Tests on AArch64 platform show that floating-point Math.min/max() intrinsics do not improve the performance too much. But it's very helpful to add auto-vectorization support for the fmin/fmax operations.
JDK-8263782AArch64: Add vectorization support for fmin/fmax
is blocked by
JDK-8188313C2: Consider enabling auto-vectorization for simple reductions