Originally published at: https://developer.nvidia.com/blog/implementing-high-precision-decimal-arithmetic-with-cuda-int128/
This post details CUDA’s new int128 support and how to implement decimal fixed-point arithmetic on top of it.
jwitsoe
1
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Emulated double precision Double single routine header | 24 | 49119 | October 18, 2010 | |
| Bitslice-DES optimization | 55 | 12589 | January 29, 2022 | |
| Possible to use the CUDA math API integer intrinsics to find the nth unset bit in a 32 bit int | 37 | 8405 | March 1, 2015 | |
| Accuracy of 1D linear interpolation by CUDA texture interpolation | 25 | 14610 | January 29, 2013 | |
| CUDA Pro Tip: Use cuFFT Callbacks for Custom Data Processing | 18 | 1198 | August 15, 2023 | |
| Mixed-Precision Programming with CUDA 8 | 1 | 383 | February 23, 2017 | |
| A more accurate, performance-competitive implementation of expf() | 24 | 8039 | November 19, 2017 | |
| Accuracy in GPU floating point calculations | 35 | 8219 | September 9, 2011 | |
| GPU/CPU precision comparison and Kernel instructions question | 5 | 676 | April 4, 2017 | |
| Optimized version of single-precision error function, erff() | 21 | 4416 | December 25, 2017 |