Related papers: RevaMp3D: Architecting the Processor Core and Cach…

Massive multi-threading in GPU imposes tremendous pressure on memory subsystems. Due to rapid growth in thread-level parallelism of GPU and slowly improved peak memory bandwidth, the memory becomes a bottleneck of GPU's performance and…

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…

Lazy search algorithms have been developed to efficiently solve planning problems in domains where the computational effort is dominated by the cost of edge evaluation. The existing algorithms operate by intelligently balancing…

Traditional DRAM-based main memory systems face several challenges with memory refresh overhead, high latency, and low throughput as the industry moves towards smaller DRAM cells. These issues have been exacerbated by the emergence of…

Long-context Large Language Model (LLM) inference faces increasing compute bottlenecks as attention calculations scale with context length, primarily due to the growing KV-cache transfer overhead that saturates High Bandwidth Memory (HBM).…

The pervasive "memory wall" bottleneck is significantly amplified in modern large-scale Mixture-of-Experts (MoE) architectures. MoE's inherent architectural sparsity leads to sparse arithmetic compute and also introduces substantial…

This paper presents the interesting observation that by performing fewer of the optimizations available in a standard compiler optimization level such as -O2, while preserving their original ordering, significant savings can be achieved in…

In this paper, we proposed an effective and efficient multi-core shared-cache design optimization approach based on reuse-distance analysis of the data traces of target applications. Since data traces are independent of system hardware…

Many modern workloads, such as neural networks, databases, and graph processing, are fundamentally memory-bound. For such workloads, the data movement between main memory and CPU cores imposes a significant overhead in terms of both latency…

3D detailed radiative transfer is computationally taxing, since the solution of the radiative transfer equation involves traversing the six dimensional phase space of the 3D domain. With modern supercomputers the hardware available for…

The Mixture-of-Experts (MoE) models have emerged as the state-of-the-art paradigm for scaling up large language models (LLMs) without proportionally increased computational cost. However, its on-device deployment faces a critical challenge…

The conventional von Neumann architecture has been revealed as a major performance and energy bottleneck for rising data-intensive applications. %, due to the intensive data movements. The decade-old idea of leveraging in-memory processing…

In modern server CPUs, the Last-Level Cache (LLC) serves not only as a victim cache for higher-level private caches but also as a buffer for low-latency DMA transfers between CPU cores and I/O devices through Direct Cache Access (DCA).…

Processing-in-memory (PIM) is a promising computing paradigm to tackle the "memory wall" challenge. However, PIM system-level benefits over traditional von Neumann architecture can be reduced when the memory array cannot fully store all the…

Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs: the first…

In modern Commercial Off-The-Shelf (COTS) multicore systems, each core can generate many parallel memory requests at a time. The processing of these parallel requests in the DRAM controller greatly affects the memory interference delay…

DRAM is the prevalent main memory technology, but its long access latency can limit the performance of many workloads. Although prior works provide DRAM designs that reduce DRAM access latency, their reduced storage capacities hinder the…

Deployment of modern TinyML tasks on small battery-constrained IoT devices requires high computational energy efficiency. Analog In-Memory Computing (IMC) using non-volatile memory (NVM) promises major efficiency improvements in deep neural…

The emergence of heterogeneity and domain-specific architectures targeting deep learning inference show great potential for enabling the deployment of modern CNNs on resource-constrained embedded platforms. A significant development is the…

BM3D has been considered the standard for comparison in the image denoising literature for the last decade. Though it has been shown to be surpassed numerous times by alternative algorithms in terms of PSNR, the margins are very thin, and…