[Bug rtl-optimization/65078] [5.0 Regression] 4.9 and 5.0 generate more spill-fill in comparison with 4.8.2
rguenth at gcc dot gnu.org
gcc-bugzilla@gcc.gnu.org
Mon Feb 16 14:38:00 GMT 2015
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65078
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|UNCONFIRMED |NEW
Last reconfirmed| |2015-02-16
Ever confirmed|0 |1
--- Comment #2 from Richard Biener <rguenth at gcc dot gnu.org> ---
Confirmed.
4.8 has
_62 = MEM[(__m64 * {ref-all})dest_284];
_63 = VIEW_CONVERT_EXPR<long long int>(_62);
_64 = {_63, 0};
_65 = VIEW_CONVERT_EXPR<vector(16) char>(_64);
_66 = __builtin_ia32_punpcklbw128 (_65, { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0 });
_67 = VIEW_CONVERT_EXPR<__m128i>(_66);
_68 = VIEW_CONVERT_EXPR<vector(8) short int>(_67);
_70 = __builtin_ia32_paddw128 (pretmp_327, _68);
_71 = __builtin_ia32_packuswb128 (_70, _70);
_72 = VIEW_CONVERT_EXPR<__m128i>(_71);
_73 = __builtin_ia32_vec_ext_v2di (_72, 0);
MEM[(long long int *)dest_284] = _73;
while 5
_79 = MEM[(__m64 * {ref-all})dest_268];
_78 = VIEW_CONVERT_EXPR<long long int>(_79);
_77 = {_78, 0};
_74 = VIEW_CONVERT_EXPR<vector(16) char>(_77);
_73 = __builtin_ia32_punpcklbw128 (_74, { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0 });
_69 = VIEW_CONVERT_EXPR<vector(8) short unsigned int>(_73);
_68 = _69 + pretmp_312;
_67 = VIEW_CONVERT_EXPR<vector(8) short int>(_68);
_64 = __builtin_ia32_packuswb128 (_67, _67);
_63 = VIEW_CONVERT_EXPR<__m128i>(_64);
_62 = BIT_FIELD_REF <_63, 64, 0>;
MEM[(long long int *)dest_268] = _62;
so some intrinsics are no longer builtins. But the real difference is
the following weird store sequence
packuswb %xmm1, %xmm2
movaps %xmm2, (%esp)
movl (%esp), %esi
movl 4(%esp), %edi
movl %esi, (%eax)
movl %edi, 4(%eax)
compared to just
packuswb %xmm1, %xmm1
movq %xmm1, (%edx)
More information about the Gcc-bugs
mailing list