On Tue, Aug 6, 2024 at 8:50 PM Andi Kleen <a...@firstfloor.org> wrote:
>
> > - s += 16;
> > + v16qi data, t;
> > + /* Unaligned load. Reading beyond the final newline is safe, since
> > + files.cc:read_file_guts pads the allocation. */
>
> You need to change that function to use 32 byte padding as Jakub
> pointed out (I forgot that too)
>
> > + data = *(const v16qi_u *)s;
> > + /* Prevent propagation into pshufb and pcmp as memory operand. */
> > + __asm__ ("" : "+x" (data));
>
> It would probably make sense to a file a PR on this separately,
> to eventually fix the compiler to not need such workarounds.
> Not sure how much difference it makes however.
This is probably to work around bugs in older compiler versions? If
not I agree.
Otherwise the patch is OK.
Thanks,
Richard.
> -Andi
