GCC 6.1 vs. LLVM Clang 3.9 Compiler Performance

Written by Michael Larabel in Software on 10 May 2016. Page 1 of 4. 10 Comments

After carrying out the recent GCC 4.9 vs. 5.3 vs. 6.1 compiler benchmarks for looking at the GNU Compiler Collection performance over the past three years on the same Linux x86_64 system, I then loaded up a development snapshot of the LLVM 3.9 SVN compiler to see how these two dominant compilers are competing on the performance front for C/C++ programs.

From the Xeon E5-2687W v3 (Haswell) system running Debian Testing x86_64 with the Linux 4.5 kernel, I compared the performance of GCC 6.1.0 against an LLVM Clang 3.9 snapshot from this past weekend.

Using the open-source Phoronix Test Suite software for test automation and reproducibility of results, I compared the latest GCC vs. Clang compiler performance for a range of C/C++ open-source tests. Those results for your viewing pleasure are on the pages ahead. The CFLAGS/CXXFLAGS during testing were set to "-O3 -march=native" while in a follow-up article I'll have more optimization tests. Seeing this article as multiple pages rather than all on an ad-free, single-page? Join Phoronix Premium to experience this and other features while supporting all of our open-source/Linux benchmarking work.

Related Articles