GLEAM: Graph-Based Learning Through Efficient Aggregation in Memory

2025-03-31

Graph Neural Networks (GNNs) have emerged as a powerful tool for analyzing relationship-based data, such as those found in social networks, logistics, weather forecasting, and other domains. Inference and training with GNN models execute slowly, bottlenecked by limited data bandwidths between memory and GPU hosts, as a result of the many irregular memory accesses inherent to GNN-based computation. To overcome these limitations, we present GLEAM, a Processing-in-Memory (PIM) hardware accelerator designed specifically for GNN-based training and inference. GLEAM units are placed per-bank and leverage the much larger, internal bandwidth of HBMs to handle GNNs' irregular memory accesses, significantly boosting performance and reducing the energy consumption entailed by the dominant activity of GNN-based computation: neighbor aggregation. Our evaluation of GLEAM demonstrates up to a 10x speedup for GNN inference over GPU baselines, alongside a significant reduction in energy usage.

A Growing and Thriving Electronic Design, Automation, and Test Community: A DATE 2025 Perspective

IEEE Design and Test · 2025-08-20

The Design, Automation, and Test in Europe (DATE) Conference is a premier international event providing unique networking opportunities, bringing together designers and design automation users, researchers and vendors, and specialists in hardware and software design, test, and manufacturing of electronic circuits and systems.

SPIRE: Inferring Hardware Bottlenecks from Performance Counter Data

2025-03-31

The persistent demand for greater computing efficiency, coupled with diminishing returns from semiconductor scaling, has led to increased microarchitecture complexity and diversity. Thus, it has become increasingly difficult for application developers and hardware architects to accurately identify low-level performance bottlenecks. Abstract performance models, such as roofline models, help but strip away important microarchitectural details. In contrast, analyses based on hardware performance counters preserve detail but are challenging to implement. This work proposes SPIRE, a novel performance model that combines the accessibility and generality of roofline models with the microarchitectural detail of performance counters. SPIRE (Statistical Piecewise Linear Roofline Ensemble) uses a collection of roofline models to estimate a processor's maximum throughput, based on data from its performance counters. Training this ensemble simply requires sampling data from a processor's performance counters. After training a SPIRE model on 23 workloads running on a CPU, we evaluated it with 4 new workloads and compared our findings against a commercial performance analysis tool. We found that our SPIRE analysis accurately identified many of the same bottlenecks while requiring minimal deployment effort.

GreenScale: Carbon Optimization for Edge Computing

IEEE Internet of Things Journal · 2025-04-02 · 3 citations

Given billions of mobile users, the environmental impact of edge computing is significant. To address this, future applications need to execute computations on a green component which is fueled by renewable energy sources. However, because of the intermittent nature of the renewable energy sources, the carbon intensity of computing components can significantly vary with location and time of use. This poses a new challenge for edge applications – deciding when and where to run computations across consumer devices at the edge and servers in the cloud. Such scheduling decisions become more complicated with the amortization of the rising embodied emissions and stochastic runtime variance. This work proposes GreenScale, an intelligent execution scaling engine that accurately selects the carbon-optimal execution target for edge applications in different runtime environments. Our evaluation with three representative categories of applications (i.e., AI, Game, and AR/VR) demonstrate that the carbon emissions of the applications can be reduced by 35.2%, on average, with GreenScale.

Duet: A Collaborative User Driven Recommendation System for Edge Devices

2024-06-23

Recommendation systems are the backbone for numerous user applications on edge devices. However, the compute and memory-intensive nature of recommendation models renders them unsuitable for edge devices. Nevertheless, by decoupling the model fraction related to user history (e.g., past visited pages, liked posts) and user attributes (such as age, gender), we can offload partial recommendation models onto local edge devices. Hence, we present Duet, a novel collaborative edge-cloud recommendation system that intelligently decomposes the recommendation model into two smaller models - user and item models - that execute simultaneously on the edge device and cloud before coming together to deliver final recommendations. Further, we propose a lightweight Duet architecture to support user models on resource-constrained edge devices. Duet reduces the average latency by 6.4X and improves energy efficiency by 4.6X across five recommendation models.

