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.

Conversion to/from half-precision floating point formats

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

ES2025 float16 (IEEE 754 half-precision floating-point) ponyfill/proposal since 2017

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

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

half float library for C and for z80

Round matrix elements to lower precision in MATLAB

C++ template library for floating point operations

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

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

Floating-Point Arithmetic Library for Z80

CUDA/HIP header-only library for low-precision (16 bit, 8 bit) and vectorized GPU kernel development

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

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

Fast SGEMM emulation on Tensor Cores

Swift Half-Precision Floating Point

Half-Precision Floating-Point for Delphi

WMMA GEMM in ROCm for RDNA GPUs

Basic linear algebra routines implemented using the chop rounding function

Minimal half-precision floating point types f16 and bf16 for Rust.

No description provided.

Size (in bytes) of a half-precision floating-point number.

Half-precision 16-bit floating point numbers

Square root of half-precision floating-point epsilon.

The DYM Math Library for Graphics and Game Programming

Emulating binary, half-precision IEEE-754 (2008) floats

Half-precision floating-point mathematical constants.

Complete software implementation of half precision IEEE 754 float16 written in c99

16-bit half-precision floating-point number.