On Mon, Oct 1, 2012 at 12:44 AM, Vladimir Makarov <vmaka...@redhat.com> wrote: > Actually, I don't see there is a problem with LRA right now. I think we > should first to solve a whole compiler memory footprint problem for this > test because cpu utilization is very small for this test. On my machine > with 8GB, the maximal resident space achieves almost 8GB.
Sure. But note that up to IRA, the max. resident memory size of the test case is "only" 3.6 GB. IRA/reload allocate more than 4GB, doubling the foot print. If you want to solve that first, that'd be great of course... Ciao! Steven