Searcharxiv⌕ Search

arXiv subjects

Wen-mei Hwu

Publications and source records attributed to Wen-mei Hwu.

At least 19 recordsLinked to original sources
arXiv2026

LSM-GNN: Large-scale Storage-based Multi-GPU GNN Training by Optimizing Data Transfer Scheme

Graph Neural Networks (GNNs) are widely used today in recommendation systems, fraud detection, and node/link classification tasks. Real world GNNs continue to scale in size and require a large memory footprint for storing graphs and embeddings that often exceed the memory capacities of the target GPUs used for training. To address limited memory capacities, traditional GNN training approaches use graph partitioning and sharding techniques to scale up across multiple GPUs within a node and/or scale out across multiple nodes. However, this approach suffers from the high computational costs of graph partitioning algorithms and inefficient communication across GPUs. To address these overheads, we propose Large-scale Storage-based Multi-GPU GNN framework (LSM-GNN), a storage-based approach to train GNN models that utilizes a novel communication layer enabling GPU software caches to function as a system-wide shared cache with low overheads. LSM-GNN incorporates a hybrid eviction policy that intelligently manages cache space by using both static and dynamic node information to significantly enhance cache performance. Furthermore, we introduce the Preemptive Victim-buffer Prefetcher (PVP), a mechanism for prefetching node feature data from a Victim Buffer located in CPU pinned-memory to further reduce the pressure on the storage devices. Experimental results show that despite the lower compute capabilities and memory capacities, LSM-GNN in a single node with two GPUs offers superior performance over two-node-four-GPU Dist-DGL baseline and provides up to 3.75x speed up on end-to-end epoch time while running large-scale GNN training

cs.DC↗
arXiv2026

IRB: Automated Generation of Robust Factuality Benchmarks

Static benchmarks for RAG systems often suffer from rapid saturation and require significant manual effort to maintain robustness. To address this, we present IRB, a framework for automatically generating benchmarks to evaluate the factuality of RAG systems. IRB employs a structured generation pipeline utilizing \textit{factual scaffold} and \textit{algorithmic scaffold}. We utilize IRB to construct a benchmark and evaluate frontier LLMs and retrievers. Our results demonstrate that IRB poses a significant challenge for frontier LLMs in the closed-book setting. Furthermore, our evaluation suggests that reasoning LLMs are more reliable, and that improving the retrieval component may yield more cost-effective gains in RAG system correctness than scaling the generator.

cs.IR↗
arXiv2026

VibeTensor: System Software for Deep Learning, Fully Generated by AI Agents

VIBETENSOR is an open-source research system software stack for deep learning, generated by LLM-powered coding agents under high-level human guidance. In this paper, "fully generated" refers to code provenance: implementation changes were produced and applied as agent-proposed diffs; validation relied on agent-run builds, tests, and differential checks, without per-change manual diff review. It implements a PyTorch-style eager tensor library with a C++20 core (CPU+CUDA), a torch-like Python overlay via nanobind, and an experimental Node.js/TypeScript interface. Unlike thin bindings, VIBETENSOR includes its own tensor/storage system, schema-lite dispatcher, reverse-mode autograd, CUDA runtime (streams/events/graphs), a stream-ordered caching allocator with diagnostics, and a stable C ABI for dynamically loaded operator plugins. We view this release as a milestone for AI-assisted software engineering: it shows coding agents can generate a coherent deep learning runtime spanning language bindings down to CUDA memory management, validated primarily by builds and tests. We describe the architecture, summarize the workflow used to produce and validate the system, and evaluate the artifact. We report repository scale and test-suite composition, and summarize reproducible microbenchmarks from an accompanying AI-generated kernel suite, including fused attention versus PyTorch SDPA/FlashAttention. We also report end-to-end training sanity checks on 3 small workloads (sequence reversal, ViT, miniGPT) on NVIDIA H100 (Hopper, SM90) and Blackwell-class GPUs; multi-GPU results are Blackwell-only and use an optional CUTLASS-based ring-allreduce plugin gated on CUDA 13+ and sm103a toolchain support. Finally, we discuss failure modes in generated system software, including a "Frankenstein" composition effect where locally correct subsystems interact to yield globally suboptimal performance.

