More Benchmarks Of AMD's Threadripper With LLVM Clang 6.0 SVN
With AMD a few days ago having landed an updated scheduler model for Zen CPUs within LLVM, I ran some fresh compiler benchmarks to see how the performance compares.
This weekend I ran tests of LLVM Clang 4.0, Clang 5.0, and Clang 6.0 SVN after the landing of the recent znver1 scheduler model update. Just some quick tests from the AMD Threadripper 1950X Linux system while a more formal compiler comparison is in the works.
And a quick look at the many C/C++ benchmarks used:
You can find all of the details in full from this OpenBenchmarking.org result file. There are some minor changes in performance in both directions with Clang 6, but nothing too major. LLVM Clang 6.0 will still be under development for about the next five months before it will be released as stable.
This weekend I ran tests of LLVM Clang 4.0, Clang 5.0, and Clang 6.0 SVN after the landing of the recent znver1 scheduler model update. Just some quick tests from the AMD Threadripper 1950X Linux system while a more formal compiler comparison is in the works.
And a quick look at the many C/C++ benchmarks used:
You can find all of the details in full from this OpenBenchmarking.org result file. There are some minor changes in performance in both directions with Clang 6, but nothing too major. LLVM Clang 6.0 will still be under development for about the next five months before it will be released as stable.
8 Comments