Access more resources about UPMEM

We have gathered a selection of past and on-going works related to UPMEM’s technology, often involving renowned Universities with links to access to papers, videos and open source code when available. For clarity purposes sections are sorted by fields of interest:

Last updated on November 2023

General overview and architecture

TitleStatusAuthorsPaper/resourceCode
UPMEM PIM platform for Data-Intensive ApplicationsPublished
(Euro-Par 2023)
UPMEMVideo
Slide deck
NA
A survey on hardware accelerators: Taxonomy, trends, challenges, and perspectivesPublished
(JSA 2022)
University of Sienna / HuaweiPaperNA
Architecture programming tools overview, showcasing genomics/analytics applications using UPMEM Processing In MemoryPublished
(HIPEAC 2021)
UPMEMVideo
SDK Documentation
GitHub

General performances and micro-benchmarks

TitleStatusAuthorsPaper/resourceCode
Energy Efficiency Impact of Processing in Memory: A Comprehensive Review of Workloads on the UPMEM ArchitecturePublished
(PECS 2023, co-located with Euro-PAR 2023)
UPMEMPaperNA
Benchmarking a New Paradigm: An Experimental Analysis of a Real Processing-in-Memory Architecture
Published
(IGSC 2021)
ETH ZurichFull paper
Video
GitHub
Benchmarking Memory-Centric Computing Systems: Analysis of Real Processing-In-Memory HardwarePublished
(CUT 2021)
ETH ZurichPaper
Video
GitHub
A Case Study of Processing-in-Memory in off-the-Shelf Systems
Published
(USENIX 2021)
University of British ColumbiaPaper
Video
GitHub

Compiler / programming model

TitleStatusAuthorsPaper/resourceCode
SimplePIM: A Software Framework for Productive and Efficient Processing-in-MemoryPublished
(PACT 2023)
ETH Zürich / American University of BeirutPaperAvailable soon
CINM (Cinnamon): A Compilation Infrastructure for Heterogeneous Compute In-Memory and Compute Near-Memory ParadigmsPublished (2023)TU Dresden / IntelPaperAvailable soon

Libraries

TITLESTATUSAUTHORSPAPER/RESOURCE CODE
PID-Comm: A Fast and Flexible Collective Communication Framework for Commodity Processing-in-DIMM DevicesAccepted to ISCA'24Seoul National University / Yonsei UniversityPaperGitHub
TransPimLib: A Library for Efficient Transcendental Functions on Processing-in-Memory SystemsPublished
(ISPASS 2023)
ETH ZurichPaperGitHub
SparseP: Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory SystemsPublished
(POMACS 2022)
ETH ZurichPaperGitHub

Genomics & Bioinformatics

TitleStatusAuthorsPaper/resourceCode
UpPipe: A Novel Pipeline Management on In-Memory Processors for RNA-seq QuantificationPaper accepted
(DAC 2023)
National Cheng Kung UniversityPaper
GitHub
A Framework for High-throughput Sequence Alignment using Real Processing-in-Memory SystemsPublished
(Hi Comb 2022)
ETH ZurichPaperGitHub
Variant Calling Parallelization on Processor-in-Memory Architecture
Published
(BIBM 2021)
IRISA / CNRS / INRIAPaperGitHub
BLAST software on the UPMEM architecturePublished (2016)INRIAPaperUpon request

Analytics & Database

TitleStatusAuthorPaper/resourceCode
UPMEM-PIM Evaluation for SQL JOIN Query AccelerationCompletedUPMEM /
Private company
Upon requestGitHub
pimDB: From Main-Memory DBMS to Processing-In-Memory DBMS-Engines on Intelligent MemoriesPublished
(DaMoN '23)
Reutlingen University / TU DarmstadtPaperNA
Design and Analysis of a Processing-in-DIMM Join Algorithm: A Case Study with UPMEM DIMMsPaper accepted
(SIGMOD 2023)
Yonsei University / Seoul National UniversityPaperGitHub
Adaptive Query Compilation with Processing-in-MemoryPublished
(HardBD 2023)
TU IlmenauPaperNA
Accelerating Large Table Scan using Processing-In-Memory TechnologyPublished
(BTW 2023)
TU IlmenauPaperGitHub
PIM-tree: A Skew-resistant Index for Processing-in-MemoryPublished
(VLDB Endowment Volume 16
Issue 4 2022)
Carnegie Mellon University PaperGitHub

Machine Learning / Deep Learning

TitleStatusAuthorsPaper/resourceCode
An Experimental Evaluation of Machine Learning Training on a Real Processing-in-Memory SystemPublished
(ISPASS 2023)
ETH ZurichPaperGitHub
Implementation and Evaluation of Deep Neural Networks in Commercially Available Processing in Memory HardwarePublished
(SOCC 2022)
Rochester Institute of TechnologyPaper
Master's thesis
NA
An implementation of a deep learning recommendation model (DLRM)On-goingUniversity of British ColumbiaMaster's thesis
GitHub

Security

TITLESTATUSAUTHORSPAPER/RESOURCE CODE
Evaluating Homomorphic Operations on a Real-World Processing-In-Memory SystemPublished
(2023)
ETH ZürichPaperNA