LLVM/Clang 3.3 Delivers Speed Improvements

Written by Michael Larabel in Software on 19 April 2013. Page 1 of 5. 4 Comments

Last month I delivered benchmarks showing LLVM/Clang 3.3 offers performance improvements and then LLVM/Clang 3.3 is very competitive to GCC 4.8. For further confirming this information, LLVM/Clang 3.3 SVN development benchmarks were carried out from an entirely different system to confirm the earlier findings. LLVM/Clang 3.3 is indeed much faster over its predecessor in a wide variety of Linux benchmarks.

The earlier LLVM/Clang 3.3 benchmarks were done from an Intel Core i7 990X "Gulftown" Extreme Edition system. This time around an Intel Core i7 3517UE "Ivy Bridge" processor was used on a low-power CompuLab Intense-PC nettop. This system was running Ubuntu 13.04 with a Linux 3.9 kernel snapshot.

For today's testing before the start of the weekend, the LLVM/Clang 3.2 release was compared to the LLVM/Clang 3.3 SVN code as of 15 April 2013 in a variety of C/C++ benchmarks. Both versions of LLVM/Clang/Compiler-RT were built in a --disable-assertions and --enable-optimized state for producing a release build. The compiler flags during the individual test profile benchmarking was also maintained the same.

All of this compiler benchmarking was handled in a fully automated and reproducible manner using the Phoronix Test Suite benchmarking software.

Related Articles