cs.SE↗
arXiv2025

AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory

Riding on the success of LLMs with retrieval-augmented generation (RAG), there has been a growing interest in augmenting agent systems with external memory databases. However, the existing systems focus on storing text information in their memory, ignoring the importance of multimodal signals. Motivated by the multimodal nature of human memory, we present AUGUSTUS, a multimodal agent system aligned with the ideas of human memory in cognitive science. Technically, our system consists of 4 stages connected in a loop: (i) encode: understanding the inputs; (ii) store in memory: saving important information; (iii) retrieve: searching for relevant context from memory; and (iv) act: perform the task. Unlike existing systems that use vector databases, we propose conceptualizing information into semantic tags and associating the tags with their context to store them in a graph-structured multimodal contextual memory for efficient concept-driven retrieval. Our system outperforms the traditional multimodal RAG approach while being 3.5 times faster for ImageNet classification and outperforming MemGPT on the MSC benchmark.

cs.AI↗
arXiv2025

Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light

Many sparse attention mechanisms such as Neighborhood Attention have typically failed to consistently deliver speedup over the self attention baseline. This is largely due to the level of complexity in attention infrastructure, and the rapid evolution of AI hardware architecture. At the same time, many state-of-the-art foundational models, particularly in computer vision, are heavily bound by attention, and need reliable sparsity to escape the O(n^2) complexity. In this paper, we study a class of promising sparse attention mechanisms that focus on locality, and aim to develop a better analytical model of their performance improvements. We first introduce Generalized Neighborhood Attention (GNA), which can describe sliding window, strided sliding window, and blocked attention. We then consider possible design choices in implementing these approaches, and create a simulator that can provide much more realistic speedup upper bounds for any given setting. Finally, we implement GNA on top of a state-of-the-art fused multi-headed attention (FMHA) kernel designed for the NVIDIA Blackwell architecture in CUTLASS. Our implementation can fully realize the maximum speedup theoretically possible in many perfectly block-sparse cases, and achieves an effective utilization of 1.3 petaFLOPs/second in FP16. In addition, we plug various GNA configurations into off-the-shelf generative models, such as Cosmos-7B, HunyuanVideo, and FLUX, and show that it can deliver 28% to 46% end-to-end speedup on B200 without any fine-tuning. We will open source our simulator and Blackwell kernels directly through the NATTEN project.

cs.CV↗
arXiv2025

SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training

The growth rate of the GPU memory capacity has not been able to keep up with that of the size of large language models (LLMs), hindering the model training process. In particular, activations -- the intermediate tensors produced during forward propagation and reused in backward propagation -- dominate the GPU memory use. This leads to high training overhead such as high weight update cost due to the small micro-batch size. To address this challenge, we propose SSDTrain, an adaptive activation offloading framework to high-capacity NVMe SSDs. SSDTrain reduces GPU memory usage without impacting performance by fully overlapping data transfers with computation. SSDTrain is compatible with popular deep learning frameworks like PyTorch, Megatron, and DeepSpeed, and it employs techniques such as tensor deduplication and forwarding to further enhance efficiency. We extensively experimented with popular LLMs like GPT, BERT, and T5. Results demonstrate that SSDTrain reduces 47% of the activation peak memory usage. Meanwhile, SSDTrain perfectly overlaps the I/O with the computation and incurs negligible overhead. Compared with keeping activations in GPU memory and layerwise full recomputation, SSDTrain achieves the best memory savings with negligible throughput loss. We further analyze how the reduced activation memory use may be leveraged to increase throughput by increasing micro-batch size and reducing pipeline parallelism bubbles.

cs.DC↗
arXiv2024

HiCCL: A Hierarchical Collective Communication Library

HiCCL (Hierarchical Collective Communication Library) addresses the growing complexity and diversity in high-performance network architectures. As GPU systems have envolved into networks of GPUs with different multilevel communication hierarchies, optimizing each collective function for a specific system has become a challenging task. Consequently, many collective libraries struggle to adapt to different hardware and software, especially across systems from different vendors. HiCCL's library design decouples the collective communication logic from network-specific optimizations through a compositional API. The communication logic is composed using multicast, reduction, and fence primitives, which are then factorized for a specified network hieararchy using only point-to-point operations within a level. Finally, striping and pipelining optimizations applied as specified for streamlining the execution. Performance evaluation of HiCCL across four different machines$\unicode{x2014}$two with Nvidia GPUs, one with AMD GPUs, and one with Intel GPUs$\unicode{x2014}$demonstrates an average 17$\times$ higher throughput than the collectives of highly specialized GPU-aware MPI implementations, and competitive throughput with those of vendor-specific libraries (NCCL, RCCL, and OneCCL), while providing portability across all four machines.

cs.DC↗
arXiv2024

Hector: An Efficient Programming and Compilation Framework for Implementing Relational Graph Neural Networks in GPU Architectures

