Given the simple test program
# define __kernel_cttz(x) __builtin_ctzl(x)
unsigned long __ffs(unsigned long word)
{
/* Whee. EV67 can calculate it directly. */
return __kernel_cttz(word);
}
long foo(const unsigned long *b)
{
unsigned long b0, b1, ofs, tmp;
b0 = b[0];
b1 = b[1];
ofs = (b0 ? 0 : 64);
tmp = (b0 ? b0 : b1);
tmp = __ffs(tmp);
return tmp + ofs;
}
gcc 4.3.4, 4.4.3, and 4.5.0 all produce very bad code at -O1. gcc-4.4.3
produces bad code at other levels as well, but that's for a different bug
report. I guess we really only care about 4.5 at this point.
# gcc-4.3.4 -Os -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
0000000000000008 <foo>:
8: 00 00 10 a4 ldq v0,0(a0)
c: 08 00 30 a4 ldq t0,8(a0)
10: c1 04 00 44 cmovne v0,v0,t0
14: a0 15 00 40 cmpeq v0,0,v0
18: 20 d7 00 48 sll v0,0x6,v0
1c: 61 06 e1 73 cttz t0,t0
20: 00 04 01 40 addq v0,t0,v0
24: 01 80 fa 6b ret
# gcc-4.3.4 -O1 -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
0000000000000008 <foo>:
8: 00 00 bb 27 ldah gp,0(t12)
c: 00 00 bd 23 lda gp,0(gp)
10: f0 ff de 23 lda sp,-16(sp)
14: 00 00 5e b7 stq ra,0(sp)
18: 08 00 3e b5 stq s0,8(sp)
1c: 01 04 f0 47 mov a0,t0
20: 00 00 10 a6 ldq a0,0(a0)
24: 08 00 21 a4 ldq t0,8(t0)
28: a9 15 00 42 cmpeq a0,0,s0
2c: 29 d7 20 49 sll s0,0x6,s0
30: 90 04 01 46 cmoveq a0,t0,a0
34: 00 00 40 d3 bsr ra,38 <foo+0x30>
38: 00 04 20 41 addq s0,v0,v0
3c: 00 00 5e a7 ldq ra,0(sp)
40: 08 00 3e a5 ldq s0,8(sp)
44: 10 00 de 23 lda sp,16(sp)
48: 01 80 fa 6b ret
# gcc-4.3.4 -O2 -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
8: 1f 04 ff 47 nop
c: 00 00 fe 2f unop
0000000000000010 <foo>:
10: 00 00 10 a4 ldq v0,0(a0)
14: 08 00 30 a4 ldq t0,8(a0)
18: c1 04 00 44 cmovne v0,v0,t0
1c: a0 15 00 40 cmpeq v0,0,v0
20: 20 d7 00 48 sll v0,0x6,v0
24: 61 06 e1 73 cttz t0,t0
28: 00 04 01 40 addq v0,t0,v0
2c: 01 80 fa 6b ret
# gcc-4.3.4 -O3 -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
8: 1f 04 ff 47 nop
c: 00 00 fe 2f unop
0000000000000010 <foo>:
10: 00 00 10 a4 ldq v0,0(a0)
14: 08 00 30 a4 ldq t0,8(a0)
18: c1 04 00 44 cmovne v0,v0,t0
1c: a0 15 00 40 cmpeq v0,0,v0
20: 20 d7 00 48 sll v0,0x6,v0
24: 61 06 e1 73 cttz t0,t0
28: 00 04 01 40 addq v0,t0,v0
2c: 01 80 fa 6b ret
# gcc-4.4.3 -Os -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
0000000000000008 <foo>:
8: 00 00 bb 27 ldah gp,0(t12)
c: 00 00 bd 23 lda gp,0(gp)
10: f0 ff de 23 lda sp,-16(sp)
14: 08 00 30 a4 ldq t0,8(a0)
18: 08 00 3e b5 stq s0,8(sp)
1c: 00 00 30 a5 ldq s0,0(a0)
20: 00 00 5e b7 stq ra,0(sp)
24: 10 04 e1 47 mov t0,a0
28: d0 04 29 45 cmovne s0,s0,a0
2c: a9 15 20 41 cmpeq s0,0,s0
30: 29 d7 20 49 sll s0,0x6,s0
34: 00 00 40 d3 bsr ra,38 <foo+0x30>
38: 00 04 20 41 addq s0,v0,v0
3c: 00 00 5e a7 ldq ra,0(sp)
40: 08 00 3e a5 ldq s0,8(sp)
44: 10 00 de 23 lda sp,16(sp)
48: 01 80 fa 6b ret
# gcc-4.4.3 -O1 -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
0000000000000008 <foo>:
8: 00 00 bb 27 ldah gp,0(t12)
c: 00 00 bd 23 lda gp,0(gp)
10: f0 ff de 23 lda sp,-16(sp)
14: 00 00 5e b7 stq ra,0(sp)
18: 08 00 3e b5 stq s0,8(sp)
1c: 00 00 30 a4 ldq t0,0(a0)
20: 08 00 10 a6 ldq a0,8(a0)
24: a9 15 20 40 cmpeq t0,0,s0
28: 29 d7 20 49 sll s0,0x6,s0
2c: d0 04 21 44 cmovne t0,t0,a0
30: 00 00 40 d3 bsr ra,34 <foo+0x2c>
34: 00 04 20 41 addq s0,v0,v0
38: 00 00 5e a7 ldq ra,0(sp)
3c: 08 00 3e a5 ldq s0,8(sp)
40: 10 00 de 23 lda sp,16(sp)
44: 01 80 fa 6b ret
