[PATCH v2 2/2] Aarch64: Add new memset for Qualcomm's 0ryon-1 core
Florian Weimer
fweimer@redhat.com
Tue May 14 07:32:29 GMT 2024
* Andrew Pinski:
> +L(try_zva):
> + /* Write the first and last 64 byte aligned block using stp rather
> + than using DC ZVA. This is faster on some cores.
> + */
The “some cores” part seems outdated if it's just a memset for the
Oryon-1 core (singulare). This comment and some others, for example
> + /*
> + * Adjust count and bias for loop. By subtracting extra 1 from count,
> + * it is easy to use tbz instruction to check whether loop tailing
> + * count is less than 33 bytes, so as to bypass 2 unnecessary stps.
> + */
do not use GNU style. This one is GNU style:
> + /* Set 64..96 bytes. Write 64 bytes from the start and
> + 32 bytes from the end. */
No separate start end end lines, no * indentation, space after the final .
Thanks,
Florian
More information about the Libc-alpha
mailing list