[Bug target/12902] Invalid assembly generated when using SSE / xmmintrin.h

[bangerth at dealii dot org]

------- Additional Comments From bangerth at dealii dot org  2004-12-13 20:54 -------
I really have not much of an idea what I am doing here, but this 
is a shorter testcase: 
------------------------- 
#include <xmmintrin.h> 
 
typedef struct { 
  int i; 
  float f[3]; 
} a_t; 
 
typedef struct { 
  float f[8]; 
} b_t; 
 
typedef union { 
  int i[4]; 
  float f[4]; 
  __m128 v; 
} vector4; 
 
void swizzle( const void *a0, const void *a1, 
              const void *a2, const void *a3, 
              vector4 *a, vector4 *b, vector4 *c, vector4 *d ) { 
  __m128 t, u; 
  a->v = _mm_loadl_pi(a->v, (__m64 *)a0); 
  c->v = _mm_loadl_pi(c->v,((__m64 *)a0)+1); 
  a->v = _mm_loadh_pi(a->v, (__m64 *)a1); 
  c->v = _mm_loadh_pi(c->v,((__m64 *)a1)+1); 
  t   = _mm_loadl_pi(b->v, (__m64 *)a2); 
  u   = _mm_loadl_pi(d->v,((__m64 *)a2)+1); 
  a->v = _mm_shuffle_ps(a->v,t,0); 
  b->v = _mm_shuffle_ps(b->v,t,0); 
  c->v = _mm_shuffle_ps(c->v,u,0); 
  d->v = _mm_shuffle_ps(d->v,u,0); 
} 
 
int main () { 
  a_t a[128]; 
  b_t b[128]; 
   vector4 ai, a0, a1, a2, b0, v0, v1, v2; 
   __m128 *p0, *p1, *p2, *p3; 
 
   int n = 1; 
   for(;n;n--) { 
     swizzle(a,a+1,a+2,a+3,&ai,&a0,&a1,&a2); 
     p0 = (__m128 *)(b + ai.i[0]); 
     p1 = (__m128 *)(b + ai.i[1]); 
     p2 = (__m128 *)(b + ai.i[2]); 
     p3 = (__m128 *)(b + ai.i[3]); 
     swizzle(p0++,p1++,p2++,p3++,&b0,&v0,&v1,&v2); 
     _mm_add_ps(_mm_add_ps(b0.v,_mm_mul_ps(a1.v,v0.v)), 
                _mm_mul_ps(a2.v,_mm_add_ps(v1.v,_mm_mul_ps(a1.v,v2.v)))); 
   } 
} 
----------------------------- 
 
It fails on 3.4 and mainline, but not with icc: 
g/x> /home/bangerth/bin/gcc-3.4.*-pre/bin/g++  -O -msse2 -g x.cc ; ./a.out  
Segmentation fault 
 
g/x> /home/bangerth/bin/gcc-4.*-pre/bin/g++  -O -msse2 -g x.cc ; ./a.out  
Segmentation fault 
 
g/x> icc x.cc ; ./a.out  
 
On mainline, I get this from a gdb session: 
 
(gdb) r 
Starting program: /home/bangerth/tmp/g/x/a.out  
 
Program received signal SIGSEGV, Segmentation fault. 
swizzle (a0=0xbfffe250, a1=0xbfffe260, a2=0xbfffe270, a3=0xbfffe280,  
    a=0xbfffeac0, b=0xbfffeab0, c=0xbfffeaa0, d=0xbfffea90) at x.cc:23 
 
(gdb) i reg 
[...] 
eip            0x80483ba	0x80483ba 
(gdb) disass 
0x080483ba <_Z7swizzlePKvS0_S0_S0_P7vector4S2_S2_S2_+38>:	movaps 0x8
(%esi),%xmm0 
 
As I said, I have no idea what this program does, and if it is wellformed  
after my attempts to reduce it at all. Maybe it helps anyway. 
 
W. 
 

-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=12902