Версия для печати темы
Нажмите сюда для просмотра этой темы в оригинальном формате
Студенческий форум > Эра "нано": настоящее и будущее. Прогнозы и планы. Масштабирование, разброс характеристик, снижение Еп > (2020) From FLOPS to IOPS: The New Bottlenecks of


Автор: VAL 4.01.2020 12:10
(2020) From FLOPS to IOPS: The New Bottlenecks of Scientific Computing
Источник: https://www.sigarch.org/from-flops-to-iops-the-new-bottlenecks-of-scientific-computing/
Автор: by Spyros Blanas on Jan 3, 2020

QUOTE
More than a decade ago, the pioneering computer scientist Jim Gray envisioned a fourth paradigm of scientific discovery that uses computers to solve data-intensive scientific problems. Today, scientific discovery, whether observational, in-silico or experimental, requires sifting through and analyzing complex, large datasets. For example, plasma simulation simulates billions of particles in a single run, but analyzing the results requires sifting through a single frame (a multi-dimensional array) that is more than 50 TB big—and that is for only one timestep of a much longer simulation. Similarly, modern observation instruments also produce large datasets: a two-photon imaging of a mouse brain yields up to 100 GB of spatiotemporal data per hour and electrocorticography (ECoG) recordings yield 280 GB per hour.


QUOTE
Given the exponential growth trend in data volumes, the bottleneck for many scientific applications is no longer floating point operations per second (FLOPS) but I/O operations per second (IOPS).

Автор: VAL 12.10.2022 10:39
doh.gif

Powered by Invision Power Board (http://www.invisionboard.com)
© Invision Power Services (http://www.invisionpower.com)