Large collection of number systems providing custom arithmetic for mixed-precision algorithm development and optimization for AI, Machine Learning, Computer Vision, Signal Processing, CAE, EDA, control, optimization, estimation, and approximation.

• UpdatedMar 22, 2025
• C++

Conversion to/from half-precision floating point formats

• UpdatedJul 31, 2024
• C++

C++17 templates between [stl::vector | armadillo | eigen3 | ublas | blitz++] and HDF5 datasets

• UpdatedApr 1, 2022
• C++

Stage 3 IEEE 754 half-precision floating-point ponyfill

• UpdatedMar 23, 2025
• JavaScript

A memory balanced and communication efficient FullyConnected layer with CrossEntropyLoss model parallel implementation in PyTorch

• UpdatedJun 11, 2020
• Python

float16 provides IEEE 754 half-precision format (binary16) with correct conversions to/from float32

• UpdatedMar 24, 2025
• Go

CPP20 implementation of a 16-bit floating-point type mimicking most of the IEEE 754 behavior. Single file and header-only.

• UpdatedFeb 4, 2024
• C++

Round matrix elements to lower precision in MATLAB

• UpdatedJun 14, 2022
• MATLAB

Code for testing the native float16 matrix multiplication performance on Tesla P100 and V100 GPU based on cublasHgemm

• UpdatedAug 20, 2019
• Cuda

half float library for C and for z80

• UpdatedFeb 9, 2020
• C

Python module which finds the IEEE-754 representation of a floating point number.

• UpdatedMar 1, 2024
• Python

C++ template library for floating point operations

• UpdatedMar 22, 2025
• C++

Floating-Point Arithmetic Library for Z80

• UpdatedSep 11, 2023
• Assembly

Convert CUDA programs from float data type to half or half2 with SIMDization

• UpdatedMay 28, 2019
• C++

Optimised Caffe with OpenCL supporting for less powerful devices such as mobile phones

• UpdatedMar 12, 2019
• C++

Swift Half-Precision Floating Point

• UpdatedNov 15, 2023
• Swift

Half-Precision Floating-Point for Delphi

• UpdatedMay 22, 2018
• Pascal

Fast SGEMM emulation on Tensor Cores

• UpdatedFeb 16, 2025
• Cuda

CUDA/HIP header-only library that streamlines working with vector and low-precision floating-point types (16 bit, 8 bit) on GPUs

• UpdatedJan 27, 2025
• C++

Basic linear algebra routines implemented using the chop rounding function

• UpdatedFeb 14, 2023
• MATLAB