Constarium
← Search

Text · dataset · 2023

EEG operation performance benchmark single GPU

Listed in CKAN @ IoT Lab

This data set contains execution time benchmark results for a set of fundamental EEG data processing operations (mean removal, convolution, average reference calculation, FFT, Current Source Density computation).

Description

The benchmarks used a single V100 GPU and varied the number of electrodes, the length of the measurement data and the parallel thread count. The benchmark programs were written in CUDA 10.2.

In addition to the total execution time, the per-element time is also calculated, where applicable. This metric shows where the GPU achieves optimal computation efficiency. The benchmarks form the basis of multi-GPU scalability analysis.

Links

Get the data

Catalogue records · 1

Topics

Provenance · 1 source records, 9 field assertions
SourceKeyLast seenRaw
CKAN @ IoT Lab40da9cb7-09b6-40a1-a9a2-2755bd3edec47 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · ckan iotlab comconnector:ckan_iotlab_com@1.0.0
concepts[field].local:field:computer-science-aimapping · ckan iotlab comconnector:ckan_iotlab_com@1.0.0
concepts[field].local:field:engineeringmapping · ckan iotlab comconnector:ckan_iotlab_com@1.0.0
created_datesource · ckan iotlab comconnector:ckan_iotlab_com@1.0.0
descriptionsource · ckan iotlab comconnector:ckan_iotlab_com@1.0.0/notes
license_textsource · ckan iotlab comconnector:ckan_iotlab_com@1.0.0
publication_datesource · ckan iotlab comconnector:ckan_iotlab_com@1.0.0
titlesource · ckan iotlab comconnector:ckan_iotlab_com@1.0.0/title
updated_datesource · ckan iotlab comconnector:ckan_iotlab_com@1.0.0