[Bug c/25500] REGREGRESSION: SSE2 vectorized code is many times slower on 4.x.x than on 3.4.4

[yuri at tsoft dot com]

------- Comment #1 from yuri at tsoft dot com  2005-12-20 05:34 -------
actually it's the defect in this case: result is not used.
But runtimes are very different in any case.
44.9s on 4.x.x vs. 0m2.371s on 3.4.4

--- begin corrected testcase -----------------------------------
#include <iostream>
using namespace std;

typedef float __v2df __attribute__ ((__vector_size__ (16)));
typedef __v2df __m128;

static __inline __m128 _mm_sub_pd (__m128 __A, __m128 __B) { return
(__m128)__builtin_ia32_subps ((__v2df)__A, (__v2df)__B); }
static __inline __m128 _mm_add_pd (__m128 __A, __m128 __B) { return
(__m128)__builtin_ia32_addps ((__v2df)__A, (__v2df)__B); }
static __inline __m128 _mm_setr_ps (float __Z, float __Y, float __X, float __W)
{ return __extension__ (__m128)(__v2df){ __Z, __Y, __X, __W }; }

struct FF {
  __m128 d;

  __inline FF() { }
  __inline FF(__m128 new_d) : d(new_d) { }
  __inline FF(float f) : d(_mm_setr_ps(f, f, f, f)) { }

  __inline FF operator+(FF other) { return (FF(_mm_add_pd(d,other.d))); }
  __inline FF operator-(FF other) { return (FF(_mm_sub_pd(d,other.d))); }
};

float f[1024*1024];

    union U {
      __m128 m;
      float f[4];
    };

int main() {
  int i;

  FF gtotal(0.f);
  for (i = 0; i < 1024*1024; i++) { f[i] = 1.f/(1024*1024 + 10 - i); }

  FF total(0.f);

  for (int rpt = 0; rpt < 1000; rpt++) {
    FF p1(0.f), p2(0.), c;

    __m128 *pf = (__m128*)f;
    for (i = 0; i < 1024*1024/4; i++) {
      FF c(*pf++);

      total = total + c - p2 + p1;

      p1 = p2;
      p2 = c;
    }
    gtotal = gtotal + total;
  }

  U u;
  u.m = gtotal.d;

  cout << (u.f[0]) << endl;
}
--- end corrected testcase -------------------------------------


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=25500