[Bug tree-optimization/46284] Lack of proper optimization for certain SSE operations, and weird behavior with similar source codes

[pinskia at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46284

Andrew Pinski <pinskia at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Severity|normal                      |enhancement

--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> 2010-11-02 
23:56:05 UTC ---
Testcase copied here:
/* 
 * File:   Common/Range.h
 * Author: ryden
 * Based on code found at:
http://gcc.gnu.org/ml/gcc-patches/2010-07/msg01854.html
 *
 */

#ifndef RANGE_H
#define    RANGE_H

template < int iMin, int iMax >
struct Range
{
    struct iterator
    {
        iterator ( int val ) : v ( val ) {}

        iterator operator++ () { iterator it ( v ); ++v; return it; }
        iterator& operator++ (int) { ++v; return *this; }
        bool operator!= ( const iterator& other ) const { return other.v != v;
}
        int operator* () const { return v; }

    private:
        int v;
    };

    iterator begin () const { return iterator ( iMin ); }
    iterator end () const { return iterator ( iMax + 1 ); }
};

#define range(min,max) Range<min,max>()
#define until(max) Range<0,(max)-1>()

#endif    /* RANGE_H */



/* 
 * File:   Common/Vector.h
 * Author: ryden
 *
 */

#ifndef VECTOR_H
#define    VECTOR_H

#include <string>
#include <sstream>

template < typename T, unsigned int uiNumComponents >
struct VectorBase
{
    typedef T __attribute__ ((vector_size(uiNumComponents*sizeof(T))))
vectorType;
    union
    {
        T           v [ uiNumComponents ];
        vectorType  vec;
    };
};

template < typename T, unsigned int uiNumComponents >
class Vector : protected VectorBase < T, uiNumComponents >
{
public:
    Vector ( )
    {
        for ( auto i : until(uiNumComponents) )
        {
            Vector::v[i] = 0;
        }
    }

    Vector ( const T values[uiNumComponents] )
    : Vector::v ( values )
    {
    }

    Vector ( const std::initializer_list<T>& list )
    {
        for ( auto i : until(uiNumComponents) )
        {
            Vector::v[i] = list.begin ()[i];
        }
    }

    Vector& operator= ( const Vector& Right )
    {
        Vector::vec = Right.vec;
        return *this;
    }

    operator std::string () const
    {
        return *(*this);
    }

    std::string operator* () const
    {
        std::ostringstream ostr;

        ostr << "( ";
        for ( const T& elem : Vector::v )
        {
            ostr << elem << ", ";
        }
        ostr.seekp( -2, std::ios_base::cur );
        ostr << " )";

        return ostr.str();
    }

    Vector operator+ ( const Vector& Right ) const
    {
        Vector vecRet;
        vecRet.vec = Vector::vec + Right.vec;
        return vecRet;
    }

    Vector& operator+= ( const Vector& Right )
    {
        Vector::vec = Vector::vec + Right.vec;
        return *this;
    }
};

template < typename T >
class Vector4 : public Vector < T, 4 >
{
    typedef Vector < T, 4 > parent;
public:

    Vector4 ()
    : parent ()
    {
    }

    Vector4 ( const T& x, const T& y = 0, const T& z = 0, const T& w = 0 )
    {
        parent::v [ 0 ] = x;
        parent::v [ 1 ] = y;
        parent::v [ 2 ] = z;
        parent::v [ 3 ] = w;
    }

    Vector4 ( const parent& Right )
    : parent ( Right )
    {
    }

    Vector4& operator= ( const parent& Right )
    {
        parent::operator= ( Right );
        return *this;
    }

    T&          x ()        { return parent::v[0]; }
    const T&    x () const  { return parent::v[0]; }
    T&          y ()        { return parent::v[1]; }
    const T&    y () const  { return parent::v[1]; }
    T&          z ()        { return parent::v[2]; }
    const T&    z () const  { return parent::v[2]; }
    T&          w ()        { return parent::v[3]; }
    const T&    w () const  { return parent::v[3]; }
};

typedef Vector4<short> Vector4s, vec4s;
typedef Vector4<float> Vector4f, vec4f;
typedef Vector4<double> Vector4d, vec4d;
#endif    /* VECTOR_H */

#include <cstdio>
#include <cstdlib>

int main(int argc, char** argv)
{
    vec4f v1 ( 1, 2, 3, 4 ), v2 ( 8, 7, 6, 5 ), v3;
    v3 = v1 + v2;
//    v3 += { 1, 0, 1, 0 };

    printf ( "Result: %f %f %f %f\n", v3.x(), v3.y(), v3.z(), v3.w() );
    return 0;
}