Litcius/Paper detail

A Review of 3D-Dynamic Random-Access Memory based Near-Memory Computation

Prasanth Prabu Ravichandiran, Paul D. Franzon

202114 citationsDOI

Abstract

The growth of Neural Networks (NNs) and Machine Learning (ML) usage has rapidly increased over the last decade. Traditional dynamic random-access memory (DRAM) is struggling to meet the computational, throughput demands of these NNs and has become a bottleneck in the system. One of the commonly proposed solutions is Near-Memory Computation (NMC) hardware accelerators to move the computation closer to the data resulting in improved throughput and reduced power consumption. In this paper, we analyze a few critical NMC architecture implementations, specifically those with 3D-Stacked DRAM memory. We have organized a literature review across structures, configuration, application, performance metrics, and present challenges and opportunities.

Topics & Concepts

BottleneckDramComputer scienceDynamic random-access memoryComputationThroughputRandom accessParallel computingComputer architectureImplementationRandom access memoryMemory architecturePower consumptionArtificial neural networkDistributed computingComputer engineeringEmbedded systemPower (physics)Semiconductor memoryComputer hardwareArtificial intelligenceOperating systemAlgorithmProgramming languageQuantum mechanicsWirelessPhysicsAdvanced Memory and Neural ComputingFerroelectric and Negative Capacitance DevicesParallel Computing and Optimization Techniques
A Review of 3D-Dynamic Random-Access Memory based Near-Memory Computation | Litcius