simdjson / simdjson

Star

Open

Fallback code paths with "SIMD Everywhere"

3

michaeleisel commented Aug 4, 2020

https://github.com/simd-everywhere/simde has done their first release ( https://simd-everywhere.github.io/blog/announcements/release/2020/06/21/0.5.0-release.html ) and it seems like something potentially useful for merging code paths. The most likely candidate I imagine is using SIMD code to replace the non-SIMD fallback path, but maybe it'd be worth checking if it can be used to merge ARM and x8

Accept custom memory allocators (std::allocator)

Open

Consider deleting check_for_unclosed_array

Find more good first issues →

HJLebbink / asm-dude

Star

Visual Studio extension for assembly syntax highlighting and code completion in assembly files and the disassembly window

syntax-highlighting visual-studio assembly x86-64 assembler avx2 nasm assembly-language-programming code-completion avx512 visual-studio-extension disassembly masm

Updated Oct 18, 2020
C#

oneapi-src / oneDNN

Star

oneAPI Deep Neural Network Library (oneDNN)

Updated Nov 25, 2020
C++

ermig1979 / Simd

Star

C++ image processing and machine learning library with using of SIMD: SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, AVX2, AVX-512, VMX(Altivec) and VSX(Power7), NEON for ARM.

Updated Nov 26, 2020
C++

VcDevel / Vc

Star

SIMD Vector Classes for C++

c-plus-plus cpp portable neon cpp14 parallel parallel-computing avx sse cpp11 simd cpp17 avx2 simd-programming vectorization avx512 simd-instructions simd-vector data-parallel

Updated Aug 28, 2020
C++

simd-everywhere / simde

Star

Open

AVX-512BW functions

10

nemequ commented Mar 10, 2020

https://software.intel.com/sites/landingpage/IntrinsicsGuide/#avx512techs=AVX512BW

_cvtmask32_u32
_cvtmask64_u64
_cvtu32_mask32
_cvtu64_mask64
_kadd_mask32
_kadd_mask64
_kand_mask32
_kand_mask64
_kandn_mask32
_kandn_mask64
_knot_mask32
_knot_mask64
_kor_mask32
_kor_mask64
_kort

WASM SIMD implementations of SSE

18

mind / wheels

Star

Performance-optimized wheels for TensorFlow (SSE, AVX, FMA, XLA, MPI)

machine-learning ai tensorflow gpu optimization wheel cuda ml avx avx2 sse41 fma sse42

Updated Jul 15, 2019

p12tic / libsimdpp

Star

Portable header-only C++ low level SIMD library

neon sse simd avx2 avx512 altivec vsx msa

Updated Jan 30, 2020
C++

microsoft / DirectXMath

Star

DirectXMath is an all inline SIMD C++ linear algebra library for use in games and graphics apps

microsoft uwp neon directx desktop xbox avx sse clang simd avx2 msvc cpp-library directxmath

Updated Oct 12, 2020
C++

minio / highwayhash

Star

Native Go version of HighwayHash with optimized assembly implementations on Intel and ARM. Able to process over 10 GB/sec on a single core on Intel CPUs - https://en.wikipedia.org/wiki/HighwayHash

neon assembly hash-functions plan9 avx2 highway-hash

Updated Sep 16, 2020
Go

Auburn / FastNoiseSIMD

Star

C++ SIMD Noise Library

neon simplex fractal sse simd noise cellular avx2 perlin perlin-noise white-noise noise-library noise-3d fastnoise-simd simplex-noise fastnoise

Updated Sep 20, 2020
C++

powturbo / TurboPFor-Integer-Compression

Star

Fastest Integer Compression

encoding library compression time-series simd compressor integer-compression intersection inverted-index avx2 sse2

Updated Sep 25, 2020
C

hfp / libxsmm

Star

Library targeting Intel Architecture for specialized dense and sparse matrix operations, and deep learning primitives.

machine-learning vector matrix intel avx sse jit simd matrix-multiplication sparse rnn blas convolution avx2 amx tensor avx512 transpose bfloat16

Updated Nov 27, 2020
C

EgorBo / SimdJsonSharp

Star

C# bindings for lemire/simdjson (and full C# port)

json simd avx2 netcore3

Updated Oct 25, 2019
C#

lemire / fastbase64

Star

SIMD-accelerated base64 codecs

simd avx2

Updated Feb 19, 2019
C

agenium-scale / boost.simd

Star

Boost SIMD

Updated Apr 10, 2019

WojciechMula / sse-popcount

Star

SIMD (SSE) population count --- http://0x80.pl/articles/sse-popcount.html

sse avx2 aarch64 avx512 popcount arm-neon

Updated Jan 25, 2020
C++

powturbo / Turbo-Run-Length-Encoding

Star

TurboRLE-Fastest Run Length Encoding

c java c-plus-plus benchmark rle sse simd avx2 run-length-encoding sse2

Updated Feb 25, 2020
C

kimwalisch / libpopcnt

Sponsor Star

🚀 Fast C/C++ bit population count library

c cpp neon avx2 avx512 popcnt popcount

Updated Oct 21, 2020
C++

altimesh / hybridizer-basic-samples

Star

Examples of C# code compiled to GPU by hybridizer

visual-studio compiler dotnet gpu optimization parallel cuda avx avx2 vectorization avx512 hybridizer-essentials

