sleef
version2
sleef | version2 | |
---|---|---|
17 | 6 | |
590 | 1,220 | |
- | 1.6% | |
8.1 | 5.8 | |
9 days ago | 3 months ago | |
C | C++ | |
Boost Software License 1.0 | Apache License 2.0 |
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.
sleef
-
The Case of the Missing SIMD Code
I'm the main author of Highway, so I have some opinions :D Number of operations/platforms supported are important criteria.
A hopefully unbiased commentary:
Simde allows you to take existing nonportable intrinsics and get them to run on another platform. This is useful when you have a bunch of existing code and tight deadlines. The downside is less than optimal performance - a portable abstraction can be more efficient than forcing one platform to exactly match the semantics of another. Although a ton of effort has gone into Simde, sometimes it also resorts to autovectorization which may or may not work.
Eigen and SLEEF are mostly math-focused projects that also have a portability layer. SLEEF is designed for C and thus has type suffixes which are rather verbose, see https://github.com/shibatch/sleef/blob/master/src/libm/sleef... But it offers a complete (more so than Highway's) libm.
-
Does anyone have any interest in my deep-learning framework?
But the other part about SIMD: I'm unsure if mgl-mat uses SIMD for transcendental functions or even for something like element-wise multiplication and division*. SIMD easily provides a speed-boost of 4-8 times which numpy uses. Libraries like sleef have been put to use by many.
- `constexpr` what?
- Advice on porting glibc trig functions to SIMD
-
SIMD intrinsics and the possibility of a standard library solution
Highway and Agner's VectorClass also have math functions. And SLEEF should definitely be mentioned.
-
Portable SIMD library
"SIMD Library for Evaluating Elementary Functions, vectorized libm and DFT" - https://github.com/shibatch/sleef
- SIMD Library for Evaluating Elementary Functions, Vectorized Libm and DFT
-
C library for multiple-precision floating-point arithmetic with correct rounding
Not mentioned in the list of users is SLEEF (https://github.com/shibatch/sleef), which provides fast approximations for various elementary functions. (It generates coefficients for the approximations with mpfr)
SLEEF itself is used by PyTorch.
-
How to speed up array writes?
If you are looking at floats, there's https://sleef.org
-
Benchmarking sine approximations and interpolators.
It would be interesting to see SLEEF added in the benchmarks.
version2
-
SIMD intrinsics and the possibility of a standard library solution
Vector class library - 938 GH stars
- Checking for the absence of a string, naive AVX-512 edition
-
-๐- 2022 Day 4 Solutions -๐-
Most of the time is spent parsing, but this problem lends itself nicely to a SIMD formulation, which using vectorclass doesn't even require detailed knowledge of the intrinsics. Hot runs take ~14 ยตs on a Core i9-12900K, including I/O. Full code is (here)[https://github.com/ahans/aoc2022/blob/main/cpp/day04.cc], the interesting part is this, where we process 32 elements at once:
- Significantly faster quicksort using SIMD
- Parsing JSON faster with Intel AVX-512
- What do you think is faster for batch-processing a lot of "double-type" arithmetic?
What are some alternatives?
nsimd - Agenium Scale vectorization library for CPUs and GPUs
highway - Performance-portable, length-agnostic SIMD with runtime dispatch
yenten-arm-miner-yespowerr16 - ARM 64 CPU miner for Yespower variant algorithms
aoc22 - Advent of Code solutions for 2022 (in Python)
sb-simd - A convenient SIMD interface for SBCL.
advent2022
vector-libm
adventOfCode2022
crlibm - A mirror of the CRLibm project from INRIA Forge
simde - Implementations of SIMD instruction sets for systems which don't natively support them.
xbyak_aarch64
Day4 - My (messy) Python3 solution for day4's puzzle.