The popular y-cruncher benchmark for CPUs will soon be getting a major update which will allow AMD Zen 4 CPUs to deliver up to 20% higher performance thanks to AVX-512.
AMD CPUs With Zen 4 Architecture & AVX-512 To Benefit Greatly From Upcoming y-cruncher Benchmark Update
The author of the y-cruncher benchmark, Alexander Yee, announced in a tweet that the upcoming version of the benchmark will see a major boost for AVX-512 hardware, especially AMD's Zen 4 core which features support for AVX-512.
The CPU benchmarking community will hate me for this. But the next version of y-cruncher will see large performance changes (both up and down).
The #AVX2 -> #AVX512 speedup on #Zen4 will soon grow to 10+% - no wider EUs needed.https://t.co/FrnHGbMA0O pic.twitter.com/iePIEax6Mc
— Alexander Yee (@Mysticial) June 7, 2023
y-cruncher benchmark is a popular tool to evaluate the CPU's performance for how fast it can compute PI. It's a very scalable & multi-threaded benchmark that is being used by the industry for years now and has been available for more than a decade. We also use the same benchmark in our CPU reviews.
Alexander has issued a new changelog for the upcoming y-cruncher 0.8x which is expected to be available soon and is an attempt to clean & modernize the project. Over 400,000 lines of code will be modified and that actual work on this began three years ago but little progress was made until this year. In a performance chart showing the speedup over v0.7.10, you can see that almost all of the CPUs except the older Nehalem and Ivy Bridge chips see a gain in performance in the newer build.
| Processor | Architecture | Clock Speeds | Binary | ISA | Pi computation Speedup vs. v0.7.10 | |
| Core i7 920 | Intel Nehalem | 2008 | 3.5 GHz + 3 x 1333 MT/s | 08-NHM ~ Ushio | x64 SSE4.1 | -27% |
| Core i7 3630QM | Intel Ivy Bridge | 2012 | stock + 2 x 1600 MT/s | 11-SNB ~ Hina | x64 AVX | -10% |
| FX-8350 | AMD Piledriver | 2012 | stock + 2 x 1600 MT/s | 11-BD1 ~ Miyu | x64 FMA4 | -1% |
| Core i7 5960X | Intel Haswell | 2013 | 4.0 GHz + 4 x 2400 MT/s | 13-HSW ~ Airi | x64 AVX2 | 3 - 4% |
| Core i7 6820HK | Intel Skylake | 2015 | stock + 2 x 2133 MT/s | 14-BDW ~ Kurumi | x64 AVX2 + ADX | 4 - 7% |
| Ryzen 7 1800X | AMD Zen 1 | 2017 | stock + 2 x 2866 MT/s | 17-ZN1 ~ Yukina | x64 AVX2 + ADX | ~1% |
| Core i9 7900X | Intel Skylake X | 2017 | 3.6 GHz (AVX512) + 4 x 3000 MT/s | 17-SKX ~ Kotori | x64 AVX512-DQ | 6 - 9% |
| Core i9 7940X | 3.6 GHz (AVX512) + 4 x 3466 MT/s | 10 - 13% | ||||
| Ryzen 9 3950X | AMD Zen 2 | 2019 | stock + 2 x 3000 MT/s | 19-ZN2 ~ Kagari | x64 AVX2 + ADX | 13 - 14% |
| Core i3 8121U | Intel Cannon Lake | 2018 | stock + 2 x 2400 MT/s | 18-CNL ~ Shinoa | x64 AVX512-VBMI | 16 - 17% |
| Core i7 1165G7 | Intel Tiger Lake | 2020 | stock + 2 x 2666 MT/s | 12 - 22% | ||
| Core i7 11800H | stock + 2 x 3200 MT/s | 23 - 27% | ||||
| Ryzen 9 7950X | AMD Zen 4 | 2022 | stock + 2 x 4400 MT/s | 22-ZN4 ~ Kizuna | x64 AVX512-GFNI | 23 - 31% |
The loss of performance is attributed to the removal of Hybrid NTT which was a big thing back in 2008 but isn't applicable to modern architectures. One of the biggest performance uplifts can be seen on the AMD Zen 4 CPUs with the Ryzen 9 7950X gaining up to 31% better performance. Yee states that we can expect Zen 4 to gain up to 20% speedup from the AVX-512 instruction set alone versus just AVX2 (no wider execution unit needed).
This is definitely going to be a major boost for AMD CPUs that feature AVX-512 whereas Intel's CPUs including the upcoming Meteor Lake chips won't be getting AVX-512 support on the client side. The Intel Alder Lake CPUs accidentally featured AVX-512 support at launch but Intel had to later remove it entirely from newer batches and 13th Gen Raptor Lake chips were void of any AVX-512 support.

Meanwhile, users running an AMD Ryzen 7000 (Zen 4) CPU can enjoy AVX-512 and use them in a range of applications such as running gaming emulators with crisp visuals and lots of FPS as demonstrated here. There are reports that Intel may bring back AVX-512 in future client chips but we can't say for sure when that would happen.









