<html><head><meta http-equiv="Content-Type" content="text/html charset=us-ascii"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;">Per IRC, here is the ll file of the un-unrolled Bubblesort. Experimentally on Haswell I see us return to approximately our original performance at a micro-op threshold of 44 (and around a 15-20% regression between that and 43). This testing is all on my desktop which is not necessarily quiescent and the test is somewhat short so I am not sure if there might a bit of tail coming of on for the last couple percentage points.<div><br><div>Numbers were obtained as follows: </div><div><div>../bad/bin/opt -O3 -x86-partial-unrolling-threshold=43 -x86-partial-max-branches=40000 -S < Bubblesort.ll >> BS43.ll</div></div><div><div>../bad/bin/opt -O3 -x86-partial-unrolling-threshold=44 -x86-partial-max-branches=40000 -S < Bubblesort.ll >> BS44.ll</div></div><div><br></div><div>Louis</div><div><br></div><div></div></div></body></html>