[Bug target/107627] New: [13] Regression int128_t shift generates extra xor/or.

[crazylht at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107627

            Bug ID: 107627
           Summary: [13] Regression int128_t shift generates extra xor/or.
           Product: gcc
           Version: 13.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: crazylht at gmail dot com
  Target Milestone: ---
            Target: x86_64-*-* i?86-*-*

The case is from PR106220.

#include<stdint.h>
static __inline
unsigned __int128 mk_u128(uint64_t hi, uint64_t lo)
{
  return ((unsigned __int128)hi << 64) | lo;
}

static __inline
uint64_t shrdq(uint64_t hi, uint64_t lo, unsigned rshift)
{
  return (uint64_t)(mk_u128(hi, lo) >> (rshift % 64));
}


void foo1to1(uint64_t *dst, const uint64_t* src, unsigned rshift)
{
  uint64_t r0 = shrdq(src[0], src[1], rshift);
  dst[0] = r0;
}


GCC trunk generates 

foo1to1:
        mov     rax, QWORD PTR [rsi]
        mov     r8, QWORD PTR [rsi+8]
        mov     ecx, edx
        xor     r9d, r9d
        mov     rdx, rax
        xor     eax, eax
        or      rax, r8
        or      rdx, r9
        shrd    rax, rdx, cl
        mov     QWORD PTR [rdi], rax

GCC12.2 generates

foo1to1:
        mov     rax, QWORD PTR [rsi+8]
        mov     r8, rdi
        mov     rdi, QWORD PTR [rsi]
        mov     ecx, edx
        shrd    rax, rdi, cl
        mov     QWORD PTR [r8], rax
        ret