[Bug target/57952] AVX/AVX2 no ymm registers used in a trivial reduction

[vincenzo.innocente at cern dot ch]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=57952

--- Comment #1 from vincenzo Innocente <vincenzo.innocente at cern dot ch> ---
I modified a bit the benchmark adding timing
and the new version now vectorize YMM with avx2, still not with old avx
if I remove the call to rdtsc(); it does not use YMM anymore
-fno-tree-pre does not help

cat polyAVX.cpp 
//template<typename T>
typedef float T;
inline T polyHorner(T y) {
  return  T(0x2.p0) + y * (T(0x2.p0) + y * (T(0x1.p0) + y * (T(0x5.55523p-4) +
y * (T(0x1.5554dcp-4) + y * (T(0x4.48f41p-8) + y * T(0xb.6ad4p-12)))))) ;
}

#include <x86intrin.h>
#include<iostream>

volatile unsigned long long rdtsc() {
    unsigned int taux=0;
    return __rdtscp(&taux);
  }

int main() {


  long long t=0;

    bool ret=true;
    float s =0;
    for (int k=0; k!=100; ++k) {
      float c =   1.f/10000000.f;
      t -=rdtsc();
      for (int i=1; i<10000001; ++i) s+= polyHorner((float(i)+float(k))*c);
      t    +=rdtsc();
    }
    ret &= s!=0;

  std::cout << t <<std::endl;

  return ret ? 0 : -1;


}
[innocent@vinavx2 vectorize]$ c++ -Ofast -S polyAVX.cpp -march=core-avx2 ; grep
-c "ymm" polyAVX.s
28
[innocent@vinavx2 vectorize]$ c++ -Ofast -S polyAVX.cpp -march=corei7-avx ;
grep -c "ymm" polyAVX.s
0