A Linux Compiler Deathmatch: GCC, LLVM, DragonEgg, Open64, Etc...
Feb 01, 2011, 14:32 (1 Talkback[s])
(Other stories by Michael Larabel)
Re-Imagining Linux Platforms to Meet the Needs of Cloud Service Providers
"Started by one of our readers more than a week ago was a
compiler deathmatch for comparing the performance of GCC, LLVM
Clang, PCC (the Portable C Compiler), TCC (Tiny C Compiler), and
Intel's C Compiler under Arch Linux. This user did not stop there
with compiling these different x86_64 code compilers, but he also
went on to look at the compiler performance with different compiler
flags, among other options. The results are definitely worth
looking at and here are some more.
"If you have not already, check out this forum thread where the
results and discussions can be found spread across a few pages with
multiple sets of results. The testing was done using the Phoronix
Test Suite 2.8 software in conjunction with Phoronix Global, but
with Phoronix Test Suite 3.0-Iveland and OpenBenchmarking.org this
will end up being even better and more powerful if this compiler
testing continues. Many different test profiles are used including
the timed Apache compilation, the Apache web-server benchmark
itself, 7-Zip compression, MP3 encoding, cryptography, ray-tracing,
and much more.
"In past months we have looked at the compiler performance on a
32-bit Atom netbook using GCC 4.2.4, GCC 4.3.5, GCC 4.4.5, GCC
4.5.1, GCC 4.6.0-20101120, and LLVM 2.8 with Clang. There also was
a more thorough comparison from an Intel 970 Gulftown system where
GCC 4.2.1, GCC 4.3, GCC 4.4, GCC 4.5, and GCC 4.6 were pressed
against LLVM with Clang 2.8, LLVM-GCC with GCC 4.2.1 and LLVM 2.8,
LLVM 2.8 with the DragonEgg plug-in for GCC 4.5.1, and then using
LLVM 2.8 with the Clang compiler."