David K. Zhang

Hey @haampie , this is fantastic work! I am especially impressed with your fast `zmm` transpose kernel; I've been trying to think of a good way to do the `MultiFloat{Vec{K,Float64},N}...

As a matter of fact, I actually have a similar struct-of-arrays construct that I started testing privately a long time ago. However, I hesitate to release an array-like construct as...

Closing this old thread since explicit vectorization is now supported in **MultiFloats.jl** v2.0. I have, for the time being, decided against introducing my own `MultiFloatArray` type and instead opted for...

Hey @jishnub , good catch! I totally overlooked this in my own testing. You're right, a conversion to `BigFloat` (with the precision set to the appropriate level) and then to...

Hey everyone! It's been ages since I last looked at **MultiFloats.jl**, but I've finally pushed a fix for this in [commit 02091e0](https://github.com/dzhang314/MultiFloats.jl/commit/02091e0ab3df36c8faa8eedf28eef61cf714a981).

Hey @oscardssmith , thanks for your interest in **MultiFloats.jl**! This is a great idea, as it simplifies the argument reduction step from subtracting an integer multiple of `log(2)` to simply...

Closing this issue to track in #28 instead.

Hey @haampie! I had a chance to dig into this today, and unfortunately, I don't think it's possible to fix this issue without significant performance impact to MultiFloats.jl. First, just...

Hey @mcabbott, thanks for your interest in **MultiFloats.jl**! This is a good suggestion, and I am interested in having standard floating-point introspection methods work for `MultiFloat` types. However, it is...

Fixed in [commit 1d54726](https://github.com/dzhang314/MultiFloats.jl/commit/1d547265c8e2db1a1904aea782bf201fb440affb).