Live briefing
Everything about Mixed-precision arithmetic
Mixed-precision arithmetic is a form of floating-point arithmetic that uses numbers with varying widths in a single operation. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Mixed-precision arithmeticA 5-minute orientation
- Skim a recent paper: Mixed-Precision Ab Initio Tensor Network State Methods Adapted for NVIDIA Blackwell Technology via Emulated FP64 ArithmeticInfluential work since 2022
- Pick up a classic book: The Computer and the BrainThe most-reprinted book on the subject
- Read the landmark paper: A survey of numerical linear algebra methods utilizing mixed-precision arithmeticCited 136 times
- Go sideways: Model compressionA closely related topic
- Go sideways: MinifloatA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
A survey of numerical linear algebra methods utilizing mixed-precision arithmetic
Accelerating Restarted GMRES With Mixed Precision Arithmetic
Mixed-precision integer-arithmetic-only neural network-based equalizers for DML-based short-reach IM/DD systems
TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture
Analysis of the GCR method with mixed precision arithmetic using QuPAT
Accelerating interval matrix multiplication by mixed precision arithmetic
Reduced- and mixed-precision Runge–Kutta methods in floating-point arithmetic
🆕 Influential since 2022
📚 Books worth reading
The Computer and the BrainJohn von Neumann · 1958
Programming Massively Parallel ProcessorsDavid Kirk, Wen-Mei W. Hwu · 2010
Sit down and drink your beerCampbell, Robert A. · 2001
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Model compression Model compression is a machine learning technique for reducing the size of trained models. Large models can achieve high accuracy, but often at the cost…
- Minifloat In computing, minifloats are floating-point values represented with very few bits. This reduced precision makes them ill-suited for general-purpose numerical…
- Block floating point Block floating point (BFP) is a method used to provide an arithmetic approaching floating point while using a fixed-point processor. BFP assigns a group…
- Half-precision floating-point format Half precision (sometimes called FP16 or float16) is a binary floating-point computer number format that occupies 16 bits (two bytes in modern computers)…
- TensorFloat-32 TensorFloat-32 (TF32) is a numeric floating point format designed for Tensor Core running on certain Nvidia GPUs. It was first implemented in the Ampere…
- Bfloat16 floating-point format The bfloat16 (brain floating point) floating-point format is a computer number format occupying 16 bits in computer memory; it represents a wide dynamic…
- Machine epsilon Machine epsilon or machine precision is an upper bound on the relative approximation error due to rounding in floating point number systems. This value…
- Irrational base discrete weighted transform In mathematics, the irrational base discrete weighted transform (IBDWT) is a variant of the fast Fourier transform using an irrational base; it was developed…