Implementing High-Precision Decimal Arithmetic with CUDA int128 | NVIDIA Technical Blog

This post details CUDA’s new int128 support and how to implement decimal fixed-point arithmetic on top of it.

Implementing High-Precision Decimal Arithmetic with CUDA int128 | NVIDIA Technical Blog Technical Blog Subscribe Related Resources Data Science English 中文 Implementing High-Precision Decimal Arithmetic with CUDA int128 Feb 10, 2022 By Conor Hoekstra , Kuhu Shukla and Mark Harris Like Discuss (0) L T F R E AI-Generated Summary Like Dislike The introduction of __int128 support in NVIDIA CUDA 11.5 enables the implementation of 128-bit decimal fixed-point arithmetic in the RAPIDS cuDF library. The fixed_point type in RAPIDS libcudf provides a way to represent real numbers with a fixed number

related reading

• How to Optimize a CUDA Matmul Kernel for cuBLAS-like Performance: a Worklogsiboehm.com
• 1. Introduction — Floating Point and IEEE 754 13.3 documentationdocs.nvidia.com
• The Best GPUs for Deep Learning in 2023 — An In-depth Analysistimdettmers.com
• What happens when you run a CUDA kernelfergusfinn.com
• CUTLASS: Fast Linear Algebra in CUDA C++ | NVIDIA Technical Blogdeveloper.nvidia.com
• CUDA Programming Guide — CUDA Programming Guidedocs.nvidia.com
• Inside NVIDIA GPUs: Anatomy of high performance matmul kernels - Aleksa Gordićaleksagordic.com
• ⭐️ Fast LLM Inference From Scratchandrewkchan.dev
• CUDA C++ Programming Guide (Legacy) — CUDA C++ Programming Guidedocs.nvidia.com
• How to Think About GPUs | How To Scale Your Modeljax-ml.github.io
• Outperforming cuBLAS on H100: a Worklogcudaforfun.substack.com
• Worklog: Optimising GEMM on NVIDIA H100 for cuBLAS-like Performance (WIP) – Hamza's Bloghamzaelshafie.bearblog.dev