64 citations · 105 across the 13 of their papers we have counts for
15 papers
Mira: Memory-Efficient MoE Inference Using Adaptive Caching and Predictive Expert Staging
Sanjali Yadav, Bahar Asgari
Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-constrained, single-GPU syste…
Characterizing LLM Kernel Access and Memory Interaction in Multi-Partition NUMA GPUs
Donghyeon Joo, Sooraj Puthoor, Nuwan Jayasena +1
Large language model (LLM) workloads motivate multi-partition GPUs as a path to scaling compute and memory capacity, but their non-uniform memory access characteristics and inter-p…
Tureis: Transformer-based Unified Resilience for IoT Devices in Smart Homes
Alireza Borhani, Vafa Andalibi, Bahar Asgari
Smart-home IoT systems rely on heterogeneous sensor networks whose correctness shapes application behavior and the physical environment. However, these low-cost, resource-constrain…
Arcalís: Accelerating Remote Procedure Calls Using a Líghtweight Near-Cache Solution
Johnson Umeike, Pongstorn Maidee, Bahar Asgari
Modern microservices increasingly depend on high-performance remote procedure calls (RPCs) to coordinate fine-grained, distributed computation. As network bandwidths continue to sc…
Belenos: Bottleneck Evaluation to Link Biomechanics to Novel Computing Optimizations
Hana Chitsaz, Johnson Umeike, Amirmahdi Namjoo +2
Finite element simulations are essential in biomechanics, enabling detailed modeling of tissues and organs. However, architectural inefficiencies in current hardware and software s…
Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference
Donghyeon Joo, Helya Hosseini, Ramyad Hadidi +1
We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-t…
GUST: Graph Edge-Coloring Utilization for Accelerating Sparse Matrix Vector Multiplication
Armin Gerami, Bahar Asgari
Sparse matrix-vector multiplication (SpMV) plays a vital role in various scientific and engineering fields, from scientific computing to machine learning. Traditional general-purpo…
Endor: Hardware-Friendly Sparse Format for Offloaded LLM Inference
Donghyeon Joo, Ramyad Hadidi, Soheil Feizi +1
The increasing size of large language models (LLMs) challenges their usage on resource-constrained platforms. For example, memory on modern GPUs is insufficient to hold LLMs that a…
Misam: Using ML in Dataflow Selection of Sparse-Sparse Matrix Multiplication
Sanjali Yadav, Bahar Asgari
Sparse matrix-matrix multiplication (SpGEMM) is a critical operation in numerous fields, including scientific computing, graph analytics, and deep learning. These applications expl…
Context-Aware Task Handling in Resource-Constrained Robots with Virtualization
Ramyad Hadidi, Nima Shoghi Ghalehshahi, Bahar Asgari +1
Intelligent mobile robots are critical in several scenarios. However, as their computational resources are limited, mobile robots struggle to handle several tasks concurrently and…
Copernicus: Characterizing the Performance Implications of Compression Formats Used in Sparse Workloads
Bahar Asgari, Ramyad Hadidi, Joshua Dierberger +3
Sparse matrices are the key ingredients of several application domains, from scientific computation to machine learning. The primary challenge with sparse matrices has been efficie…
LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition
Ramyad Hadidi, Bahar Asgari, Jiashen Cao +6
Deep neural networks (DNNs) have inspired new studies in myriad edge applications with robots, autonomous agents, and Internet-of-things (IoT) devices. However, performing inferenc…
Memory Slices: A Modular Building Block for Scalable, Intelligent Memory Systems
Bahar Asgari, Saibal Mukhopadhyay, Sudhakar Yalamanchili
While reduction in feature size makes computation cheaper in terms of latency, area, and power consumption, performance of emerging data-intensive applications is determined by dat…
Performance Implications of NoCs on 3D-Stacked Memories: Insights from the Hybrid Memory Cube
Ramyad Hadidi, Bahar Asgari, Jeffrey Young +4
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 Memo…
Demystifying the Characteristics of 3D-Stacked Memories: A Case Study for Hybrid Memory Cube
Ramyad Hadidi, Bahar Asgari, Burhan Ahmad Mudassar +3
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 ne…