[Bug optimization/11873] New: inefficient use of registers induces size and time overhead

[Bug optimization/11873] New: inefficient use of registers induces size and time overhead

[willy at w dot ods dot org]

PLEASE REPLY TO gcc-bugzilla@gcc.gnu.org ONLY, *NOT* gcc-bugs@gcc.gnu.org.

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=11873

           Summary: inefficient use of registers induces size and time
                    overhead
           Product: gcc
           Version: 3.3.1
            Status: UNCONFIRMED
          Severity: enhancement
          Priority: P2
         Component: optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: willy at w dot ods dot org
                CC: gcc-bugs at gcc dot gnu dot org
 GCC build triplet: i586-linux-gnu
  GCC host triplet: i586-linux-gnu
GCC target triplet: i586-linux-gnu

I wrote a simple test function which uses an unsigned long long arg and returns
its integer part + 1 if not 0, otherwise 0. GCC 3.3.1 passes some intermediate
values through several registers while it's unneeded. Here comes all my analysis.
I hope this can help improving the optimizer.
The following code :

int test(unsigned long long x) {
        if (x) {
                return (int)x + 1;
        }
        else {
                return (int)x;
        }
}

processed this way :

# 1 "bool.c"
# 1 "<built-in>"
# 1 "<command line>"
# 1 "bool.c"
int test(unsigned long long x) {
        if (x) {
                return (int)x + 1;
        }
        else {
                return (int)x;
        }
}



produces the following code when compiled with gcc 2.95.3 :
(gcc -c -O2 -fomit-frame-pointer bool.c)

00000000 <test>:
   0:   8b 54 24 04             mov    0x4(%esp,1),%edx
   4:   8b 4c 24 08             mov    0x8(%esp,1),%ecx
   8:   89 d0                   mov    %edx,%eax
   a:   09 c8                   or     %ecx,%eax
   c:   75 03                   jne    11 <test+0x11>
   e:   89 d0                   mov    %edx,%eax
  10:   c3                      ret
  11:   8d 42 01                lea    0x1(%edx),%eax
  14:   c3                      ret
  15:   8d 76 00                lea    0x0(%esi),%esi
  18:


and this one with gcc-3.3.1 :
(gcc-3.3.1 -c -O2 -fomit-frame-pointer bool.c)

00000000 <test>:
   0:   53                      push   %ebx
   1:   8b 4c 24 0c             mov    0xc(%esp,1),%ecx
   5:   8b 54 24 08             mov    0x8(%esp,1),%edx
   9:   89 cb                   mov    %ecx,%ebx
   b:   89 d0                   mov    %edx,%eax
   d:   09 d3                   or     %edx,%ebx
   f:   74 03                   je     14 <test+0x14>
  11:   8d 42 01                lea    0x1(%edx),%eax
  14:   5b                      pop    %ebx
  15:   c3                      ret
  16:   8d 76 00                lea    0x0(%esi),%esi
  19:   8d bc 27 00 00 00 00    lea    0x0(%edi,1),%edi
  20:


the EBX register is used and clobbered for nothing here. The
same code could be written this way, which is fully equivalent
and saves some cycles and bytes :

00000000 <test>:
   0:   8b 4c 24 0c             mov    0xc(%esp,1),%ecx
   4:   8b 54 24 08             mov    0x8(%esp,1),%edx
   8:   89 d0                   mov    %edx,%eax
   a:   09 d1                   or     %edx,%ecx
   c:   74 03                   je     11 <test+0x11>
   e:   8d 42 01                lea    0x1(%edx),%eax
  11:   c3                      ret
  12:

Now we can also save EDX and some more bytes :

00000000 <test>:
   0:   8b 4c 24 0c             mov    0xc(%esp,1),%ecx
   4:   8b 54 24 08             mov    0x8(%esp,1),%eax
   a:   09 c1                   or     %eax,%ecx
   c:   74 01                   je     f <test+0xf>
   e:   41                      inc    %eax
   f:   c3                      ret
  10:

Here are the compilers versions :

wtap:~/dev$ gcc -v
Reading specs from /usr/lib/gcc-lib/i586-pc-linux-gnu/2.95.3/specs
gcc version 2.95.3 20010315 (release)

wtap:~/dev$ gcc-3.3.1 -v
Reading specs from /usr/lib/gcc-lib/i586-pc-linux-gnu/3.3.1/specs
Configured with: ./configure --prefix=/usr --with-cpu=i386 --host=i586-pc-linux-gnu --enable-languages=c,c++ --disable-nls --disable-locale --enable-shared --enable-target-optspace --enable-version-specific-runtime-libs --program-suffix=-3.3.1 --enable-threads
Thread model: posix
gcc version 3.3.1

[Bug optimization/11873] inefficient use of registers induces size and time overhead

[pinskia at gcc dot gnu dot org]

PLEASE REPLY TO gcc-bugzilla@gcc.gnu.org ONLY, *NOT* gcc-bugs@gcc.gnu.org.

