English
Related papers

Related papers: FUSE: Fusing STT-MRAM into GPUs to Alleviate Off-C…

200 papers

Magneto-Electric FET (MEFET) is a recently developed post-CMOS FET, which offers intriguing characteristics for high speed and low-power design in both logic and memory applications. In this paper, for the first time, we propose a…

Emerging Technologies · Computer Science 2020-09-15 Shaahin Angizi , Navid Khoshavi , Andrew Marshall , Peter Dowben , Deliang Fan

Embedded machine learning (ML) systems have now become the dominant platform for deploying ML serving tasks and are projected to become of equal importance for training ML models. With this comes the challenge of overall efficient…

Hardware Architecture · Computer Science 2022-06-29 Ahmet Inci , Mehmet Meric Isgenc , Diana Marculescu

In recent years, researchers have explored use of non-volatile devices such as STT-RAM (spin torque transfer RAM) for designing on-chip caches, since they provide high density and consume low leakage power. A common limitation of all…

Hardware Architecture · Computer Science 2013-11-01 Sparsh Mittal

Memory bandwidth is critical in today's high performance computing systems. The bandwidth is particularly paramount for GPU workloads such as 3D Gaming, Imaging and Perceptual Computing, GPGPU due to their data-intensive nature. As the…

Performance · Computer Science 2018-08-13 Ishwar Bhati , Udit Dhawan , Jayesh Gaur , Sreenivas Subramoney , Hong Wang

We provide an optimized implementation of the forward pass of FlashAttention-2, a popular memory-aware scaled dot-product attention algorithm, as a custom fused CUDA kernel targeting NVIDIA Hopper architecture and written using the…

Machine Learning · Computer Science 2023-12-20 Ganesh Bikshandi , Jay Shah

Precise estimation of model inference latency is crucial for time-critical mobile edge applications, enabling devices to calculate latency margins against deadlines and trade them for enhanced model performance or resource savings. However,…

Hardware Architecture · Computer Science 2026-04-20 Jiesong Chen , Jun You , Zhidan Liu , Zhenjiang Li

Prices of NAND flash memories are falling drastically due to market growth and fabrication process mastering while research efforts from a technological point of view in terms of endurance and density are very active. NAND flash memories…

Hardware Architecture · Computer Science 2012-09-17 Jalil Boukhobza , Pierre Olivier , Stéphane Rubini

Cloud platforms host thousands of tenants that demand POSIX semantics, high throughput, and rapid evolution from their storage layer. Kernel-native distributed file systems supply raw speed, but their privileged code base couples every…

Operating Systems · Computer Science 2025-10-23 Haoyu Li , Jingkai Fu , Qing Li , Windsor Hsu , Asaf Cidon

Subgraph matching is a core operation in graph analytics, supporting a broad spectrum of applications from social network analysis to bioinformatics. Recent GPU-based approaches accelerate subgraph matching by leveraging parallelism but…

Databases · Computer Science 2026-04-14 Weitian Chen , Shixuan Sun , Cheng Chen , Yongmin Hu , Yingqian Hu , Minyi Guo

While GPUs dominate massively parallel computing through the single-instruction, multiple-thread (SIMT) programming model, their underlying single-instruction, multiple-data (SIMD) execution incurs substantial energy overhead from frequent…

Hardware Architecture · Computer Science 2026-05-08 Jiayi Wang , Ang Da Lu , Zhichen Zeng , Ang Li

The Fast Fourier Transform (FFT), as a core computation in a wide range of scientific applications, is increasingly threatened by reliability issues. In this paper, we introduce TurboFFT, a high-performance FFT implementation equipped with…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-07 Shixun Wu , Yujia Zhai , Jinyang Liu , Jiajun Huang , Zizhe Jian , Huangliang Dai , Sheng Di , Zizhong Chen , Franck Cappello

The exponential growth of data-intensive machine learning workloads has exposed significant limitations in conventional GPU-accelerated systems, especially when processing datasets exceeding GPU DRAM capacity. We propose MQMS, an augmented…

Hardware Architecture · Computer Science 2024-12-10 Ayush Gundawar , Euijun Chung , Hyesoon Kim

Spiking Neural Networks (SNNs) offer a promising solution for energy-efficient edge intelligence; however, their hardware deployment is constrained by memory overhead, inefficient scaling operations, and limited parallelism. This work…

Hardware Architecture · Computer Science 2026-04-07 Sonu Kumar , Mukul Lokhande , Santosh Kumar Vishvakarma

The use of analog resistance states for storing weights in neuromorphic systems is impeded by fabrication imprecision and device stochasticity that limit the precision of synapse weights. This challenge can be resolved by emulating analog…

Neural and Evolutionary Computing · Computer Science 2021-12-13 Peng Zhou , Julie A. Smith , Laura Deremo , Stephen K. Heinrich-Barna , Joseph S. Friedman

Massively multicore processors, such as Graphics Processing Units (GPUs), provide, at a comparable price, a one order of magnitude higher peak performance than traditional CPUs. This drop in the cost of computation, as any…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-11-18 Samer Al-Kiswany , Abdullah Gharaibeh , Matei Ripeanu

Witnessing the advancing scale and complexity of chip design and benefiting from high-performance computation technologies, the simulation of Very Large Scale Integration (VLSI) Circuits imposes an increasing requirement for acceleration…

Data Structures and Algorithms · Computer Science 2023-04-27 Weijie Fang , Yanggeng Fu , Jiaquan Gao , Longkun Guo , Gregory Gutin , Xiaoyan Zhang

High Performance Computing (HPC) on hybrid clusters represents a significant opportunity for Computational Fluid Dynamics (CFD), especially when modern accelerators are utilized effectively. However, despite the widespread adoption of GPUs,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-30 Simone Bnà , Giuseppe Giaquinto , Ettore Fadiga , Tommaso Zanelli , Francesco Bottau

As AI workloads drive increasing memory requirements, domain-specific accelerators need higher-density on-chip memory beyond what current SRAM scaling trends can provide. Simultaneously, the vast amounts of short-lived data in these…

Structural clustering is one of the most popular graph clustering methods, which has achieved great performance improvement by utilizing GPUs. Even though, the state-of-the-art GPU-based structural clustering algorithm, GPUSCAN, still…

Databases · Computer Science 2023-12-01 Long Yuan , Zeyu Zhou , Xuemin Lin , Zi Chen , Xiang Zhao , Fan Zhang

Cross-workload design space exploration (DSE) is crucial in CPU architecture design. Existing DSE methods typically employ the transfer learning technique to leverage knowledge from source workloads, aiming to minimize the requirement of…

Hardware Architecture · Computer Science 2025-04-21 Runzhen Xue , Hao Wu , Mingyu Yan , Ziheng Xiao , Xiaochun Ye , Dongrui Fan