https://gcc.gnu.org/bugzilla/show_bug.cgi?id=69489
--- Comment #14 from Julian Taylor <jtaylor.debian at googlemail dot com> ---
I am on x86_64. It actually does vectorize with -mavx but not with -msse2.
The other variant of the loop I posted does vectorize with sse2.
$ gcc --version
gcc (GCC) 7.0.0 20160421 (experimental)
Copyright (C) 2016 Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
$ cat test.c
double
yule_bool_distance_char2(const char *u, const char *v, long n)
{
long i;
long ntt = 0l, nff = 0l, nft = 0l, ntf = 0l;
for (i = 0l; i < n; i++) {
ntf += (u[i] && !v[i]);
nft += (!u[i] && v[i]);
}
return (2.0 * ntf * nft);
}
$ gcc -O2 -ftree-vectorize test.c -c
#same with O3
$ objdump -d test.o
test.o: file format elf64-x86-64
Disassembly of section .text:
0000000000000000 <yule_bool_distance_char2>:
0: 48 85 d2 test %rdx,%rdx
3: 7e 69 jle 6e <yule_bool_distance_char2+0x6e>
5: 55 push %rbp
6: 53 push %rbx
7: 45 31 d2 xor %r10d,%r10d
a: 45 31 db xor %r11d,%r11d
d: 31 c0 xor %eax,%eax
f: 31 ed xor %ebp,%ebp
11: 0f 1f 80 00 00 00 00 nopl 0x0(%rax)
18: 44 0f b6 0c 06 movzbl (%rsi,%rax,1),%r9d
1d: 44 0f b6 04 07 movzbl (%rdi,%rax,1),%r8d
22: 45 84 c9 test %r9b,%r9b
25: 0f 94 c3 sete %bl
28: 31 c9 xor %ecx,%ecx
2a: 45 84 c0 test %r8b,%r8b
2d: 0f 95 c1 setne %cl
30: 48 21 d9 and %rbx,%rcx
33: 49 01 ca add %rcx,%r10
36: 31 c9 xor %ecx,%ecx
38: 45 84 c9 test %r9b,%r9b
3b: 0f 95 c1 setne %cl
3e: 45 84 c0 test %r8b,%r8b
41: 48 0f 45 cd cmovne %rbp,%rcx
45: 48 83 c0 01 add $0x1,%rax
49: 49 01 cb add %rcx,%r11
4c: 48 39 c2 cmp %rax,%rdx
4f: 75 c7 jne 18 <yule_bool_distance_char2+0x18>
51: 66 0f ef c0 pxor %xmm0,%xmm0
55: 66 0f ef c9 pxor %xmm1,%xmm1
59: 5b pop %rbx
5a: f2 49 0f 2a c2 cvtsi2sd %r10,%xmm0
5f: f2 49 0f 2a cb cvtsi2sd %r11,%xmm1
64: 5d pop %rbp
65: f2 0f 58 c0 addsd %xmm0,%xmm0
69: f2 0f 59 c1 mulsd %xmm1,%xmm0
6d: c3 retq
6e: 66 0f ef c0 pxor %xmm0,%xmm0
72: c3 retq