Relational graph neural networks (RGNNs) are graph neural networks with dedicated structures for modeling the different types of nodes and edges in heterogeneous graphs. While RGNNs have been increasingly adopted in many real-world applications due to their versatility and accuracy, they pose performance and system design challenges: inherent memory-intensive computation patterns, the gap between the programming interface and kernel APIs, and heavy programming effort in optimizing kernels caused by their coupling with data layout and heterogeneity. To systematically address these challenges, we propose Hector, a novel two-level intermediate representation and its code generator framework, that (a) captures the key properties of RGNN models, and opportunities to reduce memory accesses in inter-operator scheduling and materialization, (b) generates code with flexible data access scheme to eliminate redundant data copies, (c) decouples model semantics, data layout, and operators-specific optimization from each other to reduce programming effort. By building on one general matrix multiply (GEMM) template and a node/edge traversal template, Hector achieves up to 9.9x speed-up in inference and 43.7x speed-up in training compared with the state-of-the-art public systems on select models, i.e., RGCN, RGAT and HGT, when running heterogeneous graphs provided by Deep Graph Library (DGL) and Open Graph Benchmark (OGB). In addition, Hector does not trigger any out-of-memory (OOM) exception in these tests. We also propose the linear operator reorder and compact materialization to further accelerate the system by up to 3.8x. As an indicator of programming effort reduction, Hector takes in 51 lines of code expressing the three models and generates a total of 8K lines of CUDA and C++ code.

cs.DC↗
arXiv2024

Accelerating Sampling and Aggregation Operations in GNN Frameworks with GPU Initiated Direct Storage Accesses

Graph Neural Networks (GNNs) are emerging as a powerful tool for learning from graph-structured data and performing sophisticated inference tasks in various application domains. Although GNNs have been shown to be effective on modest-sized graphs, training them on large-scale graphs remains a significant challenge due to lack of efficient data access and data movement methods. Existing frameworks for training GNNs use CPUs for graph sampling and feature aggregation, while the training and updating of model weights are executed on GPUs. However, our in-depth profiling shows the CPUs cannot achieve the throughput required to saturate GNN model training throughput, causing gross under-utilization of expensive GPU resources. Furthermore, when the graph and its embeddings do not fit in the CPU memory, the overhead introduced by the operating system, say for handling page-faults, comes in the critical path of execution. To address these issues, we propose the GPU Initiated Direct Storage Access (GIDS) dataloader, to enable GPU-oriented GNN training for large-scale graphs while efficiently utilizing all hardware resources, such as CPU memory, storage, and GPU memory with a hybrid data placement strategy. By enabling GPU threads to fetch feature vectors directly from storage, GIDS dataloader solves the memory capacity problem for GPU-oriented GNN training. Moreover, GIDS dataloader leverages GPU parallelism to tolerate storage latency and eliminates expensive page-fault overhead. Doing so enables us to design novel optimizations for exploiting locality and increasing effective bandwidth for GNN training. Our evaluation using a single GPU on terabyte-scale GNN datasets shows that GIDS dataloader accelerates the overall DGL GNN training pipeline by up to 392X when compared to the current, state-of-the-art DGL dataloader.

cs.DC↗
arXiv2023

Parallelizing Maximal Clique Enumeration on GPUs

We present a GPU solution for exact maximal clique enumeration (MCE) that performs a search tree traversal following the Bron-Kerbosch algorithm. Prior works on parallelizing MCE on GPUs perform a breadth-first traversal of the tree, which has limited scalability because of the explosion in the number of tree nodes at deep levels. We propose to parallelize MCE on GPUs by performing depth-first traversal of independent subtrees in parallel. Since MCE suffers from high load imbalance and memory capacity requirements, we propose a worker list for dynamic load balancing, as well as partial induced subgraphs and a compact representation of excluded vertex sets to regulate memory consumption. Our evaluation shows that our GPU implementation on a single GPU outperforms the state-of-the-art parallel CPU implementation by a geometric mean of 4.9x (up to 16.7x), and scales efficiently to multiple GPUs. Our code has been open-sourced to enable further research on accelerating MCE.

cs.DC↗
arXiv2023

RackBlox: A Software-Defined Rack-Scale Storage System with Network-Storage Co-Design

