<html xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:10.0pt;
font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
span.EmailStyle19
{mso-style-type:personal-reply;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
mso-ligatures:none;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style>
</head>
<body lang="EN-US" link="blue" vlink="purple" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal"><span style="font-size:11.0pt">Hi, Xin Liu.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">Thank you for working on this. I’m glad to see the progress.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">> </span><span style="font-size:11.0pt">PEA: num allocations tracked = 24741, num materializations = 16037<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">Can you give more details on what these numbers are? Is the “num allocations tracked” all allocations happening in the methods (including no escape?) and “num materializations” the number of (escaping) allocations
that you had to rematerialize at least once?<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">Do you by any chance have an idea of how many allocations escape inside a control block and aren’t used after escaping – requiring no merge? If that happens often perhaps it’s a low hanging fruit that you
could pursue instead of the general PEA problem. I.e., something like this:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">Point p = new Point(…);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">if (….) {<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"> method(p);<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">}<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">Thanks,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt">Cesar<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt"><o:p> </o:p></span></p>
<div id="mail-editor-reference-message-container">
<div>
<div style="border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal" style="margin-bottom:12.0pt"><b><span style="font-size:12.0pt;color:black">From:
</span></b><span style="font-size:12.0pt;color:black">hotspot-compiler-dev <hotspot-compiler-dev-retn@openjdk.org> on behalf of Liu, Xin <xxinliu@amazon.com><br>
<b>Date: </b>Wednesday, May 17, 2023 at 4:48 PM<br>
<b>To: </b>hotspot-compiler-dev@openjdk.java.net <hotspot-compiler-dev@openjdk.java.net><br>
<b>Subject: </b>Update on PEA in C2 (Episode 3)<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal" style="margin-bottom:12.0pt"><span style="font-size:11.0pt">Hi,
<br>
I would like to update what we have done in C2 PEA. <br>
<br>
We manage to compile java.base module with PEA and inliner. It contains 7, 442<br>
classes and 62,210 methods. Here are the number of objects we track and materialize.<br>
PEA: num allocations tracked = 24741, num materializations = 16037<br>
<br>
We also CTW jdk.compiler and java.compiler modules. No compilation error is<br>
found. We fixed those compiler errors mainly by correcting allocation state. <br>
<br>
We verified behavior with one microbenchmark that we ported to JMH. It shows the<br>
allocation rate drops as expected. Because PEA is flow-sensitive, it can allocate<br>
on demand. The allocate rate reduces 75% when the object has 25% chance to<br>
escape (odd = 4); reduce to 1/8 when the object has only 12.5% chance to escape.<br>
<a href="https://github.com/navyxliu/jdk/pull/36">https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnavyxliu%2Fjdk%2Fpull%2F36&data=05%7C01%7Cdivino.cesar%40microsoft.com%7C4db7d7afba524192f3b808db57314523%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C638199641360138680%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=x2CPg%2BegAqcri48C61VhjyBckubFzR3LhD1ipUAeJs4%3D&reserved=0</a><br>
<br>
Remaining problems:<br>
1. In order to curb complexity, we disable passive materialization for time<br>
being. Passive materialization takes place only at a merging point because<br>
any of predecessor has already materialized the object. We prove that it is<br>
still correct to skip passive materialization. The downside is that we may<br>
have partial redundant allocation because C2 can't guarantee to eliminate<br>
the original object now. Currently, JDK-8287061 is working on this problem. The<br>
patch unravels 'reducible phi nodes' and then the original AllocateNodes are<br>
eliminated by ScalarReplacement. More details can be found here. <br>
<a href="https://gist.github.com/navyxliu/6239ce24f1ae447060302cc8562cbb71?permalink_comment_id=4520588#gistcomment-4520588">https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgist.github.com%2Fnavyxliu%2F6239ce24f1ae447060302cc8562cbb71%3Fpermalink_comment_id%3D4520588%23gistcomment-4520588&data=05%7C01%7Cdivino.cesar%40microsoft.com%7C4db7d7afba524192f3b808db57314523%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C638199641360138680%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=rXguep3zzXLM1bh0vHTYepXrde7OtMBhXsFgr173EQU%3D&reserved=0</a><br>
<br>
If JDK-8287061 processes all reducible phi nodes, PEA will have synergy effect<br>
with it. Our design goal is to punt complex jobs to C2 optimizer. If PEA<br>
introduces severe performance problem, we will revisit 'passive materialization'.
<br>
<br>
2. There are still 400+ runtime errors when we try to run hotspot:tier1<br>
tests. Most of them are from javac. here is what we have so far.<br>
<br>
$make test TEST="hotspot:tier1" CONF=linux-x86_64-server-fastdebug JTREG="VM_OPTIONS=-XX:+UnlockExperimentalVMOptions -XX:+DoPartialEscapeAnalysis"<br>
Test summary<br>
==============================<br>
TEST TOTAL PASS FAIL ERROR<br>
>> jtreg:test/hotspot/jtreg:tier1 2150 1717 145 288 <<<br>
==============================<br>
<br>
Our understanding is that PEA can't guarantee to replace all the old<br>
objects with the new objects in the debug sections of<br>
GraphKit::add_safepoint_edges().<br>
If deoptimization happens, runtime will rematerialize objects based on the<br>
wrong debuginfo. We end up wrong objects then. Our next goal to fix those runtime<br>
errors.<br>
<br>
We post a draft PR for curious audiences. We will port those tests to jtreg once we fix tier1 tests.<br>
<a href="https://github.com/openjdk/jdk/pull/14041">https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fopenjdk%2Fjdk%2Fpull%2F14041&data=05%7C01%7Cdivino.cesar%40microsoft.com%7C4db7d7afba524192f3b808db57314523%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C638199641360138680%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=gHoHmZ3aqpkGcP2RVhYXlXsnZmUVLj4jUJXiKxW2z1o%3D&reserved=0</a><br>
<br>
thanks,<br>
--lx<br>
<br>
<o:p></o:p></span></p>
</div>
</div>
</div>
</div>
</body>
</html>