LLVM Clang Performance Matching The GCC Compiler On AMD Threadripper 3960X
Last week were some benchmarks showing LLVM Clang hitting ~96% the performance of GCC using Intel Ice Lake while now for the recently released Zen2-based AMD Ryzen Threadripper 3960X we are seeing results where overall LLVM Clang is now at performance parity to GCC.
This round of compiler testing was done on the AMD Ryzen Threadripper 3960X 24-core processor atop Ubuntu 19.10 with the Linux 5.4 kernel. The tested compilers were GCC 9.2.1, GCC 10.0 development snapshot from this month, LLVM Clang 9.0.0, and LLVM Clang 10.0.0. All four compilers were built in their release mode. The CFLAGS/CXXFLAGS when building the benchmarks under test were set at "-O3 -march=native" throughout testing.
Via the Phoronix Test Suite a wide range of C/C++ benchmarks were carried out across the four tested compilers. No other changes were made during testing besides swapping out the compiler and rebuilding the software under test.