Related papers: Improving 3D NAND Flash Memory Lifetime by Tolerat…
Feature embedding-based methods have shown exceptional performance in detecting industrial anomalies by comparing features of target images with normal images. However, some methods do not meet the speed requirements of real-time inference,…
Emerging applications, such as big data analytics and machine learning, require increasingly large amounts of main memory, often exceeding the capacity of current commodity processors built on DRAM technology. To address this, recent…
To overcome the well-known memory bottleneck of AI chips, 3D stacked architectures that employ advanced packaging technology with high-density through-silicon vias (TSVs) pins have proven to be a promising solution. The 3D-stacked AI chip…
Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities.…
Large-scale systems with all-flash arrays have become increasingly common in many computing segments. To make such systems resilient, we can adopt erasure coding such as Reed-Solomon (RS) code as an alternative to replication because…
The demand for high-density data storage with ultrafast accessibility motivates the search for new memory implementations. Ideally such storage devices should be robust to input error and to unreliability of individual elements; furthermore…
Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanism requires massive matrix multiplications and frequent…
The Network-on-Chip (NoC) paradigm has been proposed as a favorable solution to handle the strict communication requirements between the increasingly large number of cores on a single chip. However, NoC systems are exposed to the aggressive…
The memory window of floating gate (FG) type non-volatile memory (NVM) devices is a fundamental figure of merit used not only to evaluate the performance, such as retention and endurance, but also to discuss the feasibility of advanced…
The alignment of code in the flash memory of deeply embedded SoCs can have a large impact on the total energy consumption of a computation. We investigate the effect of code alignment in six SoCs and find that a large proportion of this…
Three-dimensional (3D)-stacking technology, which enables the integration of DRAM and logic dies, offers high bandwidth and low energy consumption. This technology also empowers new memory designs for executing tasks not traditionally…
Accurate simulation techniques are indispensable to efficiently propose new memory or architectural organizations. As implementing new hardware concepts in real systems is often not feasible, cycle-accurate simulators employed together with…
Process simulation are performed in order to simulate the full fabrication process of an alternative nano-flash memory in order to optimise it and to improve the understanding of the dot storage formation. The influence of various…
Solid-State Drives (SSDs) have significant performance advantages over traditional Hard Disk Drives (HDDs) such as lower latency and higher throughput. Significantly higher price per capacity and limited lifetime, however, prevents…
Modern DRAM modules are often equipped with hardware error correction capabilities, especially for DRAM deployed in large-scale data centers, as process technology scaling has increased the susceptibility of these devices to errors. To…
In this paper, we consider modulation codes for practical multilevel flash memory storage systems with cell levels. Instead of maximizing the lifetime of the device [Ajiang-isit07-01, Ajiang-isit07-02, Yaakobi_verdy_siegel_wolf_allerton08,…
SAM3D enables scalable, open-world 3D reconstruction from complex scenes, yet its deployment is hindered by prohibitive inference latency. In this work, we conduct the \textbf{first systematic investigation} into its inference dynamics,…
Recent works demonstrate the advantages of hardware rasterization for 3D Gaussian Splatting (3DGS) in forward-pass rendering through fast GPU-optimized graphics and fixed memory footprint. However, extending these benefits to backward-pass…
Phase-change memory (PCM) is a scalable and low latency non-volatile memory (NVM) technology that has been proposed to serve as storage class memory (SCM), providing low access latency similar to DRAM and often approaching or exceeding the…
3D integration has the potential to improve the scalability and performance of Chip Multiprocessors (CMP). A closed form analytical solution for optimizing 3D CMP cache hierarchy is developed. It allows optimal partitioning of the cache…