Performance optimization for NEC SX AURORA (!97)

The subroutines `init_zero_4d_[dp,sp,i4]` do not vectorize properly on NEC SX AURORA.

Loop collapsing is enforced by a compiler directive for the subroutines `init_zero_4d_[dp,sp,i4]`, in order to ensure proper vectorization on NEC SX AURORA.

Approved-by: Yen-Chen Chen <yen-chen.chen@kit.edu>
Merged-by: Yen-Chen Chen <yen-chen.chen@kit.edu>
Changelog: feature