Benchmarking The Performance Impact To AMD Inception Mitigations
Over the past few days I also ran some benchmarks on an AMD Ryzen 9 7950X Zen 4 desktop. Here it was a comparison of Linux 6.4.10 stable using the default "safe RET no microcode" mitigation where simply moving to the new patched Linux kernel versions but where there isn't mitigated microcode yet available.
Like with the EPYC Zen 3 server testing, on the desktop Zen 4 side it's also primarily a matter of seeing some typically small changes for workloads involving I/O.
The good news for gamers is I hadn't spotted any changes in my graphics benchmarking so far.
Video encoding and other workloads not involving significant I/O were typically not showing any performance changes with the Inception mitigation.
Like with the AMD EPYC 7763 server testing, the code compilation performance was coming in a little bit slower with the new mitigated kernel default.