# AIaccelerators-SC23-tutorial

**Repository Path**: lomberer/AIaccelerators-SC23-tutorial

## Basic Information

- **Project Name**: AIaccelerators-SC23-tutorial
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: habana
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-07-27
- **Last Updated**: 2025-07-27

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Programming Novel AI Accelerators for Scientific Computing

Scientific applications are increasingly adopting Artificial Intelligence (AI) techniques to advance science. There are specialized hardware accelerators designed and built to run AI applications efficiently. With a wide diversity in the hardware architectures and software stacks of these systems, it is challenging to understand the differences between these accelerators, their capabilities, programming approaches, and how they perform, particularly for scientific applications. 

In this tutorial, we will cover an overview of the AI accelerators landscape with a focus on SambaNova, Cerebras, Graphcore, Groq, and Habana systems along with architectural features and details of their software stacks. We will have hands-on exercises that will help attendees understand how to program these systems by learning how to refactor codes written in standard AI framework implementations and compile and run the models on these systems. The tutorial will enable the attendees with an understanding of the key capabilities of emerging AI accelerators and their performance implications for scientific applications.


## Tutorial at SC23

| Date      | Sunday, 12 November 2023     |
|-----------|------------------------------|
| Time      | 8:30am - 12:00pm MST         |
| Location  | 203. Colorado Convention Center, Denver, CO |


## Agenda

| Time (MST)          | Topic                                                   |
|--------------------|---------------------------------------------------------|
| 08.30 - 8.35       |  [Introduction to AI Testbed at ALCF (ANL)]()                  
| 08.35 - 8.50       |  [Claire Zhang (Cerebras Systems)](./Slides/SC23_Tutorial_Cerebras.pdf)
| 08.50 - 9.05       |  [Petro Junior Milan (SambaNova Systems)](./Slides/SC23_Tutorial_SambaNova.pdf)                 
| 09.05 - 9.20       |  [Alex Tsyplikhin (Graphcore)](./Slides/SC23_Tutorial_Graphcore.pdf)                            
| 09.20 - 9.35       |  [Sanjif Shanmugavelu (Groq)](./Slides/SC23_Tutorial_Groq.pdf)                             
| 09.35 - 9.50       |  [Leon Tran (Intel Habana)](./Slides/SC23_Tutorial_Habana.pdf)                                     
| **10.00 - 10.30**  |  **Break**
| 10.30 - 12.00      |  Hands session on the AI Testbed (ANL)

## Hands-On Session

* [SambaNova](./SambaNova/README.md)                                    
* [Graphcore](./Graphcore/README.md)  
* [Cerebras](./Cerebras/README.md)    
* [Groq](./Groq/README.md)        
* [Habana](./Habana/README.md)      


## Request Account on AI Testbeds At ALCF

* Request an [ALCF Computer User Account](https://accounts.alcf.anl.gov/accountRequest) if you do not currently have one
* If you have an ALCF Account that is currently inactive, submit an [account reactivation](https://accounts.alcf.anl.gov/accountReactivate) request*.
* If you have an active ALCF account, click [Join Project](https://accounts.alcf.anl.gov/joinProject) to submit a membership request. Specify the following in your request: 
  Project Name: `aitestbed_tutorial`

Contact accounts@alcf.anl.gov M-F 9am to 5pm CT. 
Reach out to us on slack channel `#help-accounts` on [ALCF-AIAccelerator-tutorials](https://join.slack.com/t/alcf-aiacc-tutorials/shared_invite/zt-25yjc7tnm-AlqTNcWrbH0c1KVNEExTuw) Slack. 

>SC23 Tutorial allocation will stay active till end of November 2023. 

### Director’s Discretionary Allocation Program

To gain access to AI Testbeds at ALCF after tutorial allocation expires apply for [Director’s Discretionary Allocation Program](https://www.alcf.anl.gov/science/directors-discretionary-allocation-program)

The ALCF Director’s Discretionary program provides “start up” awards to researchers working to achieve computational readiness for for a major allocation award.



## Useful Links 

* [SC23 Tutorial Webpage](https://sc23.supercomputing.org/presentation/?id=tut139&sess=sess2121)
* [Github Tutorial Repository](https://github.com/argonne-lcf/AIaccelerators-SC23-tutorial)
* [Overview of AI Testbeds at ALCF](https://www.alcf.anl.gov/alcf-ai-testbed)
* [ALCF AI Testbed Documentation](https://www.alcf.anl.gov/support/ai-testbed-userdocs/)
* [Director’s Discretionary Allocation Program](https://www.alcf.anl.gov/science/directors-discretionary-allocation-program)
* [Join Slack Workspace](https://join.slack.com/t/alcf-aiacc-tutorials/shared_invite/zt-25yjc7tnm-AlqTNcWrbH0c1KVNEExTuw)

##### Acknowledgements

Contributors: [Siddhisanket (Sid) Raskar](https://sraskar.github.io/), Varuni Sastry, Bill Arnold, [Murali Emani](https://memani1.github.io/). 

> This research used resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357.