GCC 4.6 performance regressions

[Sebastian Pop]

On Tue, Feb 8, 2011 at 16:14, Xinliang David Li <davidxl@google.com> wrote:
> What are the base option set used in all the comparison? O2, O3?  Some

The flags are those set by the Makefiles of the different benchmarks
(as downloaded from the web).

Setting different flags with CFLAGS=... is painful.

> of the build time results look weired -- e.g., adding -march speeds up
> *compile time* by 35%.

Because phoronix uses make -j the compile times are highly random.

Sebastian