[Bug c/39102] New: gcc generating multiple stack stores in optimised code

[Bug c/39102] New: gcc generating multiple stack stores in optimised code

[adam at consulting dot net dot nz]

Test code:

#include <stdint.h>

struct u64x2_t {
  uint64_t u64a;
  uint64_t u64b;
};

union u64_u {
  uint64_t u64;
  uint64_t *ptr_u64;
};

struct u64x2_t multiple_stack_stores(struct u64x2_t in) {
  struct u64x2_t out;
  out.u64a=in.u64a+1;
  out.u64b=in.u64b;
  if ((out.u64a & 63)==0) {
    union u64_u u;
    u.u64=(out.u64a >> 6) << 3;
    out.u64b=u.ptr_u64[0];
  }
  return out;
}

struct u64x2_t no_stack_stores(uint64_t u64a, uint64_t u64b) {
  struct u64x2_t out;
  out.u64a=u64a+1;
  out.u64b=u64b;
  if ((out.u64a & 63)==0) {
    union u64_u u;
    u.u64=(out.u64a >> 6) << 3;
    out.u64b=u.ptr_u64[0];
  }
  return out;
}

int main() {
  return 0;
}


$ gcc-4.3 -O3 gcc-stack-stores-bug.c && objdump -d -m i386:x86-64:intel a.out
generates in part:

0000000000400480 <multiple_stack_stores>:
  400480:       48 8d 4f 01             lea    rcx,[rdi+0x1]
  400484:       48 89 7c 24 d8          mov    QWORD PTR [rsp-0x28],rdi
  400489:       48 89 74 24 e0          mov    QWORD PTR [rsp-0x20],rsi
  40048e:       f6 c1 3f                test   cl,0x3f
  400491:       75 0f                   jne    4004a2
<multiple_stack_stores+0x22>
  400493:       48 89 c8                mov    rax,rcx
  400496:       48 c1 e8 06             shr    rax,0x6
  40049a:       48 8b 34 c5 00 00 00    mov    rsi,QWORD PTR [rax*8+0x0]
  4004a1:       00 
  4004a2:       48 89 f2                mov    rdx,rsi
  4004a5:       48 89 c8                mov    rax,rcx
  4004a8:       c3                      ret    
  4004a9:       0f 1f 80 00 00 00 00    nop    DWORD PTR [rax+0x0]

00000000004004b0 <no_stack_stores>:
  4004b0:       48 8d 4f 01             lea    rcx,[rdi+0x1]
  4004b4:       f6 c1 3f                test   cl,0x3f
  4004b7:       75 0f                   jne    4004c8 <no_stack_stores+0x18>
  4004b9:       48 89 c8                mov    rax,rcx
  4004bc:       48 c1 e8 06             shr    rax,0x6
  4004c0:       48 8b 34 c5 00 00 00    mov    rsi,QWORD PTR [rax*8+0x0]
  4004c7:       00 
  4004c8:       48 89 f2                mov    rdx,rsi
  4004cb:       48 89 c8                mov    rax,rcx
  4004ce:       c3                      ret    
  4004cf:       90                      nop    


With the better-designed x86-64 ABI this struct is passed and returned in
registers. So why is gcc generating this code:

  400484:       48 89 7c 24 d8          mov    QWORD PTR [rsp-0x28],rdi
  400489:       48 89 74 24 e0          mov    QWORD PTR [rsp-0x20],rsi

Similar output is observed with gcc-4.1, gcc-4.2 and gcc-snapshot (Debian
20090129-1) 4.4.0 20090129 (experimental) [trunk revision 143770]


-- 
           Summary: gcc generating multiple stack stores in optimised code
           Product: gcc
           Version: 4.3.3
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: adam at consulting dot net dot nz
  GCC host triplet: Debian Linux
GCC target triplet: x86-84 core2


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=39102