I think all of this talk of execution resources, buffer sizes, etc etc is all rather superfluous. GLC/RPC use significantly more transistors than Zen 4 (with higher power to match) yet doesn't have anything significant (IPC, meaningful frequency gap) to show for it. I think it's thus fair to conclude that GLC is bloated. The fact that they seem to be more or less reusing it until '24 doesn't make it look any better today. The opposite, if anything.