https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86029
Tavian Barnes <tavianator at gmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |tavianator at gmail dot com
--- Comment #1 from Tavian Barnes <tavianator at gmail dot com> ---
Maybe a dupe of https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70291? In the -O3
version, __mulsc3() dominates the profile.
│ for(int i=0; i<=decimate_taps_length; i++) decim +=
samplebuf[i] * decimate_taps[i];
0.20 │430:┌─→vmovss 0x4(%r13,%rbx,1),%xmm1
3.63 │ │ vmovss 0x0(%r13,%rbx,1),%xmm0
12.35 │ │ vmovss 0x4(%r12,%rbx,1),%xmm3
0.31 │ │ vmovss (%r12,%rbx,1),%xmm2
0.02 │ │ add $0x8,%rbx
36.48 │ │→ callq __mulsc3
0.01 │ │ vmovss -0x78(%rbp),%xmm6
0.00 │ │ vmovss -0x80(%rbp),%xmm4
23.70 │ │ vmovq %xmm0,-0x68(%rbp)
14.25 │ │ vaddss -0x68(%rbp),%xmm6,%xmm5
1.54 │ │ vaddss -0x64(%rbp),%xmm4,%xmm7
0.48 │ │ vmovss %xmm5,-0x78(%rbp)
5.92 │ │ vmovss %xmm7,-0x80(%rbp)
│ ├──cmp $0x2590,%rbx
0.01 │ └──jne 430
At -Ofast,
│ for(int i=0; i<=decimate_taps_length; i++) decim +=
samplebuf[i] * decimate_taps[i];
9.36 │5e0: vpermilps $0xf5,(%r12,%rax,1),%ymm0
15.56 │ vpermilps $0xa0,(%r12,%rax,1),%ymm1
11.24 │ vmulps (%rbx,%rax,1),%ymm0,%ymm0
17.55 │ vpermilps $0xb1,(%rbx,%rax,1),%ymm4
3.31 │ add $0x20,%rax
2.11 │ vmovaps %ymm1,%ymm3
6.62 │ vfmadd132ps %ymm4,%ymm0,%ymm3
3.79 │ vfmsub231ps %ymm4,%ymm1,%ymm0
2.91 │ vblendps $0xaa,%ymm0,%ymm3,%ymm0
10.75 │ vaddps %ymm0,%ymm6,%ymm6
│ cmp $0x2580,%rax
5.59 │ ↑ jne 5e0
0.01 │ vmovss 0x258c(%rbx),%xmm0
0.01 │ vmovss -0x70(%rbp),%xmm7
0.01 │ vmovss %xmm5,-0xd0(%rbp)
0.05 │ vextractf128 $0x1,%ymm6,%xmm3
0.01 │ vmovss 0x2588(%rbx),%xmm8
0.03 │ vshufps $0xff,%xmm3,%xmm3,%xmm13
