<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body>
<div dir="auto" style="direction: ltr; margin: 0; padding: 0; font-family: sans-serif; font-size: 11pt; color: black; ">
Don't the latest incarnations of ECL use the Bohem GC?<br>
<br>
</div>
<div dir="auto" style="direction: ltr; margin: 0; padding: 0; font-family: sans-serif; font-size: 11pt; color: black; ">
Just asking...<br>
<br>
</div>
<div dir="auto" style="direction: ltr; margin: 0; padding: 0; font-family: sans-serif; font-size: 11pt; color: black; ">
MA<br>
</div>
<div dir="auto" style="direction: ltr; margin: 0; padding: 0; font-family: sans-serif; font-size: 11pt; color: black; ">
<span id="ms-outlook-android-cursor"></span><br>
</div>
<div dir="auto" style="direction: ltr; margin: 0; padding: 0; font-family: sans-serif; font-size: 11pt; color: black; ">
<span id="OutlookSignature">
<div dir="auto" style="direction: ltr; margin: 0; padding: 0; font-family: sans-serif; font-size: 11pt; color: black; ">
Get <a href="https://aka.ms/ghei36">Outlook for Android</a></div>
</span><br>
</div>
<hr style="display:inline-block;width:98%" tabindex="-1">
<div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" style="font-size:11pt" color="#000000"><b>From:</b> pro <pro-bounces@common-lisp.net> on behalf of Martin Cracauer <cracauer@cons.org><br>
<b>Sent:</b> Thursday, December 3, 2020 6:25:50 PM<br>
<b>To:</b> Discussion list for Common Lisp professionals <pro@common-lisp.net><br>
<b>Subject:</b> Re: Call for Interest: Clojure (or Lisp?) Code Camp with BLM focus</font>
<div> </div>
</div>
<div class="BodyFragment"><font size="2"><span style="font-size:11pt;">
<div class="PlainText">Pascal Costanza wrote on Thu, Dec 03, 2020 at 04:17:56PM +0100:
<br>
> <br>
> > Parallel GC is no problem and implemented.<br>
> <br>
> <br>
> Which CL implementations have a parallel GC?<br>
<br>
Clasp (via Boehm GC and MPS).<br>
<br>
I thought SBCL was there, but I just checked, not yet. I think Google<br>
is pushing for a parallel GC instead, because of response times to<br>
their production monitoring.<br>
<br>
Another untapped source of performance is userfaultfd(2) in the Linux<br>
kernel. It allows those GCs that implement a write barrier using<br>
page protections SIGSEGV to use the faster userfaultfd interface<br>
instead (as opposed to those using a bitmap). This won't help<br>
concurrent GC, but parallel GC would benefit even more than<br>
single-thread GC because it uses faster system calls.<br>
Proof of concept is here:<br>
<a href="https://www.cons.org/cracauer/cracauer-userfaultfd.html">https://www.cons.org/cracauer/cracauer-userfaultfd.html</a><br>
<br>
Martin<br>
-- <br>
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%<br>
Martin Cracauer <cracauer@cons.org> <a href="http://www.cons.org/cracauer/">http://www.cons.org/cracauer/</a><br>
<br>
</div>
</span></font></div>
</body>
</html>