SPEC2000: Comparison of LLVM-2.7 and GCC4.5.0 on x86

The goal of these runs is to compare the performance of the latest versions of LLVM and GCC on x86. Most widely used common options -O2 and -O3 are taken for all runs.

The used machine is 2.93Ghz Intel Core I7 with 8GB memory under Fedora Core10.

GCC-4.5.0 is configured with --enable-checking=release and compiled by GCC-3.4.6. (it means that GCC-4.5.0 compilation speed can be improved a bit more if the compiler were bootstrapped or built by more recent version of GCC). LLVM-2.7 x86 binaries are taken from LLVM download site. All changes are given relative to LLVM-2.7.

Compilation Speed
Code Size

Here the code size is the corresponding text and data segment size.
- Base SPECInt2000
- Peak SPECInt2000
- Base SPECFP2000
- Peak SPECFP2000
Generated Code Performace
- Base SPECInt2000
- Peak SPECInt2000
- Base SPECFP2000
- Peak SPECFP2000