[Bug other/103345] New: missed optimization: add/xor individual bytes to form a word

["gcc at rjk dot terraraq.uk" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103345

            Bug ID: 103345
           Summary: missed optimization: add/xor individual bytes to form
                    a word
           Product: gcc
           Version: unknown
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: other
          Assignee: unassigned at gcc dot gnu.org
          Reporter: gcc at rjk dot terraraq.uk
  Target Milestone: ---

All code generated with godbolt's idea of 'trunk'. See
https://godbolt.org/z/Wcj61PKKG

Source:

#include <stdint.h>

uint32_t load_le_32_or(const uint8_t *ptr)
{
  return ((uint32_t)ptr[0]) | ((uint32_t)ptr[1] << 8) | ((uint32_t)ptr[2] <<
16) | ((uint32_t)ptr[3] << 24);
}

uint32_t load_le_32_add(const uint8_t *ptr)
{
  return ((uint32_t)ptr[0]) + ((uint32_t)ptr[1] << 8) + ((uint32_t)ptr[2] <<
16) + ((uint32_t)ptr[3] << 24);
}


uint32_t load_le_32_xor(const uint8_t *ptr)
{
  return ((uint32_t)ptr[0]) ^ ((uint32_t)ptr[1] << 8) ^ ((uint32_t)ptr[2] <<
16) ^ ((uint32_t)ptr[3] << 24);
}

The ^ version is admittedly a bit of an odd choice but the + version is a
reasonably natural way to write the code.


Code on gcc -O2:

load_le_32_or:
        mov     eax, DWORD PTR [rdi]
        ret
load_le_32_add:
        movzx   eax, BYTE PTR [rdi+1]
        movzx   edx, BYTE PTR [rdi+2]
        sal     eax, 8
        sal     edx, 16
        add     eax, edx
        movzx   edx, BYTE PTR [rdi]
        add     eax, edx
        movzx   edx, BYTE PTR [rdi+3]
        sal     edx, 24
        add     eax, edx
        ret
load_le_32_xor:
        movzx   eax, BYTE PTR [rdi+1]
        movzx   edx, BYTE PTR [rdi+2]
        sal     eax, 8
        sal     edx, 16
        xor     eax, edx
        movzx   edx, BYTE PTR [rdi]
        xor     eax, edx
        movzx   edx, BYTE PTR [rdi+3]
        sal     edx, 24
        xor     eax, edx
        ret


Code on clang -O2:

load_le_32_or:                          # @load_le_32_or
        mov     eax, dword ptr [rdi]
        ret
load_le_32_add:                         # @load_le_32_add
        mov     eax, dword ptr [rdi]
        ret
load_le_32_xor:                         # @load_le_32_xor
        mov     eax, dword ptr [rdi]
        ret