GCC 6.2 vs. Clang 3.9 Compiler Performance On Clear Linux With Intel Kaby Lake
The FFTW performance slightly favored GCC 6.2.0 but LLVM Clang 3.9.0 wasn't far behind.
Under MAFFT, Clang 3.9 had the slight advantage over GCC 6.2.
With SciMark 2.0 these micro-benchmarks favored Clang 3.9 due to it doing really well in a few tests like Dense LU Matrix Factorization, Sparse Matrix Multiplicatiom, and Jacobi Successive Over-Relaxation but GCC 6.2 on the other hand was more than twice as fast for monte carlo.