2 Commits

Author	SHA1	Message	Date
Martin Hořeňovský	d99eb8bec8	Optimize 64x64 extended multiplication implementation ... Now we use intrinsics when possible, and fallback to optimized implementation in portable C++. The difference is about 4x when we can use intrinsics and about 2x when we cannot. This should speed up our Lemire's algorithm implementation nicely.	2024-04-03 13:28:25 +02:00
Martin Hořeňovský	04a829b0e1	Add helpers for implementing uniform integer distribution ... * Utility for extended mult n x n bits -> 2n bits * Utility to adapt output from URBG to target (unsigned) integral type * Utility to reorder signed values into unsigned type while keeping the order.	2023-12-10 19:53:36 +01:00