Related papers: Design Guidelines for High-Performance SCM Hierarc…
SoCs are now designed with their own AI accelerator segment to accommodate the ever-increasing demand of Deep Learning (DL) applications. With powerful MAC engines for matrix multiplications, these accelerators show high computing…
The semantics of HPC storage systems are defined by the consistency models to which they abide. Storage consistency models have been less studied than their counterparts in memory systems, with the exception of the POSIX standard and its…
High-Bandwidth Memory (HBM) delivers exceptional bandwidth and energy efficiency for AI workloads, but its high cost per bit, driven in part by stringent on-die reliability requirements, poses a growing barrier to scalable deployment. This…
Parallel programmers face the often irreconcilable goals of programmability and performance. HPC systems use distributed memory for scalability, thereby sacrificing the programmability advantages of shared memory programming models.…
Digital Computing-in-Memory (DCIM) is an innovative technology that integrates multiply-accumulation (MAC) logic directly into memory arrays to enhance the performance of modern AI computing. However, the need for customized memory cells…
Large Language Models (LLMs) have become increasingly popular, transforming a wide range of applications across various domains. However, the real-world effectiveness of their query cache systems has not been thoroughly investigated. In…
As a core component in modern data centers, key-value cache provides high-throughput and low-latency services for high-speed data processing. The effectiveness of a key-value cache relies on its ability of accommodating the needed data.…
3D point cloud neural networks have significantly enhanced the perceptual capabilities of resource-limited mobile intelligent systems. However, despite the transformative impact, the point cloud algorithm suffers from substantial memory…
This report introduces a shared resource arbitration scheme "DPQ - Dynamic Priority Queue" which provides bandwidth guarantees and low worst case latency to each master in an MPSoC. Being a non-trivial candidate for timing analysis, SDRAM…
Memories that exploit three-dimensional (3D)-stacking technology, which integrate memory and logic dies in a single stack, are becoming popular. These memories, such as Hybrid Memory Cube (HMC), utilize a network-on-chip (NoC) design for…
Processing-in-memory (PIM) has emerged as a promising solution for accelerating memory-intensive workloads as they provide high memory bandwidth to the processing units. This approach has drawn attention not only from the academic community…
The use of multi-chip modules (MCM) and/or multi-socket boards is the most suitable approach to increase the computation density of servers while keep chip yield attained. This paper introduces a new coherence protocol suitable, in terms of…
With recent trend of wearable devices and Internet of Things (IoTs), it becomes attractive to develop hardware-based deep convolutional neural networks (DCNNs) for embedded applications, which require low power/energy consumptions and small…
Deploying Small Language Models (SLMs) on edge platforms is critical for real-time, privacy-sensitive generative AI, yet constrained by memory, latency, and energy budgets. Quantization reduces model size and cost but suffers from device…
In this paper we determine the delivery time for a multi-server coded caching problem when the cache size of each user is small. We propose an achievable scheme based on coded cache content placement, and employ zero-forcing techniques at…
Memory accounts for a considerable portion of the total power budget and area of digital systems. Furthermore, it is typically the performance bottleneck of the processing units. Therefore, it is critical to optimize the memory with respect…
The Intel Optane DC Persistent Memory (DCPM) is an attractive novel technology for building storage systems for data intensive HPC applications, as it provides lower cost per byte, low standby power and larger capacities than DRAM, with…
Hybrid memory systems comprised of dynamic random access memory (DRAM) and non-volatile memory (NVM) have been proposed to exploit both the capacity advantage of NVM and the latency and dynamic energy advantages of DRAM. An important…
Embedded applications are widely used in portable devices such as wireless phones, personal digital assistants, laptops, etc. High throughput and real time requirements are especially important in such data-intensive tasks. Therefore,…
Today's high-performance architectures are increasingly constrained by data movement latency and energy overhead, as the slowdown of single-core performance scaling coincides with the rise of highly data-intensive workloads. In-memory…