https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105617
--- Comment #21 from Michael_S ---
(In reply to Mason from comment #20)
> Doh! You're right.
> I come from a background where overlapping/aliasing inputs are heresy,
> thus got blindsided :(
>
> This would be the optimal code, right?
>
> add4i
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105617
--- Comment #20 from Mason ---
Doh! You're right.
I come from a background where overlapping/aliasing inputs are heresy,
thus got blindsided :(
This would be the optimal code, right?
add4i:
# rdi = dst, rsi = a, rdx = b
movq 0(%rdx
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105617
--- Comment #19 from Michael_S ---
(In reply to Mason from comment #18)
> Hello Michael_S,
>
> As far as I can see, massaging the source helps GCC generate optimal code
> (in terms of instruction count, not convinced about scheduling).
>
> #in
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105617
--- Comment #18 from Mason ---
Hello Michael_S,
As far as I can see, massaging the source helps GCC generate optimal code
(in terms of instruction count, not convinced about scheduling).
#include
typedef unsigned long long u64;
void add4i(u64
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105617
Richard Biener changed:
What|Removed |Added
Target Milestone|12.3|12.4
--- Comment #17 from Richard Bien