# gcc-4.4.3 -O2 -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
8: 1f 04 ff 47 nop
c: 00 00 fe 2f unop
0000000000000010 <foo>:
10: 00 00 bb 27 ldah gp,0(t12)
14: 00 00 bd 23 lda gp,0(gp)
18: f0 ff de 23 lda sp,-16(sp)
1c: 08 00 30 a4 ldq t0,8(a0)
20: 08 00 3e b5 stq s0,8(sp)
24: 00 00 30 a5 ldq s0,0(a0)
28: 00 00 5e b7 stq ra,0(sp)
2c: 10 04 e1 47 mov t0,a0
30: d0 04 29 45 cmovne s0,s0,a0
34: a9 15 20 41 cmpeq s0,0,s0
38: 29 d7 20 49 sll s0,0x6,s0
3c: 00 00 40 d3 bsr ra,40 <foo+0x30>
40: 00 04 20 41 addq s0,v0,v0
44: 00 00 5e a7 ldq ra,0(sp)
48: 08 00 3e a5 ldq s0,8(sp)
4c: 10 00 de 23 lda sp,16(sp)
50: 01 80 fa 6b ret
54: 00 00 fe 2f unop
58: 1f 04 ff 47 nop
5c: 00 00 fe 2f unop
# gcc-4.4.3 -O3 -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
8: 1f 04 ff 47 nop
c: 00 00 fe 2f unop
0000000000000010 <foo>:
10: 00 00 30 a4 ldq t0,0(a0)
14: 08 00 10 a4 ldq v0,8(a0)
18: c0 04 21 44 cmovne t0,t0,v0
1c: a1 15 20 40 cmpeq t0,0,t0
20: 21 d7 20 48 sll t0,0x6,t0
24: 60 06 e0 73 cttz v0,v0
28: 00 04 01 40 addq v0,t0,v0
2c: 01 80 fa 6b ret
# gcc-4.5.0 -Os -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
0000000000000008 <foo>:
8: 00 00 30 a4 ldq t0,0(a0)
c: 08 00 10 a4 ldq v0,8(a0)
10: c0 04 21 44 cmovne t0,t0,v0
14: a1 15 20 40 cmpeq t0,0,t0
18: 21 d7 20 48 sll t0,0x6,t0
1c: 60 06 e0 73 cttz v0,v0
20: 00 04 01 40 addq v0,t0,v0
24: 01 80 fa 6b ret
# gcc-4.5.0 -O1 -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
0000000000000008 <foo>:
8: 00 00 bb 27 ldah gp,0(t12)
c: 00 00 bd 23 lda gp,0(gp)
10: f0 ff de 23 lda sp,-16(sp)
14: 00 00 5e b7 stq ra,0(sp)
18: 08 00 3e b5 stq s0,8(sp)
1c: 00 00 30 a4 ldq t0,0(a0)
20: 08 00 10 a6 ldq a0,8(a0)
24: a9 15 20 40 cmpeq t0,0,s0
28: 29 d7 20 49 sll s0,0x6,s0
2c: d0 04 21 44 cmovne t0,t0,a0
30: 00 00 40 d3 bsr ra,34 <foo+0x2c>
34: 00 04 20 41 addq s0,v0,v0
38: 00 00 5e a7 ldq ra,0(sp)
3c: 08 00 3e a5 ldq s0,8(sp)
40: 10 00 de 23 lda sp,16(sp)
44: 01 80 fa 6b ret
# gcc-4.5.0 -O2 -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
8: 1f 04 ff 47 nop
c: 00 00 fe 2f unop
0000000000000010 <foo>:
10: 00 00 30 a4 ldq t0,0(a0)
14: 08 00 10 a4 ldq v0,8(a0)
18: c0 04 21 44 cmovne t0,t0,v0
1c: a1 15 20 40 cmpeq t0,0,t0
20: 21 d7 20 48 sll t0,0x6,t0
24: 60 06 e0 73 cttz v0,v0
28: 00 04 01 40 addq v0,t0,v0
2c: 01 80 fa 6b ret
# gcc-4.5.0 -O3 -mcpu=ev67 -c z.c && objdump -d z.o
z.o: file format elf64-alpha
Disassembly of section .text:
0000000000000000 <__ffs>:
0: 60 06 f0 73 cttz a0,v0
4: 01 80 fa 6b ret
8: 1f 04 ff 47 nop
c: 00 00 fe 2f unop
0000000000000010 <foo>:
10: 00 00 30 a4 ldq t0,0(a0)
14: 08 00 10 a4 ldq v0,8(a0)
18: c0 04 21 44 cmovne t0,t0,v0
1c: a1 15 20 40 cmpeq t0,0,t0
20: 21 d7 20 48 sll t0,0x6,t0
24: 60 06 e0 73 cttz v0,v0
28: 00 04 01 40 addq v0,t0,v0
2c: 01 80 fa 6b ret
4.3.4 -Os: good
4.3.4 -O1: bad
4.3.4 -O2: good
4.3.4 -O3: good
4.4.3 -Os: bad
4.4.3 -O1: bad
4.4.3 -O2: bad
4.4.3 -O3: good
4.5.0 -Os: good
4.5.0 -O1: bad
4.5.0 -O2: good
4.5.0 -O3: good
--
Summary: gcc produces bad code at -O1
Product: gcc
Version: 4.5.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: rtl-optimization
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: mattst88 at gmail dot com
GCC build triplet: alpha-unknown-linux-gnu
GCC host triplet: alpha-unknown-linux-gnu
GCC target triplet: alpha-unknown-linux-gnu
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=44123
