flâneur — a map of the web's best reading

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

developer.nvidia.com · 4,395 words · saved by 1 readers

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

Explore this link on the map →

related reading