4x faster than c (somehow, even though doubles only allow 2x simd).
overal flac encoding: 15-50% faster on core2, 4-11% on k8, 3-13% on p4.


git-svn-id: file:///var/local/repositories/ffmpeg/trunk@10621 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b