
<html><head></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><br><div><div>On Jun 29, 2010, at 1:39 PM, Jakob Stoklund Olesen wrote:</div><br class="Apple-interchange-newline"><blockquote type="cite"><div><br>On Jun 28, 2010, at 10:46 PM, Evan Cheng wrote:<br><br><blockquote type="cite"><br></blockquote><blockquote type="cite">On Jun 28, 2010, at 10:09 PM, Jakob Stoklund Olesen wrote:<br></blockquote><blockquote type="cite"><br></blockquote><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite">On Jun 28, 2010, at 10:00 PM, Evan Cheng wrote:<br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">On Jun 28, 2010, at 6:13 PM, Jakob Stoklund Olesen wrote:<br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">Author: stoklund<br></blockquote></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">Date: Mon Jun 28 20:13:07 2010<br></blockquote></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">New Revision: 107114<br></blockquote></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">URL: <a href="http://llvm.org/viewvc/llvm-project?rev=107114&view=rev">http://llvm.org/viewvc/llvm-project?rev=107114&view=rev</a><br></blockquote></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">Log:<br></blockquote></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">When no memoperands are present, assume unaligned, volatile.<br></blockquote></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><blockquote type="cite">Have you checked if this disabled a lot of potential optimizations? I am afraid assuming volatileness is overly conservative.<br></blockquote></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite">I haven't checked anything but running unit tests.<br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite">We need both non-volatile and 4-byte alignment to safely combine loads and stores. If memoperands are missing, I don't see any alternative. How else can we guarantee the optimization is valid?<br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite"><br></blockquote></blockquote><blockquote type="cite"><blockquote type="cite">If this causes missed optimizations, we should ensure that memory operands are present.<br></blockquote></blockquote><blockquote type="cite"><br></blockquote><blockquote type="cite">I agree. I am just wondering if that's indeed the case. Can you add a llc beta check to look for differences in # of load / store multiple optimizations?<br></blockquote><br>I ran an assembly diff across the entire nightly test suite.<br><br>We lost 117 of 56783 ldms and 40 of 47702 stms.<font class="Apple-style-span" color="#000000"><font class="Apple-style-span" color="#144FAE"><br></font></font></div></blockquote><br></div><div>Thanks. Can you file a bug about this? We should take a look.</div><div><br></div><div>Evan</div><div><br></div></body></html>