Differences

This shows you the differences between two versions of the page.

--- start [2024/10/23 12:44] – [Tutorial Materials] geraldod
+++ start [2024/11/02 20:52] (current) – [Tutorial Materials] mnika
@@ Line 49: / Line 49: @@
 ^ Time ^ Speaker ^ Title ^ Materials ^
-| 01:00pm-01:30pm   | Prof. Onur Mutlu / Geraldo F. Oliveira | Memory-Centric Computing |{{|(PDF)}} {{|(PPT)}}|
+| 01:00pm-01:30pm   | Prof. Onur Mutlu / Geraldo F. Oliveira | Memory-Centric Computing |{{geraldo-micro24-lecture1-memory-centric-computing-beforelecture.pdf|(PDF)}} {{geraldo-micro24-lecture1-memory-centric-computing-beforelecture.pptx|(PPT)}}|
-| 01:30pm-02:00pm   | Geraldo F. Oliveira | Processing-Near-Memory Systems: Academia & Industry Developments | {{|(PDF)}} {{|(PPT)}}|
+| 01:30pm-02:00pm   | Geraldo F. Oliveira | Processing-Near-Memory Systems: Developments fro Academia & Industry | {{geraldo-micro24-lecture2-processing-near-memory-beforelecture.pdf|(PDF)}} {{geraldo-micro24-lecture2-processing-near-memory-beforelecture.pptx|(PPT)}}|
-| 02:00pm-02:30pm   | [[https://brian-schwedock.github.io/|Dr. Brian Schwedock]] | Architectures and Programming Models for General-Purpose Near-Data Computing | {{|(PDF)}} {{|(PPT)}}|
+| 02:00pm-02:30pm   | [[https://brian-schwedock.github.io/|Dr. Brian Schwedock]] | Architectures and Programming Models for General-Purpose Near-Data Computing | {{2024.pim-micro.ndc.pdf|(PDF)}} {{2024.pim-micro.ndc.pptx|(PPT)}}|
-| 02:30pm-03:00pm   | [[https://cgiannoula.github.io/|Dr. Christina Giannoula]] | System Software and Libraries for Sparse Computational Kernels in PIM Architectures |{{|(PDF)}} {{|(PPT)}}|
+| 02:30pm-03:00pm   | Geraldo F. Oliveira | Processing-Using-Memory Systems for Bulk Bitwise Operations |{{geraldo-micro24-lecture3-processing-using-memory-beforelecture.pdf|(PDF)}} {{geraldo-micro24-lecture3-processing-using-memory-beforelecture.pptx|(PPT)}}|
 | 03:00pm-03:30pm  | N/A | Coffee Break | |
-| 03:30pm-03:30pm  | Geraldo F. Oliveira | Processing-Using-Memory Systems for Bulk Bitwise Operations |{{|(PDF)}} {{|(PPT)}}|
+| 03:30pm-04:00pm  | Ataberk Olgun | Infrastructure for Processing-Using-Memory Research |{{2024_micro_pim_tutorial_dram_pum_infrastructure.pdf|(PDF)}} {{2024_micro_pim_tutorial_dram_pum_infrastructure.pptx|(PPT)}}|
-| 04:00pm-04:30pm  | Ataberk Olgun | Infrastructure for Processing-Using-Memory Research | {{|(PDF)}} {{|(PPT)}}|
+| 04:00pm-04:30pm  | [[https://cgiannoula.github.io/|Dr. Christina Giannoula]] | System Software and Libraries for Sparse Computational Kernels in PIM Architectures | {{sparselibraries_pim.pdf|(PDF)}} {{sparselibraries_pim.pptx|(PPT)}}|
-| 04:30pm-05:30pm  | Nika Mansouri Ghiasi | Storage-Centric Computing for Genomics and Metagenomics |{{|(PDF)}} {{|(PPT)}}|
+| 04:30pm-05:00pm  | Nika Mansouri Ghiasi | Storage-Centric Computing for Genomics and Metagenomics |{{pim-tutorial-micro24-nika-v2.pdf|(PDF)}} {{pim-tutorial-micro24-nika-v2.pptx|(PPT)}}|
-| 05:00pm  | Geraldo F. Oliveira | Research Challenges for PIM & Closing Remarks |{{|(PDF)}} {{|(PPT)}}|
+| 05:00pm  | Geraldo F. Oliveira | Research Challenges for PIM & Closing Remarks |{{geraldo-micro24-lecture4-adoption-programmability-beforelecture.pdf|(PDF)}} {{geraldo-micro24-lecture4-adoption-programmability-beforelecture.pptx|(PPT)}}|
 ==== Invited Speakers ====
 === Dr. Brian C. Schwedock ===
-**Talk Tile:** Architectures and Programming Models for General-Purpose Near-Data Computing{{ ::brian_headshot.jpg?nolink&200|}}
+**Talk Title:** Architectures and Programming Models for General-Purpose Near-Data Computing{{ ::brian_headshot.jpg?nolink&200|}}
 **Talk Abstract:** As computer systems are increasingly bottlenecked by data movement, traditional CPU scaling can no longer meet processing demands. To continue improving performance and energy efficiency, novel data-centric architectures move compute closer to data, typically by adding compute resources near data storage. Although these near-data computing (NDC) architectures promise significant gains in performance and energy efficiency, they are often limited by targeting a narrow range of application domains. In this talk, we present two architectures, täkō and Leviathan, that generalize NDC by adding programmable compute resources within the memory hierarchy and providing flexible, easy-to-use programming interfaces. By enabling architectures to implement a wide range of data-centric optimizations, täkō and Leviathan provide a path toward practical NDC.
@@ Line 69: / Line 69: @@
 === Dr. Christina Giannoula ===
-**Talk Tile:** System Software and Libraries for Sparse Computational Kernels in PIM Architectures{{ ::christina_headshot.jpg?nolink&200|}}
+**Talk Title:** System Software and Libraries for Sparse Computational Kernels in PIM Architectures{{ ::christina_headshot.jpg?nolink&200|}}
+**Talk Abstract:** Processing-In-Memory (PIM) offers a promising solution to alleviate the data movement bottleneck between memory and processors. Several manufacturers have already started to commercialize PIM architectures, providing significant performance and energy improvements for memory-intensive workloads. This talk will explore how specialized libraries and system software can unlock the potential of PIM architectures. I will first present SparseP, the first comprehensive Sparse Matrix Vector Multiplication (SpMV) library for real-world PIM systems. SparseP explores various parallelization strategies, load balancing, and synchronization techniques across thousands of PIM cores, offering insights into performance and energy efficiency benefits. Then, I will briefly introduce PyGim, a novel Graph Neural Network (GNN) library tailored for PIM systems, which optimizes memory-intensive GNN kernels through intelligent parallelization strategies. Our evaluations demonstrate that PyGim provides significant performance and energy improvements over prior state-of-the-art approaches.
-**Talk Abstract:**
 **Bio:** [[https://cgiannoula.github.io/#home|Christina Giannoula]] received the Ph.D. degree from the School of Electrical and Computer