←back to thread

A benchmark of three different floating point packages for the 6809

(boston.conman.org)
40 points ingve | 1 comments | 14 Oct 24 09:25 UTC | HN request time: 1.066s | source
Show context
mannyv ◴[18 Oct 24 02:16 UTC] No.41875816[source]▶
If you can find a copy Apple's SANE for the 6502 test it. It was faster than hardware fpus. That was according to a friend who was an FP geek back when.
replies(2): >>41876206 #>>41876676 #
spc476 ◴[18 Oct 24 03:54 UTC] No.41876206[source]▶
First off, the assembler is for a Motorola 6809, which is not a 6502. Second, one benchmark result I found [1] showed it being a bit slower than some alternatives.

[1] https://www.callapple.org/programming/sane-programming-on-th...

replies(2): >>41877377 #>>41882344 #
1. Someone ◴[18 Oct 24 18:52 UTC] No.41882344[source]▶
From that article: “In comparing measurements remember that SANE calculates to 19 digits. BASIC to 9 and Pascal to 6”.

SANEs claim to fame wasn’t that it was fast, it was that it produced results accurate to ½ ulp (https://en.wikipedia.org/wiki/Unit_in_the_last_place) in a large (for the time) floating point format.