AMD AOCC 1.3 Compiler Benchmarks vs. GCC 8.2 vs. LLVM Clang 7.0

Earlier this month marked the release of the AMD Optimizing C/C++ Compiler 1.3 (AOCC 1.3) with a re-base to the LLVM 7.0 code-base, enhanced loop optimizations, better vectorization, code generation, integration of the optimized AMD Math Library, and other enhancements. Here are some fresh benchmarks against AMD AOCC 1.3 against LLVM Clang 7.0 upstream as well as GCC 8.2.0.

Using the Dell PowerEdge R7425 that we received a few weeks ago and have been using for a lot of our Zen/EPYC benchmarks given its dual EPYC 7601 processors, the server was running Ubuntu 18.10 in its current configuration for the latest compiler toolchain. AMD AOCC 1.3 was tested using its default binaries and compared to GCC 8.2.0 and LLVM Clang 7.0. The CFLAGS/CXXFLAGS for testing were maintained at "-O3 -march=native" throughout.

A variety of C/C++ benchmarks were compiled and run in a fully-automated and reproducible manner using the open-source Phoronix Test Suite.