[Bug c++/15820] New: GCC emits MOVAPS to load unaligned data in case when -O2 is invoked

["dimfair at yahoo dot com" <gcc-bugzilla at gcc dot gnu dot org>]

When -O2 option is invoked, GCC emits MOVAPS as part of _mm_loadh_pi intrinsic 
to load of unaligned data.  
 
For the code like 
	float *float_ptr; 
	__m128 a; 
	... 
	_mm_loadh_pi( a, (__m64 *)(float_ptr + 22) ); 
 
GCC emits following asm code 
	movaps	88(%eax), %xmm1		;; eax -> float_ptr 
	movhps	%xmm1, -120(%ebp) 
Compiled program faults on movaps because 88(%eax) isn't 16-byte aligned. 
This bug appears only when -O2 option is invoked (-O1, -O3 are OK). 
 
Command line: 
	g++ -O2 -g -march=pentium4 -msse2 test.cpp 
 
test.cpp: 
- begin ------------------------------------------------------------- 
#include <iostream> 
#include <xmmintrin.h> 
 
bool Invert_6x6_fast( float *src ) 
{ 
	__m128	det, tmp1, tmp2; 
	__m128	row[6]; 
 
	tmp1 = _mm_setzero_ps(); 
	tmp2 = _mm_setzero_ps(); 
 
	row[0]	= _mm_shuffle_ps( tmp1, tmp2, 0x88 ); 
	row[1]	= _mm_shuffle_ps( tmp1, tmp2, 0xDD ); 
	tmp1	= _mm_loadh_pi( _mm_loadl_pi( tmp1, (__m64*)(&src[11]) ), 
(__m64*)(&src[22]) ); 
	row[2]	= _mm_shuffle_ps( tmp1, tmp2, 0x88 ); 
	row[3]	= _mm_shuffle_ps( tmp1, tmp2, 0x44 ); 
 
	tmp1	= _mm_loadh_pi( _mm_loadl_pi( tmp1, (__m64*)(&src[16]) ), 
(__m64*)(&src[20]) ); 
	row[5]	= _mm_shuffle_ps( tmp1, tmp2, 0x22 ); 
 
	tmp2	= _mm_load_ss( &src[0] ); 
	tmp2	= _mm_sub_ss( _mm_add_ss( tmp1, tmp1 ), _mm_mul_ss( tmp2, 
_mm_mul_ss( tmp1, tmp1 ) ) ); 
 
	_mm_store_ss( &src[0], tmp2 ); 
 
	row[1]	= _mm_sub_ps( row[1], tmp1); 
	row[3]	= _mm_sub_ps( row[3], tmp1); 
	row[5]	= _mm_sub_ps( row[5], _mm_mul_ps( row[0], tmp1 ) ); 
 
	// ----------------------------------------------- 
	det		= _mm_mul_ps( row[2], tmp1 ); 
 
	if( _mm_movemask_ps( det )  ) 
		return false; 
 
	det		= _mm_sub_ss( tmp1, det ); 
 
	return true; 
} // Invert_6x6_fast 
 
 
using namespace std; 
 
 
int main() 
{ 
	cout << "Hello, World!" << endl; 
 
	float data[64] __attribute__((aligned(16))); 
 
	for(int i=0;i < 64;i++) 
		data[i] = (float)i*i + 1; 
 
	Invert_6x6_fast(data); 
 
	for(int i=0;i < 16;i++) 
		cout << i << ": " << data[i] << endl; 
 
	return 0;	 
} 
- end ---------------------------------------------------------------

-- 
           Summary: GCC emits MOVAPS to load unaligned data in case when -O2
                    is invoked
           Product: gcc
           Version: 3.4.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P2
         Component: c++
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: dimfair at yahoo dot com
                CC: gcc-bugs at gcc dot gnu dot org
 GCC build triplet: i686-pc-linux-gnu
  GCC host triplet: i686-pc-linux-gnu
GCC target triplet: i686-pc-linux-gnu


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15820