, 16 tweets, 9 min read
My Authors
Read all threads
@nasa looks at macro scale and @cern at the tiniest scale
95% of the universe is unknown
@cern has built a €13.8B time-machine to understand the universe outside Geneva
@ubotica is one of the few Irish companies that has been inside the @CERN LHC with @esa @ESA_EO
Battering @IntelMovidius #MyriadX using this baby 100m below ground using 50M sensors and 40M fps

The SoC designed here in Ireland passed with flying colours

@ubotica @Intel_IRL @Inteliot @ESA_EO @Happy4Trigger
The next step is an 80km accelerator to accelerate particles to 99.9999% of the speed of light
Machine Learning is at the heart of the largest IoT installation on the planet

BTW 90% of @CERN staff are engineers not physicists

Only AI/ML can pick apart 40M collisions per sec
The HW Trigger system is used to achieve ultra low latency @ 1petabyte/sec

Trigger parses out 1k from 1.7B collisions at the heart of the ATLAS detector
@cern inference, not training, is the big challenge
Inference has to be completed in tiny fractions of a second using FPGAs
The €1B EU quantum computing initiative could target particle physics as its an ideal use case
The energy required from the grid is so high the LHC has to be switched off in winter to prevent Switzerland from freezing
The @cern massive IoT instrument generates a tsunami of data
Hadoop didn't fit @CERN's needs given the size of the dataset. For real time operation a better solution is required for 24hr uptime. They're using @Oracle object storage for much more cost-efficient storage
They're using a custom framework but have built @ProjectJupyter workbooks on top for ease of use
Missing some Tweet in this thread? You can try to force a refresh.

Enjoying this thread?

Keep Current with david moloney

Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

Twitter may remove this content at anytime, convert it as a PDF, save and print for later use!

Try unrolling a thread yourself!

how to unroll video

1) Follow Thread Reader App on Twitter so you can easily mention us!

2) Go to a Twitter thread (series of Tweets by the same owner) and mention us with a keyword "unroll" @threadreaderapp unroll

You can practice here first or read more on our help page!

Follow Us on Twitter!

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just three indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!