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

["pluto at agmk dot net" <gcc-bugzilla at gcc dot gnu dot org>]

------- Comment #21 from pluto at agmk dot net  2005-12-01 00:52 -------
I'm wondering is it possible to implement tranformations
of vector arithmetics into vector builtins?

e.g.

#include <mmintrin.h>
__v8qi foo(const __v8qi x, const __v8qi y) { return x + y; }
__v8qi bar(const __v8qi x, const __v8qi y) { return _mm_add_pi8(x, y); }

I except from compiler the same code for both functions
but it produces insane code for foo() :/

foo (x, y)
{
  unsigned int D.2377;
  unsigned int D.2376;
  unsigned int D.2369;
  unsigned int D.2368;
<bb 0>:
  D.2368 = BIT_FIELD_REF <x, 32, 0>;
  D.2369 = BIT_FIELD_REF <y, 32, 0>;
  D.2376 = BIT_FIELD_REF <x, 32, 32>;
  D.2377 = BIT_FIELD_REF <y, 32, 32>;
  return VIEW_CONVERT_EXPR<__v8qi>(
    {(D.2368 ^ D.2369) & 080808080 ^ (D.2369 & 2139062143) +
     (D.2368 & 2139062143),
     (D.2376 ^ D.2377) & 080808080 ^ (D.2377 & 2139062143) +
     (D.2376 & 2139062143)});
}

bar (x, y)
{
  vector signed char D.2448;
<bb 0>:
  D.2448 = __builtin_ia32_paddb (
    VIEW_CONVERT_EXPR<vector signed char>(VIEW_CONVERT_EXPR<__m64>(x)),
    VIEW_CONVERT_EXPR<vector signed char>(VIEW_CONVERT_EXPR<__m64>(y)));
  return VIEW_CONVERT_EXPR<__v8qi>(VIEW_CONVERT_EXPR<vector int>(D.2448));
}

# gcc -O2 -march=pentium3 -fomit-frame-pointer -mregparm=3

foo:
        subl    $44, %esp
        movq    %mm0, 24(%esp)
        movl    %ebx, 32(%esp)
        movl    24(%esp), %ebx
        movl    %esi, 36(%esp)
        movl    28(%esp), %esi
        movq    %mm1, 24(%esp)
        movl    24(%esp), %eax
        movl    28(%esp), %edx
        movl    %edi, 40(%esp)
        movl    %ebx, %edi
        andl    $2139062143, %edi
        movl    %eax, %ecx
        xorl    %eax, %ebx
        andl    $2139062143, %ecx
        movl    %esi, %eax
        addl    %edi, %ecx
        xorl    %edx, %eax
        movl    40(%esp), %edi
        andl    $2139062143, %esi
        andl    $-2139062144, %ebx
        andl    $2139062143, %edx
        xorl    %ecx, %ebx
        addl    %esi, %edx
        andl    $-2139062144, %eax
        movl    36(%esp), %esi
        movl    %ebx, 20(%esp)
        xorl    %edx, %eax
        movl    32(%esp), %ebx
        movss   20(%esp), %xmm0
        movl    %eax, 20(%esp)
        movss   20(%esp), %xmm1
        unpcklps        %xmm1, %xmm0
        movlps  %xmm0, 8(%esp)
        movl    8(%esp), %eax
        movl    12(%esp), %edx
        movl    %eax, (%esp)
        movl    %edx, 4(%esp)
        movq    (%esp), %mm1
        addl    $44, %esp
        movq    %mm1, %mm0
        ret

bar:
        paddb   %mm1, %mm0
        ret


-- 


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