Re: slowdown with -std=gnu18 with respect to -std=c99

["Stéphane Glondu" <stephane.glondu@inria.fr>]

Le 03/05/2022 à 11:09, Alexander Monakov a écrit :
>> Does anyone have a clue?
> 
> I can reproduce a difference, but in my case it's simply because in -std=gnuXX
> mode (as opposed to -std=cXX) GCC enables FMA contraction, enabling the last few
> steps in the benchmarked function to use fma instead of separate mul/add
> instructions.
> 
> (regarding __builtin_expect, it also makes a small difference in my case,
> it seems GCC generates some redundant code without it, but the difference is
> 10x smaller than what presence/absence of FMA gives)
> 
> I think you might be able to figure it out on your end if you run both variants
> under 'perf stat', note how cycle count and instruction counts change, and then
> look at disassembly to see what changed. You can use 'perf record' and 'perf
> report' to easily see the hot code path; if you do that, I'd recommend to run
> it with the same sampling period in both cases, e.g. like this:
> 
>     perf record -e instructions:P -c 500000 ./perf ...
I did that. The hot code path corresponds to (from exp10f.c):

    double a = iln2h*z, ia = __builtin_floor(a), h = (a - ia) + iln2l*z;
    long i = ia, j = i&0xf, e = i - j;
    e >>= 4;
    double s = tb[j];
    b64u64_u su = {.u = (e + 0x3fful)<<52};
    s *= su.f;
    double h2 = h*h;
    double c0 = c[0] + h*c[1];
    double c2 = c[2] + h*c[3];
    double c4 = c[4] + h*c[5];
    c0 += h2*(c2 + h2*c4);
    double w = s*h;
    return s + w*c0;

With -std=c99, where the overall performance is 22 cycles, I get:

  4,03 │ 3a:   vcvtss2sd  -0x4(%rsp),%xmm0,%xmm0
  0,01 │       vmulsd     ir.4+0x38,%xmm0,%xmm1
       │       vmulsd     ir.4+0x40,%xmm0,%xmm0
  0,01 │       lea        tb.1,%rdx
  3,06 │       vroundsd   $0x9,%xmm1,%xmm1,%xmm2
  0,03 │       vsubsd     %xmm2,%xmm1,%xmm1
 10,42 │       vcvttsd2si %xmm2,%rax
  0,01 │       vaddsd     %xmm0,%xmm1,%xmm1
       │       mov        %rax,%rcx
  0,02 │       vmulsd     ir.4+0x58,%xmm1,%xmm0
  0,38 │       vmulsd     %xmm1,%xmm1,%xmm5
  0,00 │       vmulsd     ir.4+0x68,%xmm1,%xmm4
       │       sar        $0x4,%rax
  0,00 │       add        $0x3ff,%rax
  1,17 │       vaddsd     ir.4+0x60,%xmm0,%xmm0
       │       shl        $0x34,%rax
  0,02 │       vaddsd     ir.4+0x70,%xmm4,%xmm4
  0,10 │       vmulsd     %xmm5,%xmm0,%xmm0
  0,85 │       vmulsd     ir.4+0x48,%xmm1,%xmm3
  0,00 │       and        $0xf,%ecx
       │       vmovq      %rax,%xmm6
  1,20 │       vmulsd     (%rdx,%rcx,8),%xmm6,%xmm2
  0,65 │       vaddsd     %xmm4,%xmm0,%xmm0
  0,00 │       vaddsd     ir.4+0x50,%xmm3,%xmm3
  3,49 │       vmulsd     %xmm5,%xmm0,%xmm0
 15,59 │       vmulsd     %xmm2,%xmm1,%xmm1
  4,61 │       vaddsd     %xmm3,%xmm0,%xmm0
 10,24 │       vmulsd     %xmm1,%xmm0,%xmm0
 11,31 │       vaddsd     %xmm2,%xmm0,%xmm0
 23,21 │       vcvtsd2ss  %xmm0,%xmm0,%xmm0
  0,00 │     ← ret

With -std=gnu18, where the overall performance is 36 cycles, I get:

  0,02 │ 3a:   vcvtss2sd   -0x4(%rsp),%xmm1,%xmm1
  0,01 │       vmulsd      ir.4+0x40,%xmm1,%xmm0
       │       vmovsd      ir.4+0x60,%xmm5
       │       vmovsd      ir.4+0x50,%xmm4
       │       lea         tb.1,%rdx
  0,13 │       vroundsd    $0x9,%xmm0,%xmm0,%xmm2
  0,83 │       vsubsd      %xmm2,%xmm0,%xmm0
 28,99 │       vcvttsd2si  %xmm2,%rax
 63,49 │       vfmadd132sd 0x961(%rip),%xmm0,%xmm1
       │       vmovsd      ir.4+0x70,%xmm0
       │       mov         %rax,%rcx
       │       sar         $0x4,%rax
  2,73 │       add         $0x3ff,%rax
  1,99 │       vmulsd      %xmm1,%xmm1,%xmm3
  0,00 │       vfmadd213sd 0x95f(%rip),%xmm1,%xmm5
  0,00 │       vfmadd213sd 0x966(%rip),%xmm1,%xmm0
       │       shl         $0x34,%rax
       │       and         $0xf,%ecx
       │       vmovq       %rax,%xmm6
  0,17 │       vmulsd      (%rdx,%rcx,8),%xmm6,%xmm2
       │       vfmadd213sd 0x92c(%rip),%xmm1,%xmm4
  0,04 │       vfmadd132sd %xmm3,%xmm5,%xmm0
  0,64 │       vmulsd      %xmm2,%xmm1,%xmm1
  0,01 │       vfmadd132sd %xmm3,%xmm4,%xmm0
  0,46 │       vfmadd132sd %xmm1,%xmm2,%xmm0
  0,27 │       vcvtsd2ss   %xmm0,%xmm0,%xmm0
       │     ← ret

The distribution of time is very different in both cases: in the first
case, most of the time is spent at the end (computing w and return value
I suppose) whereas in the second case, most of the time is spent in the
first multiply-and-add (computing h). I do not understand this change of
behaviour.


Cheers,

-- 
Stéphane