In the code snippet below, the function mul_8_8 compiles to use
exactly one `mul' instruction on the AVR. The function mul_16_8 calls
mul_8_8 twice. If mul_8_8 is a static inline function and inlined in
mul_16_8, each call generates three `mul' instructions! Why does
inlining mul_8_8 cause each 8x8 multiplication to be promoted to a
16x16 multiplication?
It seems that the inlining mechanism has a real bug if inlining can
cause such a major change in the code generated for a given function.
Cheers,
Shaun
$ avr-gcc --version |head -1
avr-gcc (GCC) 4.1.0
$ cat mul.c
#include <stdint.h>
static uint16_t mul_8_8(uint8_t a, uint8_t b)
{
return a * b;
}
uint32_t mul_16_8(uint16_t a, uint8_t b)
{
uint8_t a0 = a, a1 = a >> 8;
return ((uint32_t)mul_8_8(a1, b) << 8) + mul_8_8(a0, b);
}
$ avr-gcc -c -g -O2 -mmcu=avr4 mul.c
$ avr-objdump -d mul.o
mul.o: file format elf32-avr
Disassembly of section .text:
00000000 <mul_8_8>:
0: 86 9f mul r24, r22
2: c0 01 movw r24, r0
4: 11 24 eor r1, r1
6: 08 95 ret
00000008 <mul_16_8>:
8: bf 92 push r11
a: cf 92 push r12
c: df 92 push r13
e: ef 92 push r14
10: ff 92 push r15
12: 0f 93 push r16
14: 1f 93 push r17
16: 6c 01 movw r12, r24
18: b6 2e mov r11, r22
1a: 8d 2d mov r24, r13
1c: 99 27 eor r25, r25
1e: f0 df rcall .-32 ; 0x0 <mul_8_8>
20: 7c 01 movw r14, r24
22: 00 27 eor r16, r16
24: 11 27 eor r17, r17
26: 10 2f mov r17, r16
28: 0f 2d mov r16, r15
2a: fe 2c mov r15, r14
2c: ee 24 eor r14, r14
2e: 6b 2d mov r22, r11
30: 8c 2d mov r24, r12
32: e6 df rcall .-52 ; 0x0 <mul_8_8>
34: aa 27 eor r26, r26
36: bb 27 eor r27, r27
38: e8 0e add r14, r24
3a: f9 1e adc r15, r25
3c: 0a 1f adc r16, r26
3e: 1b 1f adc r17, r27
40: c8 01 movw r24, r16
42: b7 01 movw r22, r14
44: 1f 91 pop r17
46: 0f 91 pop r16
48: ff 90 pop r15
4a: ef 90 pop r14
4c: df 90 pop r13
4e: cf 90 pop r12
50: bf 90 pop r11
52: 08 95 ret
$ sed -i 's/static/& inline/' mul.c
$ avr-gcc -c -g -O2 -mmcu=avr4 mul.c
$ avr-objdump -d mul.o
mul.o: file format elf32-avr
Disassembly of section .text:
00000000 <mul_16_8>:
0: ac 01 movw r20, r24
2: 26 2f mov r18, r22
4: 33 27 eor r19, r19
6: 89 2f mov r24, r25
8: 99 27 eor r25, r25
a: 82 9f mul r24, r18
c: b0 01 movw r22, r0
e: 83 9f mul r24, r19
10: 70 0d add r23, r0
12: 92 9f mul r25, r18
14: 70 0d add r23, r0
16: 11 24 eor r1, r1
18: 88 27 eor r24, r24
1a: 99 27 eor r25, r25
1c: 98 2f mov r25, r24
1e: 87 2f mov r24, r23
20: 76 2f mov r23, r22
22: 66 27 eor r22, r22
24: 55 27 eor r21, r21
26: f9 01 movw r30, r18
28: e4 9f mul r30, r20
2a: 90 01 movw r18, r0
2c: e5 9f mul r30, r21
2e: 30 0d add r19, r0
30: f4 9f mul r31, r20
32: 30 0d add r19, r0
34: 11 24 eor r1, r1
36: 44 27 eor r20, r20
38: 55 27 eor r21, r21
3a: 62 0f add r22, r18
3c: 73 1f adc r23, r19
3e: 84 1f adc r24, r20
40: 95 1f adc r25, r21
42: 08 95 ret
