The microblog: 2022.06.07 20:12:44

2022.06.07 20:12:44 (1534236934238703616) from Daniel J. Bernstein, replying to "Richard Startin (@richardstartin)" (1533450679892729857):

When I started collecting vectorized-sorting references years ago, I quickly noticed a pattern of previous work not citing other clearly relevant previous work ... so to compensate I did _more_ searches, finding many interesting implementations and papers:

2022.06.07 20:20:11 (1534238808492847104) from Daniel J. Bernstein:

Smaller searches today (on duckduckgo to avoid filter bubbles) find vxsort without trouble. It's puzzling to see Google claiming state-of-the-art speeds without a direct comparison. Also, days after being pointed to djbsort and vxsort, Google still can't manage to run benchmarks?


2022.06.05 15:34:43 (1533442191900692480) from "damageboy (@damageboy)", replying to "damageboy (@damageboy)" (1533391869618491392):

BTW, Here is VxSort on an 12th Gen with hacked-on AVX-512 + DDR5 (Nice boost):

2022.06.05 15:57:47 (1533447996272148482) from "Richard Startin (@richardstartin)", replying to "damageboy (@damageboy)" (1533442191900692480):

When I read the blog post I was scanning for a reference to your work, but I didn’t find it, I hope it was just a case of not knowing how to use Google to find prior art

2022.06.05 16:04:25 (1533449665991032832) from "damageboy (@damageboy)", replying to "Richard Startin (@richardstartin)" (1533447996272148482):

Yeah, I assume no malice. I remember I researched a bit and saw some of the prior work but I missed @hashbreaker 's work until well after i was mostly finished for example.

2022.06.05 16:08:26 (1533450679892729857) from "Richard Startin (@richardstartin)", replying to "damageboy (@damageboy)" (1533449665991032832):

To be fair I can’t find yours on Google, I only know about it because I saw the link on twitter