<div dir="ltr"><div dir="ltr"><div class="gmail_default" style="font-size:small">Hi Marcel,</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Fri, Aug 20, 2021 at 3:22 AM Marcel Taeumel <<a href="mailto:marcel.taeumel@hpi.de">marcel.taeumel@hpi.de</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-style:solid;border-left-color:rgb(204,204,204);padding-left:1ex"> <div id="gmail-m_-2957149777794694628__MailbirdStyleContent" style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);text-align:left" dir="ltr">
Hi all --<div><br></div><div>I found the culprit. The regression started with the introduction of <span style="white-space:pre-wrap;font-size:10pt"><b>FastCPrimitiveFlag</b> in VMMaker.oscog-eem.2995. That new feature needs more adjustments, I suppose. :-)</span></div><div><br></div><div>My previous numbers were kind of wrong. I compared cog.spur against stack.spur. The latter being, in comparison, blazingly fast in #compileAll. Something is wrong with current cog.spur, at least on Windows (64-bit).</div><div><br></div><div>CommitHash: d8576b0 Plugins: 2021<b>0820</b>0011 <br></div><div><br></div><div>stack.pur</div><div><div>Morph methodDict size. " 1493 "</div><div>[Morph compileAll] timeToRun " 1293 "</div></div><div><br></div><div>cog.spur</div><div><div>Morph methodDict size. " 1493 "</div><div>[Morph compileAll] timeToRun " 23018 "</div><div><br></div><div>Here are more tests with cog.spur:</div><div><br></div><div>CommitHash: 128d14994 Plugins: 2021<b>0505</b>0056</div><div>cog.spur -- [Morph compileAll] timeToRun " 1294 "</div><div><div><br></div><div>CommitHash: 9d4e82529 Plugins: 2021<b>0712</b>1800<br></div><div>cog.spur -- [Morph compileAll] timeToRun " 910 "</div><div><br></div><div>CommitHash: c0d1a5574 Plugins: 2021<b>0721</b>1710 -- <span style="font-size:10pt">VMMaker.oscog-eem.2991</span><br></div><div>cog.spur -- [Morph compileAll] timeToRun " 901 "<br></div><div><br></div><div>CommitHash: 118a02c69 Plugins: 2021<b>0723</b>2247<br></div><div>cog.spur -- [Morph compileAll] timeToRun " 984 "</div><div><br></div><div><i>(BUILD BROKEN -- VMMaker.oscog-eem.2995)</i></div><div><i>(VM CRASHES between VMMaker.oscog-eem.2996 and VMMaker.oscog-eem.3009)</i><br></div><div><br></div><div>CommitHash: 03c4ef31b Plugins: 2021<b>0801</b>0511 -- VMMaker.oscog-eem.3009<br></div><div>cog.spur -- [Morph compileAll] timeToRun " 20787 "<br></div><div><br></div><div>***</div><div><br></div><div>Note that #compileAll does not write into the .changes file.<br></div><div><br></div><div>Note that the last "good" commit hash is 118a02c69f3e4c8c29e8ba867a78bd39f9a53cb4 (still using VMMaker.oscog-eem.2991). I added the tag "last-before-FastCPrimitiveFlag" to this commit.</div></div></div></div></blockquote><div><br></div><div class="gmail_default" style="font-size:small">2992 is good too. I see the regresion. It's huge; an 11 x slow down. Looking at VM parameters I see a 4 fold change in the number of check event calls, but that can be explained by the longer run time, so I don't think this is significant. ANyway, looking closely now.</div><div class="gmail_default" style="font-size:small"></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-style:solid;border-left-color:rgb(204,204,204);padding-left:1ex"><div id="gmail-m_-2957149777794694628__MailbirdStyleContent" style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);text-align:left" dir="ltr"><div><div><div><br></div><div>Now let's review and fix this. ^__^</div><div><br></div><div>Best,</div><div>Marcel</div><div><br></div></div></div><div></div>
<blockquote type="cite" style="border-left-style:solid;border-width:1px;margin-top:20px;margin-left:0px;padding-left:10px;min-width:500px">
<p style="color:rgb(170,170,170);margin-top:10px">Am 19.08.2021 15:55:34 schrieb Marcel Taeumel <<a href="mailto:marcel.taeumel@hpi.de" target="_blank">marcel.taeumel@hpi.de</a>>:</p><div style="font-family:Arial,Helvetica,sans-serif"><div id="gmail-m_-2957149777794694628__MailbirdStyleContent" style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);text-align:left" dir="ltr">
<div>[Morph compileAll] timeToRunWithoutGC</div><div><br></div><div>VM <span style="font-size:10pt">202108160631 : </span><span style="font-size:10pt">24607 milliseconds</span></div><div><span style="font-size:10pt">VM </span><span style="font-size:10pt">202108010511 : 1078 milliseconds</span></div><div><span style="font-size:10pt"><br></span></div><div><span style="font-size:10pt">Best,</span></div><div><span style="font-size:10pt">Marcel</span></div><div></div><blockquote type="cite" style="border-left-style:solid;border-width:1px;margin-top:20px;margin-left:0px;padding-left:10px;min-width:500px">
<p style="color:rgb(170,170,170);margin-top:10px">Am 19.08.2021 15:40:03 schrieb Marcel Taeumel <<a href="mailto:marcel.taeumel@hpi.de" target="_blank">marcel.taeumel@hpi.de</a>>:</p><div style="font-family:Arial,Helvetica,sans-serif"><div id="gmail-m_-2957149777794694628__MailbirdStyleContent" style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);text-align:left" dir="ltr">Hi all!<div></div><div><br></div><div>There is a serious performance regression in recent VM (<span style="font-size:10pt">202108160631) </span><span style="font-size:10pt">regarding code compilation. I could only narrow it down to CompiledMethod >> #methodClass:. Still investigating. The start-up is also very slow. Maybe GC-related?</span></div><div><span style="font-size:10pt"><br></span></div><div>This regression was not there in 202108010511.</div><div><br></div><div>Best,</div><div>Marcel</div></div></div></blockquote></div></div></blockquote></div></blockquote></div><div dir="ltr" class="gmail_signature"><div dir="ltr"><div><span style="font-size:small;border-collapse:separate"><div>_,,,^..^,,,_<br></div><div>best, Eliot</div></span></div></div></div></div>