Since around JDK 16 the following method cannot be compiled by C2 on AArch64:

public double mergeSync() { return Math.log(Math.sin(value)); }

811 416 ! 3 Test::mergeSync (61 bytes)
813 417 ! 4 Test::mergeSync (61 bytes)
816 417 ! 4 Test::mergeSync (61 bytes) COMPILE SKIPPED: too many D-U pinch points (retry at different tier)
816 418 ! 1 Test::mergeSync (61 bytes)
416 ! 3 Test::mergeSync (61 bytes) made not entrant

The problem is the scheduler will create temporary Nodes for each OptoReg killed by the MachProjs from the two runtime log/sin leaf calls. After SVE support was added these runtime calls kill more registers, and the number of new Nodes added by anti_do_def exceeds an internal limit (which is roughly proportional to the method size).