Software-defined networking (SDN) and software-defined flash (SDF) have been serving as the backbone of modern data centers. They are managed separately to handle I/O requests. At first glance, this is a reasonable design by following the rack-scale hierarchical design principles. However, it suffers from suboptimal end-to-end performance, due to the lack of coordination between SDN and SDF. In this paper, we co-design the SDN and SDF stack by redefining the functions of their control plane and data plane, and splitting up them within a new architecture named RackBlox. RackBlox decouples the storage management functions of flash-based solid-state drives (SSDs), and allow the SDN to track and manage the states of SSDs in a rack. Therefore, we can enable the state sharing between SDN and SDF, and facilitate global storage resource management. RackBlox has three major components: (1) coordinated I/O scheduling, in which it dynamically adjusts the I/O scheduling in the storage stack with the measured and predicted network latency, such that it can coordinate the effort of I/O scheduling across the network and storage stack for achieving predictable end-to-end performance; (2) coordinated garbage collection (GC), in which it will coordinate the GC activities across the SSDs in a rack to minimize their impact on incoming I/O requests; (3) rack-scale wear leveling, in which it enables global wear leveling among SSDs in a rack by periodically swapping data, for achieving improved device lifetime for the entire rack. We implement RackBlox using programmable SSDs and switch. Our experiments demonstrate that RackBlox can reduce the tail latency of I/O requests by up to 5.8x over state-of-the-art rack-scale storage systems.

cs.OS↗
arXiv2023

CODAG: Characterizing and Optimizing Decompression Algorithms for GPUs

Data compression and decompression have become vital components of big-data applications to manage the exponential growth in the amount of data collected and stored. Furthermore, big-data applications have increasingly adopted GPUs due to their high compute throughput and memory bandwidth. Prior works presume that decompression is memory-bound and have dedicated most of the GPU's threads to data movement and adopted complex software techniques to hide memory latency for reading compressed data and writing uncompressed data. This paper shows that these techniques lead to poor GPU resource utilization as most threads end up waiting for the few decoding threads, exposing compute and synchronization latencies. Based on this observation, we propose CODAG, a novel and simple kernel architecture for high throughput decompression on GPUs. CODAG eliminates the use of specialized groups of threads, frees up compute resources to increase the number of parallel decompression streams, and leverages the ample compute activities and the GPU's hardware scheduler to tolerate synchronization, compute, and memory latencies. Furthermore, CODAG provides a framework for users to easily incorporate new decompression algorithms without being burdened with implementing complex optimizations to hide memory latency. We validate our proposed architecture with three different encoding techniques, RLE v1, RLE v2, and Deflate, and a wide range of large datasets from different domains. We show that CODAG provides 13.46x, 5.69x, and 1.18x speed up for RLE v1, RLE v2, and Deflate, respectively, when compared to the state-of-the-art decompressors from NVIDIA RAPIDS.

cs.DC↗
arXiv2023

IGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research

Graph neural networks (GNNs) have shown high potential for a variety of real-world, challenging applications, but one of the major obstacles in GNN research is the lack of large-scale flexible datasets. Most existing public datasets for GNNs are relatively small, which limits the ability of GNNs to generalize to unseen data. The few existing large-scale graph datasets provide very limited labeled data. This makes it difficult to determine if the GNN model's low accuracy for unseen data is inherently due to insufficient training data or if the model failed to generalize. Additionally, datasets used to train GNNs need to offer flexibility to enable a thorough study of the impact of various factors while training GNN models. In this work, we introduce the Illinois Graph Benchmark (IGB), a research dataset tool that the developers can use to train, scrutinize and systematically evaluate GNN models with high fidelity. IGB includes both homogeneous and heterogeneous academic graphs of enormous sizes, with more than 40% of their nodes labeled. Compared to the largest graph datasets publicly available, the IGB provides over 162X more labeled data for deep learning practitioners and developers to create and evaluate models with higher accuracy. The IGB dataset is a collection of academic graphs designed to be flexible, enabling the study of various GNN architectures, embedding generation techniques, and analyzing system performance issues for node classification tasks. IGB is open-sourced, supports DGL and PyG frameworks, and comes with releases of the raw text that we believe foster emerging language models and GNN research projects. An early public version of IGB is available at https://github.com/IllinoisGraphBenchmark/IGB-Datasets.

cs.LG↗
arXiv2023

Can Language Models Be Specific? How?

