Version 0.7.8 Patch with Zen 2 Optimizations: (March 1, 2020) - permalink
A new patch for v0.7.8 has been released. Aside from the usual bug fixes, this release includes a new binary optimized for AMD Zen 2 processors.
I don't usually add new features to patch releases. However, my priorities in recent months have largely shifted away from y-cruncher. As such, very little progress has been made on v0.7.9. With no timeline for when the next feature release will happen, I decided to pull the Zen 2 optimizations into the v0.7.8 branch.
That aside, the new Zen 2 binary seems bring about 10% performance improvement. This is far greater than the 1-2% that I had expected.
This may be a bit of a shocker, but I have no idea why the improvement is so large nor do I have the time to investigate. Most of the tuning is automated by a superoptimizer. So all I did was run the superoptimizer, wait a week for it to finish, then copy-paste the results into the code.
In other words, I have no idea what it did or what it found that is so significant. But it worked, and I'll take it - no questions asked.
The Pi Record Returns to the Personal Computer: (January 29, 2020) - permalink
After a grueling 10 months of computation running from April of last year to today, the world record for Pi has once again fallen. This time to Timothy Mullican who computed 50 trillion digits of Pi on a dated (but still powerful) personal computer.
As the previous record was set by Google using their cloud platform, this computation marks the return of the Pi record to single machine personal computers.
Timothy used a 2012-era computer (Ivy Bridge) along with a very large array of 48 modern hard drives. While the processing power was significantly less than that of Google's computation, it had a better balance of computing power and storage bandwidth - thus leading to a computation of comparable speed to Google's.
Full details of the computation can be found on Tim's blog.