Conversation

Number to divide by? 3
precision? 64
Shift dividend right. Shift#1
Shift dividend right. Shift#2
Add dividend to accumulator (dividend /4.000000)
Shift dividend right. Shift#3
Shift dividend right. Shift#4
Add dividend to accumulator (dividend /16.000000)
Shift dividend right. Shift#5
Shift dividend right. Shift#6
Add dividend to accumulator (dividend /64.000000)
Shift dividend right. Shift#7
Shift dividend right. Shift#8
Add dividend to accumulator (dividend /256.000000)
Shift dividend right. Shift#9
Shift dividend right. Shift#10
Add dividend to accumulator (dividend /1024.000000)
Shift dividend right. Shift#11
Shift dividend right. Shift#12
Add dividend to accumulator (dividend /4096.000000)
Shift dividend right. Shift#13
Shift dividend right. Shift#14
Add dividend to accumulator (dividend /16384.000000)
Shift dividend right. Shift#15
Shift dividend right. Shift#16
Add dividend to accumulator (dividend /65536.000000)
Shift dividend right. Shift#17
Shift dividend right. Shift#18
Add dividend to accumulator (dividend /262144.000000)
Shift dividend right. Shift#19
Shift dividend right. Shift#20
Add dividend to accumulator (dividend /1048576.000000)
Shift dividend right. Shift#21
Shift dividend right. Shift#22
Add dividend to accumulator (dividend /4194304.000000)
Shift dividend right. Shift#23
Shift dividend right. Shift#24
Add dividend to accumulator (dividend /16777216.000000)
Shift dividend right. Shift#25
Add dividend to accumulator (dividend /33554432.000000)

well, thats not faster is it!

:P
:]

Embed this notice

Sid (谷思谛) 🐺 (autinerd@chaos.social)'s status on Thursday, 19-Feb-2026 16:40:53 JST

Sid (谷思谛) 🐺

in reply to

Rue Mohr

@RueNahcMohr @soatok A multiplication is always faster than a division. And thanks to the limited number range in a register, you can in many cases represent division via multiplication. But it doesn't always work.

Embed this notice

Rue Mohr (ruenahcmohr@infosec.exchange)'s status on Thursday, 19-Feb-2026 16:40:54 JST

Rue Mohr

in reply to

@soatok can that really be faster than a shift?surely there is an MMX instruction that does the divide and whatever the next instruction in the program is supposed to do too. :]

Embed this notice

Orange Lizard Girlthing (naahrathescaled@furry.engineer)'s status on Thursday, 19-Feb-2026 19:56:41 JST

Orange Lizard Girlthing

in reply to

@soatok Rust devs wish they could have a compiler like this

Soatok Dreamseeker repeated this.

Embed this notice

Thomas (horaynarea@chaos.social)'s status on Thursday, 19-Feb-2026 23:18:02 JST

Thomas

in reply to

Orange Lizard Girlthing

@NaahraTheScaled @soatok but… it does? (with optimizations enabled/in release mode)

Embed this notice

Soatok Dreamseeker (soatok@furry.engineer)'s status on Friday, 20-Feb-2026 00:37:59 JST

Soatok Dreamseeker

in reply to

Sophie Schmieg

@sophieschmieg laughs in constant-time code

Embed this notice

Sophie Schmieg (sophieschmieg@infosec.exchange)'s status on Friday, 20-Feb-2026 00:38:00 JST

Sophie Schmieg

in reply to

@soatok is it bad that I find the assembly completely reasonable? It's just a Barrett reduction.

Soatok Dreamseeker repeated this.

Embed this notice

Soatok Dreamseeker (soatok@furry.engineer)'s status on Friday, 20-Feb-2026 00:59:13 JST

Soatok Dreamseeker

in reply to

Kelly MacNeill

@pyromuffin Yep. It's Barrett reduction :D

Embed this notice

Kelly MacNeill (pyromuffin@mastodon.gamedev.place)'s status on Friday, 20-Feb-2026 00:59:15 JST

Kelly MacNeill

in reply to

@soatok integer division is very slow, so this is a reasonable thing to do for division by a constant.

Embed this notice

Soatok Dreamseeker (soatok@furry.engineer)'s status on Friday, 20-Feb-2026 01:11:11 JST

Soatok Dreamseeker

in reply to

@autinerd @RueNahcMohr It's also good for avoiding side-channels:

https://blog.trailofbits.com/2025/11/14/how-we-avoided-side-channels-in-our-new-post-quantum-go-cryptography-libraries/

Embed this notice

Craig Stuntz (craigstuntz@discuss.systems)'s status on Friday, 20-Feb-2026 02:01:10 JST

Craig Stuntz

in reply to

Sophie Schmieg

@sophieschmieg @soatok

Embed this notice

Soatok Dreamseeker (soatok@furry.engineer)'s status on Friday, 20-Feb-2026 02:01:26 JST

Soatok Dreamseeker

in reply to

@HorayNarea @NaahraTheScaled I apprrciate the shitpost fact checking :3

Embed this notice

Thomas (horaynarea@chaos.social)'s status on Friday, 20-Feb-2026 02:43:38 JST

Thomas

in reply to

Orange Lizard Girlthing

@soatok @NaahraTheScaled i have even more facts: it's actually LLVM that doesn't do this specific optimization on -O0, so even clang emits a div unless you explicitly choose to optimize! :D

Embed this notice

Rich Felker (dalias@hachyderm.io)'s status on Wednesday, 25-Feb-2026 12:47:59 JST

Rich Felker

in reply to

@RueNahcMohr @autinerd @soatok I mean it looks like a mul one bit at a time. 🙃

Embed this notice

Arcanoraptor (arcanoraptor@furry.engineer)'s status on Friday, 27-Mar-2026 02:08:36 JST

Arcanoraptor

in reply to

Rue Mohr

@soatok @RueNahcMohr A long time ago in a simpler time, I was responsible for compiling my org’s copy of a common simulation program written in Fortran. I compiled with --02, and the build tests all failed.

Compiled with --O3 (a superset of O2 with unsafe optimizations) and suddenly everything was correct and the build tests all passed. I have a few users test with known-good benchmark values, and they are happy.

To this day I still have no idea what in the world was going on. It wasn’t even a weird compiler either, it was whatever the stable version of gfortran was at that time. Can confirm, compiler optimizations are black magic.

Public

Notices

Feeds