The long lifespan of the pi math icon has been extended even further thanks to Google Cloud.
Google developer advocate Emma Haruka Iwao has successfully calculated pi to 100 trillion digits using the company’s cloud platform.
What’s even more impressive is that this is the second time in just three years that Iwao has broken the record.
Why does it matter?
Mathematicians have been trying to calculate pi to its limits since Ancient Egypt, Greece, and Babylon.
Google openly admitted that you may not need to “calculate trillions of decimals of pi”, but said that “massive calculation demonstrates how flexible Google Cloud infrastructure allows teams around the world to push the boundaries of scientific experimentation”.
While pi-related calculations appear in everything from relativity theory to engineering problems and GPS mapping, these types of extreme calculations are often used as a benchmarking tool by computer scientists, to prove and evaluate the power of your hardware.
How did they do it?
Google Cloud says it used is available to everyone Compute Engine service to do the registration calculation.
The tech giant attributed its improved result compared to the last time it made the attempt in 2019 to improve networking and storage.
The project managed to achieve 100 Gbps of egress bandwidth, a huge improvement on the 16 Gbps of egress available when they calculated 31.4 trillion digits in 2019.
The project used a new network driver Google Virtual NIC (gVNIC)which is integrated with Google’s Andromeda Virtual Networking stack
Google also attributed the project’s success largely to improving storage, saying that because “the dataset doesn’t fit in main memory, the speed of the storage system was the bottleneck in the calculation.”
For this work, they decided to use the Balanced Persistent Disc, a new type of persistent disk that, according to Google, offers up to 1,200 MB/s read and write and 15-80k IOPS.
Those interested in checking out more about the project details can head over to GitHub (opens in new tab) to find the code that Google used.
Google will also host a live webinar on June 15 to share more about the experimentation process and results. here (opens in new tab) to join.