NVIDIA Developer Forums

Not enough GPU memory? Not a problem

AI & Data Science Data Science of the Day

jimscott January 6, 2021, 9:16pm 1

Did you know reading more data than there is #GPU memory isn't a problem? Here, we see that reading 100 million records (58 GB) from a CSV file 2–3x faster than with CPU.
Click the image to read the article
Find more #DSotD posts

1 Like

Topic		Replies	Views	Activity
Massive Speed-Ups for Massive Operations at Capital One Data Science of the Day python , fun-facts , dask , gpu	0	1006	January 27, 2021
Ever Try to Process a 100GB Dataset on a CPU? Can You Say Caffeine Addiction? #GoFastOrGoHome Data Science of the Day python , fun-facts , sql , rapids	0	1361	March 4, 2021
Executing RAPIDS from Your Computer (Without a Local GPU) Data Science of the Day python , fun-facts , gpu	0	1015	October 19, 2021
An Introduction to Distributed Computing with GPUs in Python Data Science of the Day python , fun-facts , dask , data-science	0	2055	March 29, 2021
Best Practices for Multi-GPU Data Analysis Using RAPIDS with Dask Technical Blog	0	201	November 21, 2024
Want to Get Improve Your Fraud Detection Game? Learn how This Kaggle Grandmaster Team Won Data Science of the Day python , gpu , data-science , machine-learning , fan-facts	0	997	March 5, 2021
Event Streaming on the GPU... Yep, It's a Thing! Data Science of the Day python , fun-facts , gpu	0	901	February 15, 2021
Imagine, Being Able to SQL Query 1TB of Data in 3 Seconds from S3! #BONKERS Data Science of the Day jupyterlab , fun-facts , gpu	0	1321	February 11, 2021
very large data set (big matrix) CUDA Programming and Performance	10	3265	October 17, 2009
Reduce TensorFlow GPU usage Jetson TX2	9	1540	June 20, 2019