"He is a person", "Paris is located on the earth". Both statements are correct but meaningless - due to lack of specificity. In this paper, we propose to measure how specific the language of pre-trained language models (PLMs) is. To achieve this, we introduce a novel approach to build a benchmark for specificity testing by forming masked token prediction tasks with prompts. For instance, given "Toronto is located in [MASK].", we want to test whether a more specific answer will be better filled in by PLMs, e.g., Ontario instead of Canada. From our evaluations, we show that existing PLMs have only a slight preference for more specific answers. We identify underlying factors affecting the specificity and design two prompt-based methods to improve the specificity. Results show that the specificity of the models can be improved by the proposed methods without additional training. We hope this work can bring to awareness the notion of specificity of language models and encourage the research community to further explore this important but understudied problem.

cs.CL↗
arXiv2023

GPU-Initiated On-Demand High-Throughput Storage Access in the BaM System Architecture

Graphics Processing Units (GPUs) have traditionally relied on the host CPU to initiate access to the data storage. This approach is well-suited for GPU applications with known data access patterns that enable partitioning of their dataset to be processed in a pipelined fashion in the GPU. However, emerging applications such as graph and data analytics, recommender systems, or graph neural networks, require fine-grained, data-dependent access to storage. CPU initiation of storage access is unsuitable for these applications due to high CPU-GPU synchronization overheads, I/O traffic amplification, and long CPU processing latencies. GPU-initiated storage removes these overheads from the storage control path and, thus, can potentially support these applications at much higher speed. However, there is a lack of systems architecture and software stack that enable efficient GPU-initiated storage access. This work presents a novel system architecture, BaM, that fills this gap. BaM features a fine-grained software cache to coalesce data storage requests while minimizing I/O traffic amplification. This software cache communicates with the storage system via high-throughput queues that enable the massive number of concurrent threads in modern GPUs to make I/O requests at a high rate to fully utilize the storage devices and the system interconnect. Experimental results show that BaM delivers 1.0x and 1.49x end-to-end speed up for BFS and CC graph analytics benchmarks while reducing hardware costs by up to 21.7x over accessing the graph data from the host memory. Furthermore, BaM speeds up data-analytics workloads by 5.3x over CPU-initiated storage access on the same hardware.

cs.DC↗
arXiv2022

Submission-Aware Reviewer Profiling for Reviewer Recommender System

Assigning qualified, unbiased and interested reviewers to paper submissions is vital for maintaining the integrity and quality of the academic publishing system and providing valuable reviews to authors. However, matching thousands of submissions with thousands of potential reviewers within a limited time is a daunting challenge for a conference program committee. Prior efforts based on topic modeling have suffered from losing the specific context that help define the topics in a publication or submission abstract. Moreover, in some cases, topics identified are difficult to interpret. We propose an approach that learns from each abstract published by a potential reviewer the topics studied and the explicit context in which the reviewer studied the topics. Furthermore, we contribute a new dataset for evaluating reviewer matching systems. Our experiments show a significant, consistent improvement in precision when compared with the existing methods. We also use examples to demonstrate why our recommendations are more explainable. The new approach has been deployed successfully at top-tier conferences in the last two years.

cs.IR↗
arXiv2022

Understanding Jargon: Combining Extraction and Generation for Definition Modeling

Can machines know what twin prime is? From the composition of this phrase, machines may guess twin prime is a certain kind of prime, but it is still difficult to deduce exactly what twin stands for without additional knowledge. Here, twin prime is a jargon - a specialized term used by experts in a particular field. Explaining jargon is challenging since it usually requires domain knowledge to understand. Recently, there is an increasing interest in extracting and generating definitions of words automatically. However, existing approaches, either extraction or generation, perform poorly on jargon. In this paper, we propose to combine extraction and generation for jargon definition modeling: first extract self- and correlative definitional information of target jargon from the Web and then generate the final definitions by incorporating the extracted definitional information. Our framework is remarkably simple but effective: experiments demonstrate our method can generate high-quality definitions for jargon and outperform state-of-the-art models significantly, e.g., BLEU score from 8.76 to 22.66 and human-annotated score from 2.34 to 4.04.

cs.CL↗
arXiv2022

DEER: Descriptive Knowledge Graph for Explaining Entity Relationships

We propose DEER (Descriptive Knowledge Graph for Explaining Entity Relationships) - an open and informative form of modeling entity relationships. In DEER, relationships between entities are represented by free-text relation descriptions. For instance, the relationship between entities of machine learning and algorithm can be represented as ``Machine learning explores the study and construction of algorithms that can learn from and make predictions on data.'' To construct DEER, we propose a self-supervised learning method to extract relation descriptions with the analysis of dependency patterns and generate relation descriptions with a transformer-based relation description synthesizing model, where no human labeling is required. Experiments demonstrate that our system can extract and generate high-quality relation descriptions for explaining entity relationships. The results suggest that we can build an open and informative knowledge graph without human annotation.

cs.CL↗