icc 10.1.012 failed to compile the code, probably some compatibility issue with the gcc 4.2.3 installed on my system.
The auto-vectorizer has to be disabled (
-no-vec), otherwise the executable crashes.
Apart from that, the results are excellent (decoding 32 frames of the Foreman sequence, Intel Core2 Duo 2.66 GHz):
-DNDEBUG -g -O3 -no-prec-div -static -fomit-frame-pointer -march=core2 -msse3 -no-vec