Bits, Math and Performance(?)

The basic trick to apply the same bit-permutation to each of the u32 s is to view them as matrix of 16 rows by 32 columns, transpose it ...

A while ago, after some back and forth on twitter/X with @corsix , I dropped some implementation of byte histogramming without explaini...

Part 2 of Enumerating all mathematical identities (in fixed-size bitvector arithmetic with a restricted set of operations) of a certain ...

I was reminded (on mastodon) of this nibble-sorting technique (it could be adapted to other element sizes), which I apparently had only ...

I have written about this before , but that was a long time ago, I've had a lot more practice with similar things since then. This ...

This is a relatively simple use of GF2P8AFFINEQB . By itself GF2P8AFFINEQB essentially multiplies two 8x8 bit-matrices (but with transp...

As a reminder, grev is generalized bit-reversal , and performs a bit-permutation that corresponds to XORing the indices of the bits of ...

Once again a boring-but-specific title, I don't want to clickbait the audience after all. Even so, let's get some "disclaim...

popcnt(x) < tzcnt(x) asks the question "does x have fewer set bits than it has trailing zeroes". It's a simple quest...

The partial sums of popcount , aka A000788: Total number of 1's in binary expansions of 0, ..., n can be computed fairly efficiently...

It's no secret that GF2P8AFFINEQB can be tricky to think about, even in the restricted context of bit-permutations. Thinking about...

This post is meant as a replacement/recap of some work that I did over a decade ago on propagating bounds through bitwise operations, w...

When computing x + y , does the sum wrap? There are various ways to find out, some of them well known, some less. Some of these are pr...

grev ( generalized bit-reverse ) is an operation that implements bit-permutations corresponding to XOR-ing the indices by some value. ...