[Bug target/14552] compiled trivial vector intrinsic code is inefficient

["astrange at ithinksw dot com" <gcc-bugzilla at gcc dot gnu dot org>]

------- Comment #32 from astrange at ithinksw dot com  2008-03-20 00:39 -------
This is missed on trees:
mmxdw dw;
mmxw w;

void test2(){
        w= __builtin_ia32_paddw(w,w); w= (mmxdw)w;
}

void test3(){
        mmxw w2= __builtin_ia32_paddw(w,w); dw= (mmxdw)w2;
}

test2 ()
{
  vector short int w.4;
  vector short int w.3;

<bb 2>:
  w.3 = w;
  w.4 = __builtin_ia32_paddw (w.3, w.3);
  w = w.4;
  dw = VIEW_CONVERT_EXPR<vector int>(w);
  return;
}

test3 ()
{
  mmxw w2;
  vector short int w.6;

<bb 2>:
  w.6 = w;
  w2 = __builtin_ia32_paddw (w.6, w.6);
  dw = VIEW_CONVERT_EXPR<vector int>(w2);
  return;
}


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=14552