Hi,
Here is a C source code which I compiled with GCC 3.4.0 and GCC 4.4.0. GCC
3.4.0 output looks a lot better.
#include <stdio.h>
#include <stdint.h>
#define umul_ppmm(xh, xl, a, b) \
__asm__ ("| Inlined umul_ppmm\n" \
" move.l %0,%/d5\n" \
" move.l %1,%/d4\n" \
" moveq #16,%/d3\n" \
" move.l %0,%/d2\n" \
" mulu %1,%0\n" \
" lsr.l %/d3,%/d4\n" \
" lsr.l %/d3,%/d5\n" \
" mulu %/d4,%/d2\n" \
" mulu %/d5,%1\n" \
" mulu %/d5,%/d4\n" \
" move.l %/d2,%/d5\n" \
" lsr.l %/d3,%/d2\n" \
" add.w %1,%/d5\n" \
" addx.l %/d2,%/d4\n" \
" lsl.l %/d3,%/d5\n" \
" lsr.l %/d3,%1\n" \
" add.l %/d5,%0\n" \
" addx.l %/d4,%1" \
: "=d" ((uint32_t) (xl)), "=d" ((uint32_t) (xh)) \
: "0" ((uint32_t) (a)), "1" ((uint32_t) (b)) \
: "d2", "d3", "d4", "d5")
inline int64_t MUL64(int a, int b)
{
uint32_t au = a;
uint32_t bu = b;
uint32_t resh, resl;
uint64_t res;
umul_ppmm(resh, resl, au, bu);
if (a < 0)
resh -= bu;
if (b < 0)
resh -= au;
res = ((uint64_t)resh << 32) | resl;
return res;
}
GCC 4.4.0 asm output:
#NO_APP
.text
.even
.globl _MUL64
_MUL64:
movem.l #16128,-(sp)
move.l 28(sp),d0
move.l 32(sp),a0
move.l d0,d6
move.l a0,d1
#APP
;# 36 "mul642.c" 1
| Inlined umul_ppmm
move.l d6,d5
move.l d1,d4
moveq #16,d3
move.l d6,d2
mulu d1,d6
lsr.l d3,d4
lsr.l d3,d5
mulu d4,d2
mulu d5,d1
mulu d5,d4
move.l d2,d5
lsr.l d3,d2
add.w d1,d5
addx.l d2,d4
lsl.l d3,d5
lsr.l d3,d1
add.l d5,d6
addx.l d4,d1
#NO_APP
tst.l d0
jlt L6
tst.l a0
jlt L7
L3:
move.l d1,d2
clr.l d3
move.l d2,d0
move.l d3,d1
or.l d6,d1
move.l d0,d6
move.l d1,d7
move.l d7,d1
movem.l (sp)+,#252
rts
L7:
sub.l d0,d1
move.l d1,d2
clr.l d3
move.l d2,d0
move.l d3,d1
or.l d6,d1
move.l d0,d6
move.l d1,d7
move.l d7,d1
movem.l (sp)+,#252
rts
L6:
sub.l a0,d1
tst.l a0
jge L3
jra L7
GCC 3.4.0 asm output:
#NO_APP
.text
.even
.globl _MUL64
_MUL64:
moveml #0x3f00,s...@-
movel sp@(28),d1
movel sp@(32),d0
movel d1,d7
movel d0,d6
#APP
| Inlined umul_ppmm
move.l d7,d5
move.l d6,d4
moveq #16,d3
move.l d7,d2
mulu d6,d7
lsr.l d3,d4
lsr.l d3,d5
mulu d4,d2
mulu d5,d6
mulu d5,d4
move.l d2,d5
lsr.l d3,d2
add.w d6,d5
addx.l d2,d4
lsl.l d3,d5
lsr.l d3,d6
add.l d5,d7
addx.l d4,d6
#NO_APP
tstl d1
jlt L5
tstl d0
jge L3
jra L6
.even
L5:
subl d0,d6
tstl d0
jge L3
.even
L6:
subl d1,d6
.even
L3:
movel d6,d0
clrl d1
orl d7,d1
moveml s...@+,#0xfc
rts
Is it a regression?
Regards
