njuffa

Questions Linux Laravel Mysql Ubuntu Git Menu

HTML CSS JAVASCRIPT SQL PYTHON PHP BOOTSTRAP JAVA JQUERY R React Kotlin

njuffa has asked 37 questions and find answers to 189 problems.

Stats

About

njuffa questions

Unsigned 64x64->128 bit integer multiply on 32-bit platforms
Branchless count-leading-zeros on 32-bit RISC-V without Zbb extension
Accurate computation of PDF of standard normal distribution using C standard math library
3D Morton code computation utilizing carry-less multiplication
Fast BCD addition
Efficient and accurate computation of the reciprocal of hypot(a,b)
Efficient AVX2 implementation of a 17x17-bit squaring operation with result truncation
Fast implementation of complementary error function with 5-digit accuracy
Optimized 53->32 bit modulo computation on 32-bit processors
Accurate floating-point computation of the sum and difference of two products

njuffa answers

Will repeatedly normalizing an IEEE floating point vector mutate it?
Is there a non-looping unsigned 32-bit integer square root function C
Why isn't 2 equal to √2 * √2?
Is there a C++ function that returns exactly the value of the built-in CPU operation RSQRTSS for inverse square root?
Approximately reversible function from a pair of floats to a single float?
Log2 approximation in fixed-point
How to compute the angles of a triangle accurately given squared edge lengths?
Sine approximation, did i beat Remez?
Why don't x86-64 (or other architectures) implement division by 10?
Can we use any value in floating point for customized flags?