A tactical mitigation/solution...?
Here's a (semi-serious) mitigation/solution.
Performance hit is (say 10%), so what manufacturers do (with the CPU vendor's blessing) is permit a 10% overclock - say matched with XMP profiles matched to the motherboard/chipset/CPU combination for supported SKUs) carefully controlled through the BIOS/MoBo firmware so that the overclock parameters are validated and supported under a warranty extension.
This would affect larger-scale operations as their power/cooling bills would go up accordingly AND presumably the additional power load might cause some additional issues (e.g. reduced density due to increased load on power supply. UPS capacity, stress on CPU and other components leading to higher failure rates and swap-outs, individual PSUs at capacity so unable to deliver any more power so unfeasible).
There would have to be a limit as to how much higher you could go (i.e. for the workloads suffering by 20% that might be too high to push it)
Replacing CPUs due to overclock stress might be a tactic for Intel/AMD/ARM etc. at least in the medium term, although the effect on other components' warranty (i.e. from server OEMs) would be hard to gauge.
Is any the above feasible? I know it's not necessarily easy (at scale) to do it so won't work for everyone.