<html><head><style type='text/css'>p { margin: 0; }</style></head><body><div style='font-family: arial,helvetica,sans-serif; font-size: 10pt; color: #000000'><br><br><hr id="zwchr"><blockquote style="border-left: 2px solid rgb(16, 16, 255); margin-left: 5px; padding-left: 5px; color: rgb(0, 0, 0); font-weight: normal; font-style: normal; text-decoration: none; font-family: Helvetica,Arial,sans-serif; font-size: 12pt;"><b>From: </b>"Sean Silva via llvm-dev" <llvm-dev@lists.llvm.org><br><b>To: </b>"Jonas Wagner" <jonas.wagner@epfl.ch><br><b>Cc: </b>"llvm-dev" <llvm-dev@lists.llvm.org><br><b>Sent: </b>Thursday, January 21, 2016 6:53:18 PM<br><b>Subject: </b>Re: [llvm-dev] Adding support for self-modifying branches to LLVM?<br><br><div dir="ltr"><br><div class="gmail_extra"><br><div class="gmail_quote">On Thu, Jan 21, 2016 at 2:52 PM, Jonas Wagner <span dir="ltr"><<a href="mailto:jonas.wagner@epfl.ch" target="_blank">jonas.wagner@epfl.ch</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;"><div dir="ltr"><div><p style="margin: 1.2em 0px ! important;">Hello,</p><span class="">
<blockquote style="margin: 1.2em 0px; border-left: 4px solid rgb(221, 221, 221); padding: 0px 1em; color: rgb(119, 119, 119); quotes: none;">
<blockquote style="margin: 1.2em 0px; border-left: 4px solid rgb(221, 221, 221); padding: 0px 1em; color: rgb(119, 119, 119); quotes: none;">
<p style="margin: 1.2em 0px ! important;">There is some data on this, e.g, in <a href="http://dslab.epfl.ch/proj/asap/#publications" target="_blank">“High System-Code Security with Low Overhead”</a>. In this work we found that, for ASan as well as other instrumentation tools, most overhead comes from the checks. Especially for CPU-intensive applications, the cost of maintaining shadow memory is small.</p>
</blockquote>
<p style="margin: 1.2em 0px ! important;">How did you measure this? If it was measured by removing the checks before optimization happens, then what you may have been measuring is not the execution overhead of the branches (which is what would be eliminated by nop’ing them out) but the effect on the optimizer.</p>
</blockquote>
</span><p style="margin: 1.2em 0px ! important;">Interesting. Indeed this was measured by removing some checks and then re-optimizing the program.</p>
<p style="margin: 1.2em 0px ! important;">I’m aware of some impact checks may have on optimization. For example, I’ve seen cases where much less inlining happens because functions with checks are larger. Do you know other concrete examples? This is definitely something I’ll have to be careful about. Philip Reames confirms this, too.</p></div></div></blockquote><div>Off the top of my head:</div><div><br></div><div>- CFG is more complex</div><div>- regalloc is harder (although in theory it needn't do a worse job since the branches are marked as unlikely; but not sure about in practice)</div><div>- the branch splits a BB which otherwise would have stayed together, restricting e.g. the scheduler (which is BB-at-a-time last I heard)</div><div id="DWT12358"><br></div></div></div></div></blockquote><br>Yes, the scheduling is per-BB (it is also interrupted by function calls). :(<br><br> -Hal<br><br><blockquote style="border-left: 2px solid rgb(16, 16, 255); margin-left: 5px; padding-left: 5px; color: rgb(0, 0, 0); font-weight: normal; font-style: normal; text-decoration: none; font-family: Helvetica,Arial,sans-serif; font-size: 12pt;"><div dir="ltr"><div class="gmail_extra"><div class="gmail_quote"><div></div><div>-- Sean Silva</div><div> </div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;"><div dir="ltr"><div>
<p style="margin: 1.2em 0px ! important;">On the other hand, we’ve also found that the benefit from removing a check is roughly proportional to the number of cycles spent executing that check’s instructions. Our model of this is not very precise, but it shows that the cost of executing the check’s instructions matters.</p><p style="margin: 1.2em 0px ! important;">I'll try to measure this, and will come back when I have data.</p>
<p style="margin: 1.2em 0px ! important;">Best,<br>Jonas</p>
<div title="MDH:SGVsbG8sPGJyPjxicj4mZ3Q7Jmd0OyBUaGVyZSBpcyBzb21lIGRhdGEgb24gdGhpcywgZS5nLCBp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" style="min-height: 0pt; width: 0pt; max-height: 0pt; max-width: 0pt; overflow: hidden; font-size: 0em; padding: 0pt; margin: 0pt;"></div></div></div>
</blockquote></div><br></div></div>
<br>_______________________________________________<br>LLVM Developers mailing list<br>llvm-dev@lists.llvm.org<br>http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev<br></blockquote><br><br><br>-- <br><div><span name="x"></span>Hal Finkel<br>Assistant Computational Scientist<br>Leadership Computing Facility<br>Argonne National Laboratory<span name="x"></span><br></div></div></body></html>