https://bugs.kde.org/show_bug.cgi?id=385409
--- Comment #55 from Vadim Barkov <vbr...@gmail.com> ---
(In reply to Julian Seward from comment #47)
> (In reply to Vadim Barkov from comment #46)
> > Since the issue is solved,
>
> I don't consider it to be solved.
>
> You didn't answer my questions in comment 44:
>
> * what your implementation strategy is
>
The VFENE instruction is implemented in this way:
/* VFENE %%v1, %%v2, %%v3 */
i = 0;
while(i < 16) {
elem1 = GetElem(V128(v2), i)
elem2 = GetElem(V128(v3), i)
if(elem1 != elem2)
break;
i++
}
v1 = 64HLto128(U64(i), U64(0))
VFENEZ also breaks the loop if (elem1 == 0)
I think this code should generate correct valgrind warnings ()
> * about the relationship to the amd64 implementation.
>
I am not sure that understand it.
PS
I am sorry for late response.
--
You are receiving this mail because:
You are watching all bug changes.
