100 GPU and compare it to fourprevious generations of GPUs, with particular focus on empirically quantifyingour derived performance expectations, and -- should those expectations beundelivered -- investigate whether the introduced data-movement features canoffset any eventual loss in performance? We find that the A100 delivers lessperformance increase than previous generations for the well-known Rodiniabenchmark suite; we show that some of these performance anomalies can beremedied through clever use of the new data-movement features, which wemicrobenchmark and demonstrate where (and more importantly, how) they should beused.

Benchmarking the Nvidia GPU Lineage: From Early K80 to Modern A100 with Asynchronous Memory Transfers