[And some notes: as mentioned in the lecture, refterm only had ~100x the throughput prior to the one part that was optimized, which was the ingress parser. With a ~20 lines of optimization, the throughput went up another 10x. The rest of the code is still mostly unoptimized.]
-
-
Show this thread
-
[Finally, it's worth noting that this throughput is still potentially very slow compared to what would happen if I had gone all the way and made "fast pipes" that communicate through L2-sized shared memory directly. So 1000x throughput is, in many ways, not even "good".]
Show this thread
End of conversation
New conversation -
-
-
Awesome series! I thought we were going to have a session with code from this project but I am not sure if there was any need for code walkthrough.
-
That was part of the live stream, but it was Q&A driven so it didn't make it into this series. I could record one now, though...
- Show replies
New conversation -
-
-
Thank you for providing so much useful, insightful content for free! Just purchased the Handmade Hero preorder b/c of the value I've gotten from watching all the videos you've provided. I learned some new things about hashing from your refterm glyph caching explanations... 1/2
-
Reminded of when I did game dev years ago and how important it was to be "smart" about everything that went into the code (and how easily that is forgotten with "modern dev", too many layers, etc.). Thanks again for your efforts and inspiration (for my side project)!!
End of conversation
New conversation -
-
-
Fantastic stuff. Wasn’t there supposed to be a “look at the code” part as well though?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Yeah, sure, refterm optimization is cool and all, but how does Casey write inverted on a whiteboard so well
-
Whiteboard optimization.
End of conversation
New conversation -
-
-
Awesome unique glass-board effect in video. It looks like you are writing behind the board in mirror image.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.