On Wed, Dec 12, 2012 at 12:27 PM, Yuri Rumyantsev <ysrum...@gmail.com> wrote:
> This fix is aimed to remove performance degradation introduced by new > LRA phase that in fact is combining problem. Gcc combiner does > propagation of memory load to if-then-else gimple that was splitted > back by old reload phase. LRA does not perform such splitting. To > avoid performance slowdown on important benchmark (this is true for > all x86 targets) we decided to enhance 'ix86_legitimate_combined_insn' > with a check on such propagation and consider such conditional > instruction with memory operand as illegal one from performance point > of view. Is this true for all x86 targets? I have no objections to the implementation, but these fine-tunings should be declared in ix86_tune_features[] array, and used as conditions involving TARGET_xxx in the code. Please see many examples in the i386 source dir. > Is it OK for 4.8 and mainline? Hm, currently 4.8 _is_ mainline. Did you mean 4.7? Thanks, Uros.
