[avr-gcc-list] gcc 4.3.3 vs inline

[Szikra Istvan]

/**
Category: miss optimization
affects: avr-gcc 4.3.3
Size optimization inline check generates bigger code

I get this warning: "inlining failed in call to 'extIntSetEnable':
optimizing for size and code size would grow"
NO! It would not!

Is this a known bug, or something that should be reported?
(tried google 'avr optimizing for size and code size would grow' with no joy)

See the test case for an example:
(sorry if it's still a bit much, but I tried to strip everything
that's not relevant.
I spent a lot of time on it, and it's a fraction of the original code.)
In this case NOT inlining generates more then 5 times as much
instructions than inlining!
*/

#define extIntSetEnable_gcc_4_3_3_aail_workaround
//#define extIntSetEnable_gcc_4_3_3_aail_workaround     
__attribute__((always_inline))

#include <avr/io.h>
#include <avr/interrupt.h>

#define BIT(x) (0x01 << (x))
#define bit_set(p,b) ((p) |= BIT(b))
#define bit_clear(p,b) ((p) &= ~BIT(b))
//#define bit_write(p,b,c) (c ? bit_set(p,b) : bit_clear(p,b))
#define bit_write(p,b,c) if (c) { bit_set(p,b);}else bit_clear(p,b)

static inline
void extIntSetEnable_gcc_4_3_3_aail_workaround extIntSetEnable(char
channel, char enabled)
{
  switch (channel) { /// enable / disable int
    case 0: {
      bit_write(GICR,INT0,enabled);
    } break;
    case 1: {
      bit_write(GICR,INT1,enabled);
    } break;
    case 2: {
      bit_write(GICR,INT2,enabled);
    } break;
  }
}
int main (void)
{
  extIntSetEnable(0,0);
  ///...
  extIntSetEnable(0,1);
  for (;;)
  {
  }
}

/**
avr-gcc (GCC) 3.4.6
avr-gcc -c -mmcu=atmega16 -I. -gdwarf-2 -DF_CPU=16000000UL
-DBOOTSIZE=1024  -Os -funsigned-char -funsigned-bitfields
-fpack-struct -fshort-enums -fno-strict-aliasing -Wall -Winline
-Wstrict-prototypes -Wa,-adhlns=test_il.lst -ID:/Lib/ -std=gnu99 -MD
-MP -MF .dep/test_il.o.d test_il.c -o test_il.o
avr-gcc -mmcu=atmega16 -I. -gdwarf-2 -DF_CPU=16000000UL
-DBOOTSIZE=1024  -Os -funsigned-char -funsigned-bitfields
-fpack-struct -fshort-enums -fno-strict-aliasing -Wall -Winline
-Wstrict-prototypes -Wa,-adhlns=test_il.o -ID:/Lib/ -std=gnu99 -MD -MP
-MF .dep/test_il.elf.d test_il.o --output test_il.elf
-Wl,-Map=test_il.map,--cref    -lm
-Wl,--section-start=.bootloader=0x3800
Size after:
.text              184      0

00000054 <__ctors_end>:
  58:   cf e5           ldi     r28, 0x5F       ; 95
  5a:   d4 e0           ldi     r29, 0x04       ; 4
  5c:   de bf           out     0x3e, r29       ; 62
  5e:   cd bf           out     0x3d, r28       ; 61
...
0000008e <main>:
  8e:   cf e5           ldi     r28, 0x5F       ; 95  <<< again? ... gcc 3.4.6 
has
it's own faults
  90:   d4 e0           ldi     r29, 0x04       ; 4
  92:   de bf           out     0x3e, r29       ; 62
  94:   cd bf           out     0x3d, r28       ; 61

  extIntSetEnable(0,0);
  96:   8b b7           in      r24, 0x3b       ; 59
  98:   8f 7b           andi    r24, 0xBF       ; 191
  9a:   8b bf           out     0x3b, r24       ; 59
  extIntSetEnable(0,1);
  9c:   8b b7           in      r24, 0x3b       ; 59
  9e:   80 64           ori     r24, 0x40       ; 64
  a0:   8b bf           out     0x3b, r24       ; 59

*/

/**
avr-gcc (WinAVR 20090313) 4.3.2
avr-gcc -c -mmcu=atmega16 -I. -gdwarf-2 -DF_CPU=16000000UL
-DBOOTSIZE=1024  -Os -funsigned-char -funsigned-bitfields
-fpack-struct -fshort-enums -fno-strict-aliasing
-fno-inline-small-functions  -save-temps  -Wall -Winline
-Wstrict-prototypes -Wa,-adhlns=test_il.lst -ID:/Lib/ -std=gnu99 -MD
-MP -MF .dep/test_il.o.d test_il.c -o test_il.o
avr-gcc -mmcu=atmega16 -I. -gdwarf-2 -DF_CPU=16000000UL
-DBOOTSIZE=1024  -Os -funsigned-char -funsigned-bitfields
-fpack-struct -fshort-enums -fno-strict-aliasing
-fno-inline-small-functions  -save-temps  -Wall -Winline
-Wstrict-prototypes -Wa,-adhlns=test_il.o -ID:/Lib/ -std=gnu99 -MD -MP
-MF .dep/test_il.elf.d test_il.o --output test_il.elf
-Wl,-Map=test_il.map,--cref    -lm
-Wl,--section-start=.bootloader=0x3800
Size after:
.text              146      0

