| commit | d02eccf5840b356e741ea0e3166db2c7623b88c4 | [log] [tgz] |
|---|---|---|
| author | Benoit Jacob <jacob.benoit.1@gmail.com> | Mon Dec 14 22:47:14 2009 -0500 |
| committer | Benoit Jacob <jacob.benoit.1@gmail.com> | Mon Dec 14 22:47:14 2009 -0500 |
| tree | 5676a85636aaf78c82f2edd39edbbdddddf53cbf | |
| parent | d5f3b2dc943a712a92834cebaea8bb9caae2f6e9 [diff] |
add SSE path for Matrix4f inverse, taken from Intel except that we do a kosher division instead of RCPPS-followed-by-Newton-Raphson. The rationale for that is that elsewhere in Eigen we dont allow ourselves this approximation (which throws 2 bits of mantissa), so there's no reason we should allow it here.