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=11873


pinskia at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |NEW
     Ever Confirmed|                            |1
           Keywords|                            |pessimizes-code
   Last reconfirmed|0000-00-00 00:00:00         |2003-08-10 13:52:01
               date|                            |


------- Additional Comments From pinskia at gcc dot gnu dot org  2003-08-10 13:52 -------
I can confirm this on the mainline (20030809).  GCC is not really good at optimizing long long's, I 
have some improvements but it seems not to help in this case.

[Bug optimization/11873] inefficient use of registers induces size and time overhead

[dhazeghi at yahoo dot com]

PLEASE REPLY TO gcc-bugzilla@gcc.gnu.org ONLY, *NOT* gcc-bugs@gcc.gnu.org.

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=11873


dhazeghi at yahoo dot com changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|3.4                         |---

[Bug rtl-optimization/11873] inefficient use of registers induces size and time overhead

[pinskia at gcc dot gnu dot org]

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
  BugsThisDependsOn|                            |15792


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=11873

[Bug rtl-optimization/11873] inefficient use of registers induces size and time overhead

[pinskia at gcc dot gnu dot org]

------- Additional Comments From pinskia at gcc dot gnu dot org  2004-06-03 04:29 -------
I filed 15792 to track part of this bug.

-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=11873

[Bug rtl-optimization/11873] inefficient use of registers induces size and time overhead

[pinskia at gcc dot gnu dot org]

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |WAITING


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=11873

[Bug rtl-optimization/11873] inefficient use of registers induces size and time overhead

[pinskia at gcc dot gnu dot org]

------- Additional Comments From pinskia at gcc dot gnu dot org  2004-11-13 06:01 -------
I don't know why this was put in waiting but it should not have been.

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|WAITING                     |NEW
   Last reconfirmed|2004-11-03 18:17:06         |2004-11-13 06:01:18
               date|                            |


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=11873

[Bug rtl-optimization/11873] inefficient use of registers induces size and time overhead

[rask at gcc dot gnu dot org]

------- Comment #4 from rask at gcc dot gnu dot org  2007-11-09 23:51 -------
This has improved (-O2 -fomit-frame-pointer):

test:
        movl    4(%esp), %eax   # 32    *movsi_1/1      [length = 4]
        movl    8(%esp), %edx   # 44    *movsi_1/1      [length = 4]
        orl     %eax, %edx      # 6     *iorsi_1/1      [length = 2]
        addl    $1, %eax        # 35    *addsi_1/1      [length = 3]
        cmpl    $1, %edx        # 38    *cmpsi_1_insn/1 [length = 3]
        sbbl    %edx, %edx      # 39    x86_movsicc_0_m1        [length = 2]
        notl    %edx            # 40    *one_cmplsi2_1  [length = 2]
        andl    %edx, %eax      # 41    *andsi_1/1      [length = 2]
        ret                     # 47    return_internal [length = 1]
        .ident  "GCC: (GNU) 4.3.0 20071102 (experimental)"

With -Os -fomit-frame-pointer we get:

test:
        movl    4(%esp), %edx   # 32    *movsi_1/1      [length = 4]
        xorl    %eax, %eax      # 48    *movsi_xor      [length = 2]
        movl    8(%esp), %ecx   # 43    *movsi_1/1      [length = 4]
        orl     %edx, %ecx      # 7     *iorsi_3        [length = 2]
        je      .L3             # 8     *jcc_1          [length = 2]
        leal    1(%edx), %eax   # 44    *lea_1          [length = 3]
.L3:
        ret                     # 47    return_internal [length = 1]

With -O2/-Os -fomit-frame-pointer -march=pentiumpro:

test:
        movl    4(%esp), %edx   # 32    *movsi_1/1      [length = 4]
        xorl    %eax, %eax      # 46    *movsi_xor      [length = 2]
        leal    1(%edx), %ecx   # 41    *lea_1          [length = 3]
        orl     8(%esp), %edx   # 36    *iorsi_3        [length = 4]
        cmovne  %ecx, %eax      # 38    *movsicc_noc/1  [length = 3]
        ret                     # 44    return_internal [length = 1]

I would probably code it like so:

        movl    4(%esp), %eax           ; 4
        movl    8(%esp), %edx           ; 4
        orl     %eax,   %edx            ; 2
        addl    $-1,    %edx            ; 3
        adcl    $0,     %eax            ; 3
        ret                             ; 1


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=11873