https://github.com/aeyage/intraday_prices

GPU-accelerated portfolio optimisation
https://github.com/aeyage/intraday_prices

cuda cupy nvidia-gpu

Last synced: 7 months ago
JSON representation

GPU-accelerated portfolio optimisation

• Host: GitHub
• URL: https://github.com/aeyage/intraday_prices
• Owner: aeyage
• License: mit
• Created: 2025-02-09T03:56:11.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-02-09T10:26:42.000Z (8 months ago)
• Last Synced: 2025-02-09T11:25:33.840Z (8 months ago)
• Topics: cuda, cupy, nvidia-gpu
• Language: Jupyter Notebook
• Homepage:
• Size: 10.7 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
## Portfolio Optimisation on GPU

Demonstration on how to perform financial computations i.e. portfolio optimisation using both CPU (with `pandas` and `NumPy`) and GPU (with `cuDF` and `CuPy`). The goal is to compare the performance of CPU and GPU for these computations.

---

RAPIDS is a suite of GPU-accelerated data science and AI libraries from Nvidia. It is built on NVIDIA CUDA-X AI™ and includes libraries that integrate with popular data science software.

Part of the problem with pandas is that it can be slow with large datasets. That is where `cuDF-pandas comes` in. `cuDF-pandas` accelerates pandas with zero code changes and brings great speed improvements.

`cuDF-pandas` is available as an extension that requires no code changes at all. To use it, just add the following code before you import pandas.

```sh

%load_ext cudf.pandas

```