SIMDRAM: A framework for bit-serial SIMD processing using DRAM

N Hajinazar, GF Oliveira, S Gregorio… - Proceedings of the 26th …, 2021 - dl.acm.org
Processing-using-DRAM has been proposed for a limited set of basic operations (ie, logic
operations, addition). However, in order to enable full adoption of processing-using-DRAM …

DAMOV: A new methodology and benchmark suite for evaluating data movement bottlenecks

GF Oliveira, J Gómez-Luna, L Orosa, S Ghose… - IEEE …, 2021 - ieeexplore.ieee.org
Data movement between the CPU and main memory is a first-order obstacle against improv
ing performance, scalability, and energy efficiency in modern systems. Computer systems …

DRAM bender: An extensible and versatile FPGA-based infrastructure to easily test state-of-the-art DRAM chips

A Olgun, H Hassan, AG Yağlıkçı… - … on Computer-Aided …, 2023 - ieeexplore.ieee.org
To understand and improve DRAM performance, reliability, security, and energy efficiency,
prior works study characteristics of commodity DRAM chips. Unfortunately, state-of-the-art …

Evaluating machine learningworkloads on memory-centric computing systems

J Gómez-Luna, Y Guo, S Brocard… - … Analysis of Systems …, 2023 - ieeexplore.ieee.org
Training machine learning (ML) algorithms is a computationally intensive process, which is
frequently memory-bound due to repeatedly accessing large training datasets. As a result …

A survey of resource management for processing-in-memory and near-memory processing architectures

K Khan, S Pasricha, RG Kim - Journal of Low Power Electronics and …, 2020 - mdpi.com
Due to the amount of data involved in emerging deep learning and big data applications,
operations related to data movement have quickly become a bottleneck. Data-centric …

To pim or not for emerging general purpose processing in ddr memory systems

A Devic, SB Rai, A Sivasubramaniam, A Akel… - Proceedings of the 49th …, 2022 - dl.acm.org
As Processing-In-Memory (PIM) hardware matures and starts making its way into normal
compute platforms, software has an important role to play in determining what to perform …

MIMDRAM: An End-to-End Processing-Using-DRAM System for High-Throughput, Energy-Efficient and Programmer-Transparent Multiple-Instruction Multiple-Data …

GF Oliveira, A Olgun, AG Yağlıkçı… - … Symposium on High …, 2024 - ieeexplore.ieee.org
Processing-using-DRAM (PUD) is a processing-in-memory (PIM) approach that uses a
DRAM array's massive internal parallelism to execute very-wide (eg, 16,384-262,144-bit …

An Experimental Evaluation of Machine Learning Training on a Real Processing-in-Memory System

J Gómez-Luna, Y Guo, S Brocard, J Legriel… - arXiv preprint arXiv …, 2022 - arxiv.org
Training machine learning (ML) algorithms is a computationally intensive process, which is
frequently memory-bound due to repeatedly accessing large training datasets. As a result …

Machine learning training on a real processing-in-memory system

J Gómez-Luna, Y Guo, S Brocard… - 2022 IEEE Computer …, 2022 - ieeexplore.ieee.org
Machine learning (ML) algorithms [1]–[6] have become ubiquitous in many fields of science
and technology due to their ability to learn from and improve with experience with minimal …

ALP: Alleviating CPU-memory data movement overheads in memory-centric systems

NM Ghiasi, N Vijaykumar, GF Oliveira… - … on Emerging Topics …, 2022 - ieeexplore.ieee.org
Partitioning applications between near-data processing (NDP) and host CPU cores causes
inter-segment data movement overhead, which is caused by moving data generated by one …