<div dir="ltr"><br><div class="gmail_extra"><br><div class="gmail_quote">On Mon, Sep 12, 2016 at 11:26 AM, Matthias Braun <span dir="ltr"><<a href="mailto:mbraun@apple.com" target="_blank">mbraun@apple.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="word-wrap:break-word"><div>I think those should be considered internal options for (llvm codegen) developers, a normal compiler user should not need to use any of them.</div></div></blockquote><div><br></div><div>We're targetting a new processor. I'm trying to get IPC numbers up a bit by trying to figure out how to improve scheduling for our particular architecture. If it turns out that some of these options give us improvements I can have them be 'on' by default for our target.<br><br></div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="word-wrap:break-word"><div> Of course you can look around the llvm sourcecode (esp. in lib/CodeGen/MachineScheduler.<wbr>cpp) and see what cl::opt options are available and how they affect the scheduler operation.</div><div><br></div><div>In case of the MachineScheduler all settings are the same regardless of the optimisation level, however the MachineScheduler is disabled as a whole in TargetPassConfig.cpp when optimized regalloc is not enabled (which I believe happens for everything except -O0).</div><div><br></div><div>- Matthias</div><br><div><blockquote type="cite"><div><div class="h5"><div>On Sep 12, 2016, at 10:41 AM, Phil Tomson via llvm-dev <<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>> wrote:</div><br></div></div><div><div><div class="h5"><div dir="ltr"><div>As a follow on question: which of these options are already enabled when compiling with -O3?<br><br></div>Phil<br></div><div class="gmail_extra"><br><div class="gmail_quote">On Mon, Sep 12, 2016 at 10:37 AM, Phil Tomson <span dir="ltr"><<a href="mailto:phil.a.tomson@gmail.com" target="_blank">phil.a.tomson@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div><div>I see that there are several options to influence instruction scheduling, but there doesn't seem to be a lot of information about what they do, for example:<br><br>-misched-topdown -misched-bottomup<br><br></div>The description in MachineScheduler.cpp says:<br><br>"Force top-down list scheduling" and "Force bottom-up list scheduling"<br><br></div>Which isn't too helpful - where might I want to use these? Under what conditions might they improve an instruction schedule?<br><br></div>Similar questions for the instruction scheduler strategies: <br><br>-misched=(default, converge,<br><div><div>ilpmax, ilpmin, or shuffle)<br><br></div><div>And for the analysis heuristics: <br><br>-misched-cluster,<br>-misched-cyclicpath, -misched-regpressure, and -misched-<br>fusion<br><br></div><div>Are these things mutually exclusive or can they be combined? What combination will give the most rigorous analysis and improve scheduling (at the cost of longer runtime of llc)<span><font color="#888888"><br><br></font></span></div><span><font color="#888888"><div>Phil<br></div></font></span></div></div>
</blockquote></div><br></div></div></div>
______________________________<wbr>_________________<br>LLVM Developers mailing list<br><a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a><br><a href="http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev" target="_blank">http://lists.llvm.org/cgi-bin/<wbr>mailman/listinfo/llvm-dev</a><br></div></blockquote></div><br></div></blockquote></div><br></div></div>