0000006c <main>:
      bit_write(GICR,INT0,enabled);
  6c:   8b b7           in      r24, 0x3b       ; 59
  6e:   8f 7b           andi    r24, 0xBF       ; 191
  70:   8b bf           out     0x3b, r24       ; 59

  72:   8b b7           in      r24, 0x3b       ; 59
  74:   80 64           ori     r24, 0x40       ; 64
  76:   8b bf           out     0x3b, r24       ; 59

*/

/**
avr-gcc (WinAVR 20100110) 4.3.3
avr-gcc -c -mmcu=atmega16 -I. -gdwarf-2 -DF_CPU=16000000UL
-DBOOTSIZE=1024  -Os -funsigned-char -funsigned-bitfields
-fpack-struct -fshort-enums -fno-strict-aliasing
-fno-inline-small-functions  -save-temps  -Wall -Winline
-Wstrict-prototypes -Wa,-adhlns=test_il.lst -ID:/Lib/ -std=gnu99 -MD
-MP -MF .dep/test_il.o.d test_il.c -o test_il.o
test_il.c: In function 'main':
test_il.c:32: warning: inlining failed in call to 'extIntSetEnable':
optimizing for size and code size would grow
test_il.c:49: warning: called from here
test_il.c:32: warning: inlining failed in call to 'extIntSetEnable':
optimizing for size and code size would grow
test_il.c:54: warning: called from here
avr-gcc -mmcu=atmega16 -I. -gdwarf-2 -DF_CPU=16000000UL
-DBOOTSIZE=1024  -Os -funsigned-char -funsigned-bitfields
-fpack-struct -fshort-enums -fno-strict-aliasing
-fno-inline-small-functions  -save-temps  -Wall -Winline
-Wstrict-prototypes -Wa,-adhlns=test_il.o -ID:/Lib/ -std=gnu99 -MD -MP
-MF .dep/test_il.elf.d test_il.o --output test_il.elf
-Wl,-Map=test_il.map,--cref    -lm
-Wl,--section-start=.bootloader=0x3800
Size after:
.text              216      0


0000006c <extIntSetEnable>:
    switch (channel) { /// enable / disable int
  6c:   81 30           cpi     r24, 0x01       ; 1
  6e:   69 f0           breq    .+26            ; 0x8a <extIntSetEnable+0x1e>
  70:   81 30           cpi     r24, 0x01       ; 1
  72:   18 f0           brcs    .+6             ; 0x7a <extIntSetEnable+0xe>
  74:   82 30           cpi     r24, 0x02       ; 2
  76:   e1 f4           brne    .+56            ; 0xb0 <extIntSetEnable+0x44>
  78:   10 c0           rjmp    .+32            ; 0x9a <extIntSetEnable+0x2e>
    case 0: {
      bit_write(GICR,INT0,enabled);
  7a:   66 23           and     r22, r22
  7c:   19 f0           breq    .+6             ; 0x84 <extIntSetEnable+0x18>
  7e:   8b b7           in      r24, 0x3b       ; 59
  80:   80 64           ori     r24, 0x40       ; 64
  82:   0f c0           rjmp    .+30            ; 0xa2 <extIntSetEnable+0x36>
  84:   8b b7           in      r24, 0x3b       ; 59
  86:   8f 7b           andi    r24, 0xBF       ; 191
  88:   0c c0           rjmp    .+24            ; 0xa2 <extIntSetEnable+0x36>
    } break;
    case 1: {
      bit_write(GICR,INT1,enabled);
  8a:   66 23           and     r22, r22
  8c:   19 f0           breq    .+6             ; 0x94 <extIntSetEnable+0x28>
  8e:   8b b7           in      r24, 0x3b       ; 59
  90:   80 68           ori     r24, 0x80       ; 128
  92:   07 c0           rjmp    .+14            ; 0xa2 <extIntSetEnable+0x36>
  94:   8b b7           in      r24, 0x3b       ; 59
  96:   8f 77           andi    r24, 0x7F       ; 127
  98:   04 c0           rjmp    .+8             ; 0xa2 <extIntSetEnable+0x36>
    } break;
    case 2: {
      bit_write(GICR,INT2,enabled);
  9a:   66 23           and     r22, r22
  9c:   21 f0           breq    .+8             ; 0xa6 <extIntSetEnable+0x3a>
  9e:   8b b7           in      r24, 0x3b       ; 59
  a0:   80 62           ori     r24, 0x20       ; 32
  a2:   8b bf           out     0x3b, r24       ; 59
  a4:   08 95           ret
  a6:   8b b7           in      r24, 0x3b       ; 59
  a8:   8f 7d           andi    r24, 0xDF       ; 223
  aa:   8b bf           out     0x3b, r24       ; 59
  ac:   08 95           ret

000000ae <main>:
    extIntSetEnable(0,0);
  ae:   80 e0           ldi     r24, 0x00       ; 0
  b0:   60 e0           ldi     r22, 0x00       ; 0
  b2:   0e 94 36 00     call    0x6c    ; 0x6c <extIntSetEnable>
    extIntSetEnable(0,1);
  b6:   80 e0           ldi     r24, 0x00       ; 0
  b8:   61 e0           ldi     r22, 0x01       ; 1
  ba:   0e 94 36 00     call    0x6c    ; 0x6c <extIntSetEnable>

*/

SIGNAL(SIG_INTERRUPT0)
{
}

-- 
Szikra Istvan