LLVM 3.3 Improves Its Loop Vectorizer
Phoronix: LLVM 3.3 Improves Its Loop Vectorizer
The release of LLVM 3.3 is still months away, but one of its features already are notable improvements to its loop vectorizer...
The Loop vectorizer is now enabled by default when -O3 is used. Clang now has flags for controlling the loop vectorizer: -fvectorize and -fno-vectorize.
Originally Posted by phoronix
Here are some benchmarks numbers on the LLVM page:
looks good - thanks !
Originally Posted by nadav