Currently some aarch64 relevant options (e.g. UseSIMDForMemoryOps) are set in vm_version_aarch64.cpp based on the concrete CPU model.

However there's currently no code for Amazon's Graviton 1 & 2 CPUs which identify themselves as follows:

Graviton 1 (Cortex A72)
===============

processor : 1
BogoMIPS : 166.66
Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 cpuid
CPU implementer : 0x41
CPU architecture: 8
CPU variant : 0x0
CPU part : 0xd08
CPU revision : 3

Graviton 2 (Neoverse N1)
================

processor : 1
BogoMIPS : 243.75
Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm lrcpc dcpop asimddp ssbs
CPU implementer : 0x41
CPU architecture: 8
CPU variant : 0x3
CPU part : 0xd0c
CPU revision : 1

After we saw quite some differences in the performance characteristics of Graviton 1 & 2 this issue will focus on Graviton 2. We'll create a separate issue for Graviton 1.