simd_decimal
eve
| simd_decimal | eve | |
|---|---|---|
| 1 | 6 | |
| 10 | 848 | |
| - | - | |
| 10.0 | 8.9 | |
| over 1 year ago | 6 days ago | |
| Rust | C++ | |
| MIT License | Boost Software License 1.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
simd_decimal
-
SIMD intrinsics and the possibility of a standard library solution
Compare this neon parser and this sse parser, or for a very direct example what happens if you naively do the x86 method of vector search on arm. The shuffle and accumulation for each parser is drastically different, since the set of horizontal multiply-accumulates are different.
eve
-
Lack of modern scientific libraries written in C
C++ offers tools for writing better APIs, and since the addition of concepts in C++20 it offers much better API enforcement. Writing an equivalent to libraries such as {fmt} or EVE is not possible in anything we’d call C.
-
Library that could generate vectorized code for different instruction sets?
Here is a doc on how we suggest to do it: https://jfalcou.github.io/eve/multiarch.html Here is complete code of that example: https://github.com/jfalcou/eve/tree/main/examples/multi-arch
-
SIMD intrinsics and the possibility of a standard library solution
My source for this was the statement:
-
C++'s smaller cleaner language
Indeed you cannot. Then again, you couldn't write a library like fmtlib in C in the first place. I mean why do you complain about C++ features which enable you to write libraries you otherwise couldn't? How would you expect to implement equivalent libraries to EVE or mp-units in C alone?
What are some alternatives?
ispc - Intel® Implicit SPMD Program Compiler
simdutf - Unicode routines (UTF8, UTF16, UTF32) and Base64: billions of characters per second using SSE2, AVX2, NEON, AVX-512, RISC-V Vector Extension. Part of Node.js and Bun.
sleef - SIMD Library for Evaluating Elementary Functions, vectorized libm and DFT
highway - Performance-portable, length-agnostic SIMD with runtime dispatch
simde - Implementations of SIMD instruction sets for systems which don't natively support them.
aoc2021
xsimd - C++ wrappers for SIMD intrinsics and parallelized, optimized mathematical functions (SSE, AVX, AVX512, NEON, SVE))
version2 - Vector class library, latest version
dmd - dmd D Programming Language compiler
fractals - Mandelbrot renderer with SIMD (NEON/AVX) acceleration.