https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113701
--- Comment #2 from Uroš Bizjak <ubizjak at gmail dot com> ---
(In reply to Uroš Bizjak from comment #0)
> Following testcase:
>
> --cut here--
> typedef unsigned __int128 U;
>
> U f0 (U x, U y) { return x + y; }
> U f1 (U x, U y) { return x - y; }
>
> U f2 (U x, U y) { return x | y; }
>
> int f3 (U x, U y) { return x == y; }
> int f4 (U x, U y) { return x < y; }
> --cut here--
>
> shows some issues with __int128 parameter passing.
>
> gcc -O2:
>
> f0:
> movq %rdx, %rax
> movq %rcx, %rdx
> addq %rdi, %rax
> adcq %rsi, %rdx
> ret
>
> f1:
> xchgq %rdi, %rsi
> movq %rdx, %r8
> movq %rsi, %rax
> movq %rdi, %rdx
> subq %r8, %rax
> sbbq %rcx, %rdx
> ret
>
> f2:
> xchgq %rdi, %rsi
> movq %rdx, %rax
> movq %rcx, %rdx
> orq %rsi, %rax
> orq %rdi, %rdx
> ret
>
> f3:
> xchgq %rdi, %rsi
> movq %rdx, %r8
> movq %rcx, %rax
> movq %rsi, %rdx
> movq %rdi, %rcx
> xorq %rax, %rcx
> xorq %r8, %rdx
> xorl %eax, %eax
> orq %rcx, %rdx
> sete %al
> ret
>
> f4:
> xorl %eax, %eax
> cmpq %rdx, %rdi
> sbbq %rcx, %rsi
> setc %al
> ret
>
> Functions f0 and f4 are now optimal.
>
> Functions f1, f2 and f3 emit extra XCHG, but the swap should be propagated
> to MOV instructions instead.
>
> The most problematic function is f3, which regressed noticeably from gcc-12.3:
This patch solves the regression:
--cut here--
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index bac0a6ade67..02fed16db72 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -1632,11 +1632,6 @@ (define_insn_and_split "*cmp<dwi>_doubleword"
(set (match_dup 4) (ior:DWIH (match_dup 4) (match_dup 5)))])]
{
split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[2]);
- /* Placing the SUBREG pieces in pseudos helps reload. */
- for (int i = 0; i < 4; i++)
- if (SUBREG_P (operands[i]))
- operands[i] = force_reg (<MODE>mode, operands[i]);
-
operands[4] = gen_reg_rtx (<MODE>mode);
/* Special case comparisons against -1. */
--cut here--
gcc -O2:
f3:
xchgq %rdi, %rsi
xorl %eax, %eax
xorq %rsi, %rdx
xorq %rdi, %rcx
orq %rcx, %rdx
sete %al
ret
