Calculating a record-breaking 31.4T digits of Pi with GCP

Meh, throwing raw power at the problem is not that impressive.<p>Bellard&#x27;s [1] 2009 record was much more impressive, because he used a clever formula to break the existing record with a mere (albeit beefy) desktop computer: <a href="https:&#x2F;&#x2F;bellard.org&#x2F;pi&#x2F;pi2700e9&#x2F;" rel="nofollow">https:&#x2F;&#x2F;bellard.org&#x2F;pi&#x2F;pi2700e9&#x2F;</a><p>The record he broke with his desktop PC was made using a supercomputer cluster.<p>[1] If somebody is not familiar with him, he is also the original author of QEMU, ffmpeg and the Tiny C Compiler.

How Many Decimals of Pi Do We Really Need? (NASA&#x2F;JPL): <a href="https:&#x2F;&#x2F;www.jpl.nasa.gov&#x2F;edu&#x2F;news&#x2F;2016&#x2F;3&#x2F;16&#x2F;how-many-decimals-of-pi-do-we-really-need&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.jpl.nasa.gov&#x2F;edu&#x2F;news&#x2F;2016&#x2F;3&#x2F;16&#x2F;how-many-decimal...</a>

Alexander Yee&#x27;s writeup is interesting – CPU utilisation was only about 12%, they encountered quite nasty I&#x2F;O bottlenecks (particularly for writes.)<p><a href="http:&#x2F;&#x2F;www.numberworld.org&#x2F;blogs&#x2F;2019_3_14_pi_record&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.numberworld.org&#x2F;blogs&#x2F;2019_3_14_pi_record&#x2F;</a><p>Contradicts the Google blog a little, especially where he points out that they hit performance issues with live migration (Google said it worked fine without impact on the application.)

This is a time someone must cite 3Blue1Brown: [(183) The most unexpected answer to a counting puzzle - YouTube](<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=HEfHFsfGXjs" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=HEfHFsfGXjs</a>)

The piano music for each digit at the A-π (API) page is particularly beautiful<p><a href="https:&#x2F;&#x2F;pi.delivery&#x2F;#demosmusic" rel="nofollow">https:&#x2F;&#x2F;pi.delivery&#x2F;#demosmusic</a>

I&#x27;m curious, did someone estimate how much it would cost to replicate this experiment on GCloud with the same infrastructure?

Don&#x27;t miss the video on how Emma did this:<p>- <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=JvEvTcXF-4Q" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=JvEvTcXF-4Q</a><p>(length 3:14)

this is perfect for mounting the Pi filesystem :)<p><a href="https:&#x2F;&#x2F;github.com&#x2F;philipl&#x2F;pifs" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;philipl&#x2F;pifs</a>

Whenever I see the ridiculous number of places to which pi has been calculated, I wonder if anyone has checked to see if there is a repeating pattern. I mean, 31 trillion places leaves a lot of possibilities for repetition of a couple of billion digits.<p>Or is my understanding of what constitutes an irrational number outdated? Is there another definition that precludes even looking for repetition in hopes of finding a denominator?

Perhaps they subliminally hope the final pages of the novel &quot;contact&quot; to be real

Are the some PI-like constants, but much harder to calculate? Like even a million digits would be hard to calculate?

&quot;we have lots of compute resources and access to software, aren&#x27;t we awesome?&quot;

Awesome, now we are a game of life which has generated Pi to 31.4T digits at least once :D

What is the file size?

&gt; March 14 (represented as 3&#x2F;14 in many parts of the world)<p>haha

How can you tell if the results are accurate?

Did they find the patterns (circle?) that was referend at the end of Carl Sagan’s Contact book?

Does pi compress? It must if it is only numbers, but only by a half?

You don&#x27;t get those gigajoules of heat waste back at the end

Why did she stop calculating? A time limit or resource issue?

Absolute madmen

&quot;31,415,926,535,897 to be exact, or π * 10^13&quot;<p>Uhm no, you mean, <i>approximately</i> π * 10^13.

I wonder if the blockchain (or contract?) approach could break the record after combining all that gpu power.