<html>
  <head>
    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
  </head>
  <body>
    <p><br>
    </p>
    <div class="moz-cite-prefix">On 4/9/21 2:44 PM, Florian Hahn wrote:<br>
    </div>
    <blockquote type="cite"
      cite="mid:43C64D9C-B04D-4B3B-B2E6-95A84B00394A@apple.com">
      <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
      Hi,<br class="">
      <div><br class="">
        <blockquote type="cite" class="">
          <div class="">On 8 Apr 2021, at 19:17, Philip Reames <<a
              href="mailto:listmail@philipreames.com" class=""
              moz-do-not-send="true">listmail@philipreames.com</a>>
            wrote:</div>
          <br class="Apple-interchange-newline">
          <div class="">
            <meta http-equiv="Content-Type" content="text/html;
              charset=UTF-8" class="">
            <div class="">
              <p class="">This isn't a regression in this change, we're
                exposing an existing issue at higher frequency.  I
                reduced a test which doesn't involve this change, and
                filed a bug for it.  <a class="moz-txt-link-freetext"
                  href="https://bugs.llvm.org/show_bug.cgi?id=49900"
                  moz-do-not-send="true">https://bugs.llvm.org/show_bug.cgi?id=49900</a></p>
              <div class=""><br class="">
              </div>
            </div>
          </div>
        </blockquote>
        Oh that’s interesting, thanks for taking a look. I think there
        might be an existing bug for a similar/identical issue. Let me
        try to find it and link it in Guggilla.<br class="">
        <blockquote type="cite" class="">
          <div class="">
            <div class="">
              <p class="">Florian, I'm willing to take a shot at fixing
                this, but need a bit of help.  Would you have a couple
                minutes to debate ideas on how the vectorizer should be
                structured to avoid querying SCEV over partially
                constructed IR?</p>
            </div>
          </div>
        </blockquote>
      </div>
      Unfortunately I won’t have time in the next few days, but I’ll try
      to take a look early next week. Perhaps it would be worth syncing
      up mid next week?</blockquote>
    <p>Sure.  I don't see this as urgent, so simply suggest a time late
      next week which works for you.</p>
    <p>One near term question.  I have a slightly ugly workaround
      (described on the bug), for this particular manifestation of the
      broader issue.  Do you think it's worth working around?  (e.g. Did
      the frequency change by enough to be concerning?)<br>
    </p>
    <blockquote type="cite"
      cite="mid:43C64D9C-B04D-4B3B-B2E6-95A84B00394A@apple.com">
      <div class=""><br class="">
      </div>
      <div class="">Cheers,</div>
      <div class="">Florian</div>
    </blockquote>
  </body>
</html>