Evergreen: Comprehensive Carbon Model for Performance-Emission Tradeoffs

2024-09-15 · 3 citations

The pervasive proliferation of computing infrastructure in recent decades has led to an increase in the fraction of worldwide energy and greenhouse gas (GHG) emissions associated with computing. A further steep increase is projected for the future, especially in light of the computational demands of large language models. While computing research has traditionally focused on performance, power, and area optimization, climate change concerns demand that the carbon footprint (CF) associated with computation be raised to a primary design parameter on par with power, performance, and area.To address this need, we propose Evergreen, a framework that augments computing tradeoffs with emission metrics. Evergreen offers the first complete carbon model for computing emission analysis, taking into account all major sources contributing to the carbon emissions associated with the execution of an application in a data center. The Evergreen carbon model considers both operational and embodied emissions associated with the computing hardware executing the application, the data transmission infrastructure, the renewable energy sources, and the battery energy storage systems. Using this model, our framework provides both an emissions predictor and a user-driven, emission-aware scheduler. The Evergreen scheduler allows users to select the data center to execute their workloads based on emissions and performance constraints associated with their execution in a cloud environment. Our evaluation shows how, for a given workload, Evergreen can provide multiple Pareto-optimal solutions in the performance-emission domain. Depending on the power source and data center values, Evergreen can identify carbon-optimal solutions that offer emission reduction with minimal latency overhead.

DATE 2024: Consolidating the New Conference Format

IEEE Design and Test · 2024-08-28

GreenScale: Carbon-Aware Systems for Edge Computing

arXiv (Cornell University) · 2023-04-01 · 1 citations

To improve the environmental implications of the growing demand of computing, future applications need to improve the carbon-efficiency of computing infrastructures. State-of-the-art approaches, however, do not consider the intermittent nature of renewable energy. The time and location-based carbon intensity of energy fueling computing has been ignored when determining how computation is carried out. This poses a new challenge -- deciding when and where to run applications across consumer devices at the edge and servers in the cloud. Such scheduling decisions become more complicated with the stochastic runtime variance and the amortization of the rising embodied emissions. This work proposes GreenScale, a framework to understand the design and optimization space of carbon-aware scheduling for green applications across the edge-cloud infrastructure. Based on the quantified carbon output of the infrastructure components, we demonstrate that optimizing for carbon, compared to performance and energy efficiency, yields unique scheduling solutions. Our evaluation with three representative categories of applications (i.e., AI, Game, and AR/VR) demonstrate that the carbon emissions of the applications can be reduced by up to 29.1% with the GreenScale. The analysis in this work further provides a detailed road map for edge-cloud application developers to build green applications.

ACRE: Accelerating Random Forests for Explainability

2023-10-28 · 1 citations

As machine learning models become more widespread, they are being increasingly applied in applications that heavily impact people’s lives (e.g., medical diagnoses, judicial system sentences, etc.). Several communities are thus calling for ML models to be not only accurate, but also explainable. To achieve this, recommendations must be augmented with explanations summarizing how each recommendation outcome is derived. Explainable Random Forest (XRF) models are popular choices in this space, as they are both very accurate and can be augmented with explainability functionality, allowing end-users to learn how and why a specific outcome was reached. However, the limitations of XRF models hamper their adoption, the foremost being the high computational demands associated with training such models to support high-accuracy classifications, while also annotating them with explainability meta-data.

Postpandemic Conferences: The DATE 2023 Experience

IEEE Design and Test · 2023-08-28

Date is a leading international event providing unique networking opportunities. The conference brings together designers and design automation users, researchers, and vendors, as well as specialists in hardware and software design, testing, and manufacturing of electronic circuits and systems—from system-level hardware and software implementation down to integrated circuit design.