Related papers: A Software-based NVM Emulator Supporting Read/Writ…
Resistive memory (RM) based neuromorphic systems can emulate synaptic plasticity and thus support continual learning, but they generally lack biologically inspired mechanisms for active forgetting, which are critical for meeting modern data…
Data movement between memory and processors is a major bottleneck in modern computing systems. The processing-in-memory (PIM) paradigm aims to alleviate this bottleneck by performing computation inside memory chips. Real PIM hardware (e.g.,…
Memristor, one of the fundamental circuit elements, has promising applications in non-volatile memory and storage technology as it can theoretically achieve infinite states. Information can be stored independently in these states and…
Emerging non-volatile memory technologies (NVRAM) offer alternatives to hard drives that are persistent, while providing similar latencies to DRAM. Intel recently released the Optane drive, which features 3D XPoint memory technology. This…
Main memories play an important role in overall energy consumption of embedded systems. Using conventional memory technologies in future designs in nanoscale era causes a drastic increase in leakage power consumption and temperature-related…
We study the design of storage-efficient algorithms for emulating atomic shared memory over an asynchronous, distributed message-passing system. Our first algorithm is an atomic single-writer multi-reader algorithm based on a novel…
Neural network (NN) emulators of the global 21 cm signal need emulation error much less than the observational noise in order to be used to perform unbiased Bayesian parameter inference. To this end, we introduce $\texttt{21cmLSTM}$ -- a…
Reliable storage emulations from fault-prone components have established themselves as an algorithmic foundation of modern storage services and applications. Most existing reliable storage emulations are built from storage services…
Hierarchical Temporal Memory (HTM) is a biomimetic machine learning algorithm imbibing the structural and algorithmic properties of the neocortex. Two main functional components of HTM that enable spatio-temporal processing are the spatial…
Recently, there has been an extensive research effort in building efficient large language model (LLM) inference serving systems. These efforts not only include innovations in the algorithm and software domains but also constitute…
The inherent dynamics of the neuron membrane potential in Spiking Neural Networks (SNNs) allows processing of sequential learning tasks, avoiding the complexity of recurrent neural networks. The highly-sparse spike-based computations in…
Applications of Binary Neural Networks (BNNs) are promising for embedded systems with hard constraints on computing power. Contrary to conventional neural networks with the floating-point datatype, BNNs use binarized weights and activations…
Processing-in-memory (PIM) has shown extraordinary potential in accelerating neural networks. To evaluate the performance of PIM accelerators, we present an ISA-based simulation framework including a dedicated ISA targeting neural networks…
Many modern workloads such as neural network inference and graph processing are fundamentally memory-bound. For such workloads, data movement between memory and CPU cores imposes a significant overhead in terms of both latency and energy. A…
Modern NVMM is closing the gap between DRAM and persistent storage, both in terms of performance and features. Having both byte addressability and persistence on the same device gives NVMM an unprecedented set of features, leading to the…
Sequence alignment is a memory bound computation whose performance in modern systems is limited by the memory bandwidth bottleneck. Processing-in-memory architectures alleviate this bottleneck by providing the memory with computing…
Neural networks (NNs) can achieved high performance in various fields such as computer vision, and natural language processing. However, deploying NNs in resource-constrained safety-critical systems has challenges due to uncertainty in the…
The deployment of Large Language Models (LLMs) on edge devices is fundamentally constrained by the "Memory Wall" the bottleneck where data movement latency outstrips arithmetic throughput. Standard inference runtimes often incur significant…
Frequent-pattern mining is a common approach to reveal the valuable hidden trends behind data. However, existing frequent-pattern mining algorithms are designed for DRAM, instead of persistent memories (PMs), which can lead to severe…
Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy…