A Look At The GCC 9 Performance On Intel Skylake Against GCC 8, LLVM Clang 7/8

Written by Michael Larabel in Software on 13 November 2018 at 12:00 PM EST. Page 4 of 5. 16 Comments.

Clang's OpenMP support has matured a lot over the past year or two and for the John The Ripper password cracking tests, Clang delivered much faster performance over GCC on this 18-core / 36-thread HEDT setup.

The Himeno pressure solver meanwhile favored GCC.

For those into chess benchmarks, Stockfish 9 was the fastest by a small margin with GCC 8.2.

LLVM Clang built the Apache web server a little bit quicker than the GCC compiler.

When it came to the timed LLVM compilation, building LLVM when using the LLVM Clang 8.0 compiler yielded a measurable speed-up compared to the three other compilers.


Related Articles