The time the x86 emulator team found code so bad that they fixed it during emulation
33 points by classichasclass
33 points by classichasclass
Big fan of the comment explaining loop unrolling to Raymond Chen.
eeeeeeh the comment might be written for the general audience, not just the blog author. There's a lot of people reading these posts who may not know as much about everything and appreciate pointers to learn more.
It's not like loop unrolling is a particularly complicated concept that is beyond the comprehension capabilities of the general audience.
Same, I also got the feeling that it was just a general comment. It's not really directed at Raymond at all; I got more of a vibe of, "That reminds me of this technique," as opposed to, "You should know that actually…."
(Not to say it doesn't happen! Nobody knows everyone.)
Fair. I am at an age where, after 25 years of development, I get defensive when people question the blog posts of a guy I was reading when I started out.
Didn't see the comment, must have been yanked, but yes, Raymond Chen, the man, the legend:
https://www.joelonsoftware.com/2004/06/13/how-microsoft-lost-the-api-war/
The comment is present under article: https://devblogs.microsoft.com/oldnewthing/20260615-00/?p=112419&commentid=144327#comment-144327
I'm betting this was on Alpha, given how much work was done on the x86 emulator for that platform.