Updated Sep 5, 2019
C#

lovell / highwayhash

Star

Node.js implementation of HighwayHash, Google's fast and strong hash function

nodejs javascript buffer checksum fingerprint hash avx2 highwayhash sse41

Updated Jul 8, 2020
JavaScript

WojciechMula / toys

Star

Storage for my snippets, toy programs, etc.

sse avx2 avx512 string-algorithms

Updated Apr 17, 2020
C++

RRZE-HPC / OSACA

Star

Open Source Architecture Code Analyzer

python hpc latency assembly avx x86 throughput avx2 performance-analysis avx512 out-of-order critical-path port-mapping performance-modeling arm64v8 sve in-core loop-carried-dependency

Updated Nov 23, 2020
Assembly

inoryy / tensorflow-optimized-wheels

Star

TensorFlow wheels built for latest CUDA/CuDNN and enabled performance flags: SSE, AVX, FMA; XLA

python tensorflow cuda sse avx2 wheels cudnn tensorflow-gpu xla tensorflow-wheels

Updated Feb 12, 2020

agenium-scale / nsimd

Star

Agenium Scale vectorization library for CPUs and GPUs

neon cuda avx simd avx2 sse2 simd-programming aarch64 avx512 simd-instructions sse42 rocm sve neon128 vectorization-library

Updated Nov 29, 2020
Python

WojciechMula / sse4-strstr

Star

SIMD (SWAR/SSE/SSE4/AVX2/AVX512F/ARM Neon) of Karp-Rabin algorithm's modification

neon sse string-manipulation avx2 avx512

Updated Mar 4, 2020
C++

OpenNMT / CTranslate2

Star

Open

Prefix build options with "CT2_"

guillaumekln commented Jul 29, 2020

We should prefix CMake build options with "CT2_", e.g. CT2_WITH_MKL instead of WITH_MKL. This is a good practice to avoid possible conflicts with other projects.

The usage should then be updated in several places:

README.md
docker/Dockerfile.*
python/tools/build_wheel.sh
.travis.yml
src/cpu/cpu_isa.h
src/profiler.cc

WojciechMula / base64simd

Star

Base64 coding and decoding with SIMD instructions (SSE/AVX2/AVX512F/AVX512BW/AVX512VBMI/ARM Neon)

base64 neon sse simd avx2 avx512

Updated Jan 8, 2019
C++

manodeep / Corrfunc

Star

⚡️

⚡️Blazing fast correlation functions on the CPU.

python c openmp avx simd cosmology astrophysics galaxies large-scale-structure pair-counting intrinsics avx2 avx512 sse42 correlation-functions

Updated Nov 25, 2020
C

powturbo / Turbo-Base64

Star

Turbo Base64 - Fastest Base64 SIMD/Neon/Altivec

encoding benchmark arm library base64 neon avx sse simd avx2 base64-encoding base64-decoding encoding-library

Updated Aug 17, 2020
C

avx2

Here are 134 public repositories matching this topic...

simdjson / simdjson

Fallback code paths with "SIMD Everywhere"

Accept custom memory allocators (std::allocator)

Consider deleting check_for_unclosed_array

HJLebbink / asm-dude

oneapi-src / oneDNN

ermig1979 / Simd

VcDevel / Vc

simd-everywhere / simde

AVX-512BW functions

WASM SIMD implementations of SSE

mind / wheels

p12tic / libsimdpp

microsoft / DirectXMath

minio / highwayhash

Auburn / FastNoiseSIMD

powturbo / TurboPFor-Integer-Compression

hfp / libxsmm

EgorBo / SimdJsonSharp

lemire / fastbase64

agenium-scale / boost.simd

WojciechMula / sse-popcount

powturbo / Turbo-Run-Length-Encoding

kimwalisch / libpopcnt

altimesh / hybridizer-basic-samples

lovell / highwayhash

WojciechMula / toys

RRZE-HPC / OSACA

inoryy / tensorflow-optimized-wheels

agenium-scale / nsimd

WojciechMula / sse4-strstr

OpenNMT / CTranslate2

Prefix build options with "CT2_"

WojciechMula / base64simd

manodeep / Corrfunc

powturbo / Turbo-Base64

Improve this page

Add this topic to your repo

Oct	NOV	Dec
	29
2019	2020	2021

avx2

Here are 134 public repositories matching this topic...

simdjson / simdjson

Fallback code paths with "SIMD Everywhere"

Accept custom memory allocators (std::allocator)

Consider deleting check_for_unclosed_array

HJLebbink / asm-dude

oneapi-src / oneDNN

ermig1979 / Simd

VcDevel / Vc

simd-everywhere / simde

AVX-512BW functions

WASM SIMD implementations of SSE

mind / wheels

p12tic / libsimdpp

microsoft / DirectXMath

minio / highwayhash

Auburn / FastNoiseSIMD

powturbo / TurboPFor-Integer-Compression

hfp / libxsmm

EgorBo / SimdJsonSharp

lemire / fastbase64

agenium-scale / boost.simd

WojciechMula / sse-popcount

powturbo / Turbo-Run-Length-Encoding

kimwalisch / libpopcnt

altimesh / hybridizer-basic-samples

lovell / highwayhash

WojciechMula / toys

RRZE-HPC / OSACA

inoryy / tensorflow-optimized-wheels

agenium-scale / nsimd

WojciechMula / sse4-strstr

OpenNMT / CTranslate2

Prefix build options with "CT2_"

WojciechMula / base64simd

manodeep / Corrfunc

powturbo / Turbo-Base64

Improve this page

Add this topic to your repo

Essential cookies

Always active

Analytics cookies