PAPI: Exploiting Dynamic Parallelism in Large Language Model with a PIM System [ASPLOS'25 Talk]

Talk title: "PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System"
Full Talk at ASPLOS 2025 by Yintao He
20 minutes

Appears in Architectural Support for Programming Languages and Operating Systems (ASPLOS), Rotterdam, Netherlands — March 30 - April 3, 2025
https://asplos-conference.org
Session 9B: Processing in Memory

Paper (pdf): https://arxiv.org/pdf/2502.15470

Slides (pptx): https://people.inf.ethz.ch/omutlu/pub...
Slides (pdf): https://people.inf.ethz.ch/omutlu/pub...

Recommended Reading:
====================
Intelligent Architectures for Intelligent Computing Systems
https://people.inf.ethz.ch/omutlu/pub...

A Modern Primer on Processing in Memory
https://people.inf.ethz.ch/omutlu/pub...

RowHammer: A Retrospective
https://people.inf.ethz.ch/omutlu/pub...


RECOMMENDED LECTURE VIDEOS & PLAYLISTS:
========================================
Computer Architecture Fall 2021 Lectures Playlist:
   • Computer Architecture - Lecture 1: In...  

Digital Design and Computer Architecture Spring 2021 Livestream Lectures Playlist:
   • Onur Mutlu - Digital Design and Compu...  

Featured Lectures:
   • Onur Mutlu - Supercomputing Frontiers...  

Interview with Professor Onur Mutlu:
   • Interview with Onur Mutlu @ ISCA 2019...  

The Story of RowHammer Lecture:
   • The Story of Rowhammer - Secure Hardw...  

Accelerating Genome Analysis Lecture:
   • Accelerating Genome Analysis: A Prime...  

Memory-Centric Computing Systems Tutorial at IEDM 2021:
   • IEDM 2020 Tutorial: Memory-Centric Co...  

Intelligent Architectures for Intelligent Machines Lecture:
   • Onur Mutlu - Invited Talk @ Seoul Nat...  

Computer Architecture Fall 2020 Lectures Playlist:
   • Computer Architecture - Lecture 1: In...  

Digital Design and Computer Architecture Spring 2020 Lectures Playlist:
   • Digital Design & Computer Architectur...  

Public Lectures by Onur Mutlu, Playlist:
   • Onur Mutlu - Future Computing Archite...  

Computer Architecture at Carnegie Mellon Spring 2015 Lectures Playlist:
   • Lecture 1. Introduction and Basics - ...  

Rethinking Memory System Design Lecture @stanfordonline :
   • Stanford Seminar - Rethinking Memory ...