[PATCH 0/5] Added optimized memcpy/memmove/memset for A64FX

[Wilco Dijkstra]

Hi Naohiro,

> Yes, I observed that just " hint #0x22" is inserted.
> The benchtest results show that the A64FX performance of size less than 100B with
> BTI is slower than ASIMD, but without BTI is faster than ASIMD.
> And the A64FX performance of 512B with BTI 4Gbps/sec slower than without BTI.

That's unfortunate - it seems like the hint is very slow, maybe even serializing...
We can work around if for now in GLIBC, but at some point distros will start to insert
BTI instructions by default, and then the performance hit will be bad.

> So if distinct degradation happens only on A64FX, I'd like to add another
> ENTRY macro in sysdeps/aarch64/sysdep.h such as:

I think the best option for now is to change BTI_C into NOP if AARCH64_HAVE_BTI
is not set. This avoids creating alignment issues in existing code (which is written
to assume the hint is present) and works for all string functions.

Cheers,
Wilco