Since aligned loads and stores are huge performance advantage the implementation always tries to do aligned access. Among the cases when src and dst addresses are aligned or unaligned evenly there are cases of not evenly unaligned src and dst. For such cases (if the length is big enough) ext instruction is used to merge-and-shift two memory chunks loaded from two adjacent aligned locations and then the adjusted chunk gets stored to aligned address.
Performance gain against the current T2 implementation: memcpy-large: 65K-32M: +40% - +10% memcpy-walk: 128-32M: +20% - +2%
75c1aee500 aarch64: optimized memcpy implementation for thunderx2
ChangeLog | 6 +
sysdeps/aarch64/multiarch/memcpy_thunderx.S | 14 -
sysdeps/aarch64/multiarch/memcpy_thunderx2.S | 607 ++++++++++++++++++++++++++-
3 files changed, 609 insertions(+), 18 deletions(-)