http://gcc.gnu.org/bugzilla/show_bug.cgi?id=47657
Summary: missed vectorization
Product: gcc
Version: 4.6.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
AssignedTo: unassig...@gcc.gnu.org
ReportedBy: joost.vandevond...@pci.uzh.ch
the following is not vectorized with gfortran (4.6 / 4.5)
gfortran -O3 -ffast-math -ftree-vectorizer-verbose=6 -S -march=native
( -march=amdfam10 -mcx16 -msahf -mpopcnt -mabm )
SUBROUTINE smm_dnn_8_8_8_4_1_2_1(A,B,C)
REAL(KIND=8) :: C(8,8), B(8,8), A(8,8)
INTEGER ::i,j,l
DO j= 1 , 8 , 2
DO l= 1 , 8 , 1
DO i= 1 , 8 , 1
C(i+0,j+0)=C(i+0,j+0)+A(i+0,l+0)*B(l+0,j+0)
C(i+0,j+1)=C(i+0,j+1)+A(i+0,l+0)*B(l+0,j+1)
ENDDO
ENDDO
ENDDO
END SUBROUTINE
while the cray ftn compiler does, yielding about twice the speed.
reference asm:
0000000000000000 <smm_dnn_8_8_8_4_1_2_1_>:
0: 53 push %rbx
1: 48 89 7c 24 f8 mov %rdi,-0x8(%rsp)
6: 48 89 74 24 f0 mov %rsi,-0x10(%rsp)
b: 48 89 54 24 e8 mov %rdx,-0x18(%rsp)
10: 31 c0 xor %eax,%eax
12: 48 89 d1 mov %rdx,%rcx
15: 49 89 c0 mov %rax,%r8
18: 49 89 c1 mov %rax,%r9
1b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1)
20: 66 0f 10 04 02 movupd (%rdx,%rax,1),%xmm0
25: 66 0f 10 4c 02 40 movupd 0x40(%rdx,%rax,1),%xmm1
2b: 66 0f 10 54 02 10 movupd 0x10(%rdx,%rax,1),%xmm2
31: 66 0f 10 5c 02 50 movupd 0x50(%rdx,%rax,1),%xmm3
37: 66 0f 10 64 02 20 movupd 0x20(%rdx,%rax,1),%xmm4
3d: 66 0f 10 6c 02 60 movupd 0x60(%rdx,%rax,1),%xmm5
43: 66 0f 10 74 02 30 movupd 0x30(%rdx,%rax,1),%xmm6
49: 66 0f 10 7c 02 70 movupd 0x70(%rdx,%rax,1),%xmm7
4f: 45 31 d2 xor %r10d,%r10d
52: 4d 89 d3 mov %r10,%r11
55: 66 66 2e 0f 1f 84 00 nopw %cs:0x0(%rax,%rax,1)
5c: 00 00 00 00
60: 66 46 0f 10 44 1f 30 movupd 0x30(%rdi,%r11,1),%xmm8
67: 4b 8d 1c 02 lea (%r10,%r8,1),%rbx
6b: f2 44 0f 12 4c de 40 movddup 0x40(%rsi,%rbx,8),%xmm9
72: 66 45 0f 28 d1 movapd %xmm9,%xmm10
77: 66 45 0f 59 d0 mulpd %xmm8,%xmm10
7c: 66 41 0f 58 fa addpd %xmm10,%xmm7
81: f2 44 0f 12 14 de movddup (%rsi,%rbx,8),%xmm10
87: 66 45 0f 59 c2 mulpd %xmm10,%xmm8
8c: 66 41 0f 58 f0 addpd %xmm8,%xmm6
91: 66 46 0f 10 44 1f 20 movupd 0x20(%rdi,%r11,1),%xmm8
98: 66 45 0f 28 d9 movapd %xmm9,%xmm11
9d: 66 45 0f 59 d8 mulpd %xmm8,%xmm11
a2: 66 41 0f 58 eb addpd %xmm11,%xmm5
a7: 66 45 0f 59 c2 mulpd %xmm10,%xmm8
ac: 66 41 0f 58 e0 addpd %xmm8,%xmm4
b1: 66 46 0f 10 44 1f 10 movupd 0x10(%rdi,%r11,1),%xmm8
b8: 66 45 0f 28 d9 movapd %xmm9,%xmm11
bd: 66 45 0f 59 d8 mulpd %xmm8,%xmm11
c2: 66 41 0f 58 db addpd %xmm11,%xmm3
c7: 66 45 0f 59 c2 mulpd %xmm10,%xmm8
cc: 66 41 0f 58 d0 addpd %xmm8,%xmm2
d1: 66 46 0f 10 04 1f movupd (%rdi,%r11,1),%xmm8
d7: 66 45 0f 59 c8 mulpd %xmm8,%xmm9
dc: 66 41 0f 58 c9 addpd %xmm9,%xmm1
e1: 66 45 0f 59 d0 mulpd %xmm8,%xmm10
e6: 66 41 0f 58 c2 addpd %xmm10,%xmm0
eb: 49 83 c3 40 add $0x40,%r11
ef: 49 ff c2 inc %r10
f2: 49 83 fa 08 cmp $0x8,%r10
f6: 0f 8c 64 ff ff ff jl 60 <smm_dnn_8_8_8_4_1_2_1_+0x60>
fc: f2 0f 11 7c 01 70 movsd %xmm7,0x70(%rcx,%rax,1)
102: 66 0f 17 7c 01 78 movhpd %xmm7,0x78(%rcx,%rax,1)
108: f2 0f 11 74 02 30 movsd %xmm6,0x30(%rdx,%rax,1)
10e: 66 0f 17 74 02 38 movhpd %xmm6,0x38(%rdx,%rax,1)
114: f2 0f 11 6c 02 60 movsd %xmm5,0x60(%rdx,%rax,1)
11a: 66 0f 17 6c 02 68 movhpd %xmm5,0x68(%rdx,%rax,1)
120: f2 0f 11 64 02 20 movsd %xmm4,0x20(%rdx,%rax,1)
126: 66 0f 17 64 02 28 movhpd %xmm4,0x28(%rdx,%rax,1)
12c: f2 0f 11 5c 02 50 movsd %xmm3,0x50(%rdx,%rax,1)
132: 66 0f 17 5c 02 58 movhpd %xmm3,0x58(%rdx,%rax,1)
138: f2 0f 11 54 02 10 movsd %xmm2,0x10(%rdx,%rax,1)
13e: 66 0f 17 54 02 18 movhpd %xmm2,0x18(%rdx,%rax,1)
144: f2 0f 11 4c 02 40 movsd %xmm1,0x40(%rdx,%rax,1)
14a: 66 0f 17 4c 02 48 movhpd %xmm1,0x48(%rdx,%rax,1)
150: f2 0f 11 04 02 movsd %xmm0,(%rdx,%rax,1)
155: 66 0f 17 44 02 08 movhpd %xmm0,0x8(%rdx,%rax,1)
15b: 49 83 c0 10 add $0x10,%r8
15f: 48 83 e8 80 sub $0xffffffffffffff80,%rax
163: 49 ff c1 inc %r9
166: 49 83 f9 04 cmp $0x4,%r9
16a: 0f 8c b0 fe ff ff jl 20 <smm_dnn_8_8_8_4_1_2_1_+0x20>
170: 5b pop %rbx
171: c3 retq
172: 66 66 66 66 66 2e 0f nopw %cs:0x0(%rax,%rax,1)
179: 1f 84 00 00 00 00 00
