Related papers: Survey of Persistent Memory Correctness Conditions
Self-sustained, elevated neuronal activity persisting on time scales of ten seconds or longer is thought to be vital for aspects of working memory, including brain representations of real space. Continuous-attractor neural networks, one of…
Non-volatile memory is expected to co-exist or replace DRAM in upcoming architectures. Durable concurrent data structures for non-volatile memories are essential building blocks for constructing adequate software for use with these…
Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on 'blurry' task…
The difficulty of developing reliable parallel software is generating interest in deterministic environments, where a given program and input can yield only one possible result. Languages or type systems can enforce determinism in new code,…
Non-volatile memory (NVM) is an emerging technology, which has the persistence characteristics of large capacity storage devices(e.g., HDDs and SSDs), while providing the low access latency and byte-addressablity of traditional DRAM memory.…
Dynamic random access memory failures are a threat to the reliability of data centres as they lead to data loss and system crashes. Timely predictions of memory failures allow for taking preventive measures such as server migration and…
The focus of this paper is on causal consistency in a {\em partially replicated} distributed shared memory (DSM) system that provides the abstraction of shared read/write registers. Maintaining causal consistency in distributed shared…
Concurrency and determinacy do not go well with each other when resources must be shared. Haskell provides parallel programming abstractions such as IVar and LVar in the Par monad and concurrent abstractions such as MVar and TVar in the in…
We propose a memory-model-aware static program analysis method for accurately analyzing the behavior of concurrent software running on processors with weak consistency models such as x86-TSO, SPARC-PSO, and SPARC-RMO. At the center of our…
Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…
Persistent memory (PM) technologies have inspired a wide range of PM-based system optimizations. However, building correct PM-based systems is difficult due to the unique characteristics of PM hardware. To better understand the challenges…
Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurrent unit (GRU). However, the dynamic properties behind the…
Neuron models of associative memory provide a new and prospective technology for reliable date storage and patterns recognition. However, even when the patterns are uncorrelated, the efficiency of most known models of associative memory is…
In-memory deep learning computes neural network models where they are stored, thus avoiding long distance communication between memory and computation units, resulting in considerable savings in energy and time. In-memory deep learning has…
In this review we discuss the persistence and the related first-passage properties in extended many-body nonequilibrium systems. Starting with simple systems with one or few degrees of freedom, such as random walk and random acceleration…
In continual learning, a system learns from non-stationary data streams or batches without catastrophic forgetting. While this problem has been heavily studied in supervised image classification and reinforcement learning, continual…
Memory dumps that are acquired while the system is running often contain inconsistencies like page smearing which hamper the analysis. One possibility to avoid inconsistencies is to pause the system during the acquisition and take an…
Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…
Deep neural networks for computer vision are deployed in increasingly safety-critical and socially-impactful applications, motivating the need to close the gap in model performance under varied, naturally occurring imaging conditions.…
Recurrent Neural Networks (RNNs) with Long Short-Term Memory units (LSTM) are widely used because they are expressive and are easy to train. Our interest lies in empirically evaluating the expressiveness and the learnability of LSTMs in the…