NVIDIA / MatX

An efficient C++17 GPU numerical computing library with Python-like syntax

Home Page:https://nvidia.github.io/MatX

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[FEA] Use CUB 2.2's Decoupled Lookback on filter()

cliffburdick opened this issue · comments

CUB 2.2 added an optimized decoupled lookback with backoff, and opened the API for other algorithms. This task is to investigate and/or integrate this API into the IIR filter() function that uses its own decoupled lookback implementation.