The Center for Research Computing's (CRC) Software Development team, in collaboration with Marc Muller, assistant professor in the Department of Civil and Environmental Engineering and Earth Sciences, and graduate student Lauren McGiven, has been developing a water sharing simulation game called Thirsty Earth.

Two students in a Thirsty Earth village group discuss their water and crop choices for the year.

How the game works:

The game places each player as one of several farmers that share a finite water basin. The players must choose whether to plant crops in each of their fields as well as whether to water each field using expensive but dependable groundwater or free yet unpredictable rainwater. Based on the rainfall amount, each player earns a certain amount of profit depending on all of the choices of players in the village as well as how depleted the water basin is from past choices.

First impressions:

The game was launched on March 27 and played by undergraduate students for the first time. Thirty students were divided into four villages and played Thirsty Earth over the course of a few classes. They were able to see how their collective decisions about a key shared resource impacted each other and the overall prosperity of their village through this gamified learning experience.

Members of the CRC were able to observe the lecture and gameplay firsthand—an extremely rewarding opportunity to see how hard work can enhance the education of the next generation of leaders.

The impact:

The research work for Thirsty Earth will continue through the summer and fall semesters as the CRC prepares the game for additional gameplay and data collection through Amazon Mechanical Turk.

Project architecture and approach:

This project utilizes the boardgame.io Javascript game framework. This framework provides the turn structure required for game development. Boardgame.io utilizes React.js to display frontend components as required for the gameplay. Koa.js, a Node.js framework, is used for the project backend.

Broader Impacts:

Questions posed to be answered:

With goals of:

Cybercrimes Iinvestigations, Research and Education Initiative (CIRE) Managing Director Mitch Kajzer and KPMG Cyber Threat Management Associate Ana Miravete (ND ‘22) spoke at the South Coast Cyber Summit in Beaufort, SC. The theme for the summit was "Building Cyber Talent for Our Nation’s Future." Kajzer discussed how CIRE is partnering with industry leaders and law enforcement to provide investigative experience, research, and education for the next generation of cyber workers. Miravete discussed how her Notre Dame education, along with two years of work experience in the Cyber Crimes Unit, prepared her for her career at KPMG. The two-day summit was attended by over 400 industry professionals from throughout South Carolina.

CRC intern and psychology student Ella Neading recently presented her lead author paper titled "Review of Integrated STEM+C e-Learning Platforms to Support Underrepresented Students" at the annual IEEE Integrated STEM Education Conference held at Johns Hopkins University. Excellent work Ella!

CuPy is a powerful Python library that can be used as a replacement for NumPy and SciPy to accelerate computations using Graphics Processing Units (GPUs). With CuPy, users can significantly speed up their computations and tackle larger and more complex problems than they could with CPU-based computations alone. One of the key benefits of using CuPy over NumPy and SciPy is its ability to perform operations in parallel. GPUs have thousands of processing cores that can be used to execute multiple calculations simultaneously, making them ideal for computationally-intensive tasks. CuPy provides a NumPy-compatible interface that allows users to easily switch between NumPy and CuPy functions without having to change their code.

CuPy also includes a number of built-in functions that are optimized for GPU performance, such as matrix multiplication and FFTs. These functions can be several times faster than their NumPy counterparts, making CuPy a great choice for scientific and engineering applications. To illustrate how CuPy can be used as a replacement for NumPy to accelerate computations, let's consider the example of matrix multiplication. Matrix multiplication is a computationally-intensive task that is used in many scientific and engineering applications. Using NumPy, we can perform matrix multiplication as follows:

import numpy as np
# Create two random matrices
a = np.random.rand(1000, 1000)
b = np.random.rand(1000, 1000)
# Perform matrix multiplication
c = np.dot(a, b)

This code will perform matrix multiplication on the CPU and can take several seconds to complete. However, by using CuPy, we can perform the same operation on the GPU and achieve significant speedup.

import cupy as cp
# Create two random matrices
a = cp.random.rand(1000, 1000)
b = cp.random.rand(1000, 1000)
# Perform matrix multiplication
c = cp.dot(a, b)

This code is very similar to the NumPy example, but with the imports changed to use CuPy instead. The dot function in CuPy is optimized for GPU performance and can perform matrix multiplication much faster than NumPy on the CPU.

In conclusion, CuPy is a powerful tool for accelerating computations using GPUs. Its compatibility with NumPy and SciPy, built-in optimized functions, and convenience features make it an attractive choice for users who want to take advantage of GPU computing. Users can achieve significant speedups for computationally-intensive tasks, allowing them to tackle larger and more complex problems than they could with CPU-based computations alone. 

Every Wednesday and Thursday in March
2:00 – 3:00 p.m.
Flanner Hall, CRC Training Room 812 (map)

This training is available to new users and current users interested in a refresher course on how to use CRC resources. Attendees learn the basics of accessing CRC resources and submitting jobs on the CRC clusters. This course is a co-requisite when receiving a CRC account. Learn more.

Friday, April 28, 2023
10:00 a.m. – 4:00 p.m.
McKenna Hall (map)

Please join Notre Dame's Center for Research Computing for a discussion about artificial intelligence and how engineering research is needed to learn more about the intrinsics of AI. Learn more.

735,153
Civil & Environmental Engineering & Earth Sciences

573,567.9
Civil & Environmental Engineering & Earth Sciences

481,175.2
Aerospace & Mechanical Engineering

388,457.8
Aerospace & Mechanical Engineering

332,370.3
Civil Engineering & Geological Sciences

249,900.9
College of Business Administration

234,652.4
Physics

192,240.9
Chemical & Biomolecular Engineering

160,805.1
Chemistry and Biochemistry

146,968.5
Aerospace & Mechanical Engineering