On Mon Jun 19 13:24:15 2023 +0000, Jinoh Kang wrote:
Can we just coalesce these two calls into one for better optimization opportunities (e.g., use of STLR with RCpc semantics on ARM64, instead of `STR; DMB ISH`)?
__atomic_add_fetch( x, SEQUENCE_MASK, __ATOMIC_RELEASE ); \
I believe this is to pair with `__SHARED_READ_FENCE` and `__SHARED_READ_SEQ` respectively. I don't know how valid it is to merge both.