[Bug tree-optimization/17863] [4.0 Regression] threefold performance loss, not inlining as much

[pinskia at gcc dot gnu dot org]

------- Additional Comments From pinskia at gcc dot gnu dot org  2004-12-24 
20:36 -------
Reduced testcase:
const int LMAX = 4;
const int LMAX41 = 4*LMAX+1;
const int LMAX12 = (LMAX+1)*(LMAX+2)/2;
template<int n>
inline double accu1( const double* p1, const double* p2 )
{
     double d = *p1 * *p2;
     return d + accu1<n-1>( ++p1, ++p2 );
}
template <> inline double accu1<0>( const double* p1, const double* p2 )
{
    return p1[0] * p2[0]; 
}
template <int ny, int nz>
inline double accu2( const double* py, const double* pz, const double* h )
{
    const double d = accu1<nz>( pz, h ) * *py;
    if( ny == 0 ) return d;
    return d + accu2<(ny ? ny-1 : -1), (ny ? nz : -1 )>( ++py, pz, ++h );
}
template<>
inline double accu2<-1, -1>( const double* , const double* , const double* )
{
    return 0.0;
}
template <int ny, int nz>
inline double accu( const double* py, const double* pz, const double* h )
{
    if( ny == 0 ) return accu1<nz>( pz, h );
    else  if( nz == 0 ) return accu1<ny>( py, h );
    else if( nz >= ny ) return accu2<ny, nz>( py, pz, h );
    else return accu2<nz, ny>( pz, py, h );
}
template <>
inline double accu<0,0>( const double* , const double* , const double* h )
{
    return *h;
}
#define SWYZ( Y, Z ) ((Y+Z) * (Y+Z+1) / 2+Z)
#define CASA( Y, Z ) case SWYZ( Y, Z ):         \
        *ap1 = accu<Y, Z>( py, pz, dxb );      \
    if( z1 == 0 ) break;                        \
    ++ap1;                                      \
    z1--; py += LMAX41; pz -= LMAX41;
#define CAS( Y, Z ) case SWYZ( Y, Z ): *ap1 = accu<Y, Z>( py, pz, dxb ); break
#define CAS1( Y ) CASA( Y, 1 );  CAS( Y+1, 0 );
#define CAS2( Y ) CASA( Y, 2 ); CAS1( Y+1 );
#define CAS3( Y ) CASA( Y, 3 ); CAS2( Y+1 );
#define CAS4( Y ) CASA( Y, 4 ); CAS3( Y+1 );

double f(const double *py, const double *pz, double *dxb, double *ap1, int 
mh_z1234, unsigned int 
z1)
{
  switch( mh_z1234 )
 {
    CAS( 0, 0 );
    CAS1(0);
    CAS2(0);
    CAS3(0);
    CAS4(0);
  }
}


When we do -O3 or -O2, we don't inline accu1<1> into accu1<2> at all, 
why?????????

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
   Last reconfirmed|2004-10-06 18:40:54         |2004-12-24 20:36:17
               date|                            |


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=17863