xsimd

xsimd copied to clipboard

Proposal for `batch_constant` biwise shift.

1

There is a trick borrowed from Lemire that I am using to implement left shift when unavailable: multiply by 2^n. (The rest of the trick is that for right shifting,...

AntoinePrv

Extend the usage of `load_masked` and `store_masked` to `batch_bool`

2

I've noticed that currently the `load_masked` and `store_masked` only supports `batch_bool_constant`. I think `load_masked` and `store_masked` is very suitable for dealing with loop tails, however in this case the mask...

dragon-archer

Add shift by multiple constant

3

@serge-sans-paille @JohanMabille this ideas works, but I cannot figure out how to refactor `bitwise_lshift_as_twice_larger` into a separate header. The issue: - `xsimd_sse2.hpp` needs `utils/shits.hpp` for `bitwise_lshift_as_twice_larger` - but `bitwise_lshift_as_twice_larger` needs...

AntoinePrv

Proposal for Pixi workflow

4

This is the proposed Pixi workflow Tasks: - [x] Add pixi.toml - [x] Add CMakePresets - [x] Add usage to documentation - [x] Add sample usage in CI Some notes...

AntoinePrv

Add `xsimd::arange_batch_constant`

1

While adding too many utilities for `batch_constant` may not be a goal, I believe an additional utility to generate a `batch_constant` with increasing numbers from zeros could be an interesting...

AntoinePrv

Pixi dev workflow

4

Currently, I locally use [Pixi](https://pixi.sh) which is a modern project-oriented Conda environment manager, which I would like to contribute here. It can easily manage multiple environment and tasks (along with...

AntoinePrv

On main, running the tests give this failure. ``` [doctest] doctest version is "2.4.12" [doctest] run with "--help" for options =============================================================================== /Users/antoine/workspace/github.com/xtensor-stack/xsimd/test/test_error_gamma.cpp:156: TEST CASE: [error gamma] gamma /Users/antoine/workspace/github.com/xtensor-stack/xsimd/test/test_error_gamma.cpp:150: ERROR: CHECK_EQ(...

AntoinePrv

serge-sans-paille

Implementing intrinsics that were released along a wider register type

6

Some intrinsics for a size `N` are introduce in the same generation that introduces a register of size `2N. - `_mm_srlv_epi32` (128 bits) is introduced in Avx2, along with `_mm256`...

AntoinePrv

Non temporal data transfers

2

1. Adding stream API for non temporal data transfers 2. Adding xsimd::fence as a wrapper around std atomic for cache coherence 3. Adding tests ~~Draft because I need to double...

DiamonDinoia