Engineers at StorageReview have shattered their own world record by calculating pi to an astounding 202,112,290,000,000 digits, smashing its previous record of 105 trillion digits set earlier this year in time for World Pi Day (March 14 – 3/14).
The previous record, the team’s second attempt, was achieved using a dual processor 128-core AMD EPYC 9754 Bergamo system, equipped with 1.5TB of DRAM and nearly a petabyte of Solidigm QLC SSDs. For this attempt, the team opted for dual Intel Xeon 8592+ CPUs and 28 Solidigm P5336 61.44TB NVMe SSDs.
Key to the challenge was a Dell PowerEdge R760 with a 24-bay NVMe Direct Drives backplane and an internal PCIe switch to enable simultaneous communication among all NVMe drives without the need for extra hardware or RAID devices. The setup was further customized by integrating a PCIe riser from multiple R760s for additional NVMe SSDs and enhancing it with larger heatsinks from another R760 to maximize turbo-boost capability.
Third time’s the charm
While the previous attempt was marred by bugs, performance-related issues, and memory and storage constraints, things ran much smoother this time around.
“Not only did the Solidigm drives and Dell PowerEdge R760 work together flawlessly, the nearly hands-off nature of this new record was a welcomed change after the perils of our last record attempt,” said Kevin O’Brien, StorageReview Lab Director.
“After what we went through on the last test run to 105, I am glad that we chose the platform we did for the big record,” he continued.
The team used the y-cruncher application and the Chudnovsky algorithm for the calculation which ran continuously for 85 days (the entire calculation run was 100.673 days), and consumed almost 1.5PB of the available total 1.720PB of data storage.
Sign up to the Ddecoraty Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!
“This new Pi world record is an exciting accomplishment because this computational workload is as intense as many of the AI workloads we are seeing today,” said Greg Matson, VP, Solidigm’s Data Center Storage Group. “We are thrilled to have had the opportunity to enable another record-breaking attempt to calculate Pi with our partners at Dell Technologies and the experts at StorageReview.”
The remarkable 202 trillion digit pi calculation serves as a landmark achievement, pushing the boundaries of computational mathematics further, but we have a sneaky suspicion that this won’t be StorageReview’s final run at the challenge.
Want to break the geekiest world record of them all?
Want to break the geekiest world record of them all? Here’s how engineers spent 75 days to calculate Pi to 105 trillion digits — just in time for Pi day.
Engineers at StorageReview decided to do something incredibly geeky for this year’s Pi day (March 14 – 3/14) – beat their own record for calculating Pi. Considering that the previous record, achieved last year, was 100 trillion digits, the challenge was no mean feat. While – spoiler alert – they smashed the record, it did take them 75 days to accomplish it.
The task was achieved using a dual processor 128-core AMD EPYC 9754 Bergamo system, equipped with 1.5TB of DRAM and nearly a petabyte of Solidigm QLC SSDs. The team started their computation on December 14, 2023, and finished on February 27, 2024, spanning 75 days. They used the Chudnovsky (1988) algorithm to calculate Pi, and the computation required a total memory of 1.36 TiB.
New challenges
The journey to 105 trillion digits of Pi – the new record – was not without fresh challenges. The team had to deal with performance-related issues, which led them to delve into the intricacies of parallel computing and hardware interactions. They discovered a CPU hazard specific to the Zen4 architecture involving super-alignment and its effects on memory access patterns.
The engineers also encountered a critical floating-point arithmetic error within the AVX512 code path of the N63 multiply algorithm. With remote assistance from the developer, Alexander Yee, they were able to diagnose and fix the problem, resulting in the successful computation.
Summing up, StorageReview’s Jordan Ranous noted, “The run to 105 trillion digits of Pi was much more complex than we expected. Upon reflection, we should have expected to encounter new issues; after all, we’re completing a computation that had never been done before. But with the 100 trillion computation completed with a much more “duct tape and chicken wire” configuration, we thought we had it made. Ultimately, it took a collaborative effort to get this rig across the finish line.”
Was it worth it? Ranous says, “While we rejoice with our partners in this record-breaking run, we must ask, “What does this even mean?” Five more trillion digits of Pi probably won’t make a huge difference to mathematics. Still, we can draw some lines between computational workloads and the need for modern underlying hardware to support them. Fundamentally, this exercise reflects that the proper hardware makes all the difference, whether an enterprise data center cluster or a large HPC installment. For the Pi computation, we were completely restricted by storage. Faster CPUs will help accelerate the math, but the limiting factor to many new world records is the amount of local storage in the box.”
Are you a pro? Subscribe to our newsletter
Sign up to the Ddecoraty Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!