g++ 4.5-20100916 ICEs with "-O3 -march=pentium4" when using the following code:
template
void transform(const T *in_points,
int num_points,
const float projection_mat[16],
const float modelview_mat[16],
float *out_points)
{
float mat[16];
int row, col;
int i;
const T *in_p;
float *out_p;
for (col = 0; col < 4; col++)
{
for (row = 0; row < 4; row++)
{
mat[col*4+row] = ( projection_mat[0*4+row]*modelview_mat[col*4+0]
+ projection_mat[1*4+row]*modelview_mat[col*4+1]
+ projection_mat[2*4+row]*modelview_mat[col*4+2]
+ projection_mat[3*4+row]*modelview_mat[col*4+3]);
}
}
for (i = 0, in_p = in_points, out_p = out_points; i < num_points;
i++, in_p += 3, out_p += 3)
{
for (row = 0; row < 3; row++)
{
out_p[row] = ( mat[0*4+row]*in_p[0] + mat[1*4+row]*in_p[1]
+ mat[2*4+row]*in_p[2] + mat[3*4+row]);
}
}
if ( (mat[0*4+3] != 0) || (mat[1*4+3] != 0)
|| (mat[0*4+3] != 0) || (mat[1*4+3] != 1) )
{
for (i = 0, in_p = in_points, out_p = out_points; i < num_points;
i++, in_p += 3, out_p += 3)
{
float w = ( mat[0*4+3]*in_p[0] + mat[1*4+3]*in_p[1]
+ mat[2*4+3]*in_p[2] + mat[3*4+3]);
if (w > 0.0)
{
out_p[0] /= w;
out_p[1] /= w;
out_p[2] /= w;
}
else
{
out_p[2] = -static_cast< float >(1.0e+38f);
}
}
}
}
void TransformPoints(double *input,
int num_input,
const float projection_mat[16],
const float modelview_mat[16],
float *output)
{
transform(input, num_input, projection_mat, modelview_mat,
output);
}
void TransformPoints(unsigned short *input,
int num_input,
const float projection_mat[16],
const float modelview_mat[16],
float *output)
{
transform(input, num_input, projection_mat, modelview_mat,
output);
}
--
Summary: [4.5 regression] ICE in
ix86_vectorize_builtin_vec_perm_ok
Product: gcc
Version: 4.5.1
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: y at momonga-linux dot org
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=45752