LLVM Clang 16 vs. GCC 13 Compiler Performance On AMD 4th Gen EPYC "Genoa"
As we've seen with other processors as well, Clang 16 can perform extremely well against the latest upstream GNU Compiler Collection.
But for some workloads, particularly some OpenMP code-bases, even with LLVM libomp for some cases the performance remains better on the GCC side.
With the SMHasher hash function tester, the results were quite mixed depending upon the particular hashing algorithm whether GCC or Clang emitted the faster code.
LLVM/Clang performance has come a long way since its early days.