Jongryool Kim

Donghwan Kim, Prakhar Singh, Younghoon Min et al.

Agentic AI completes tasks through iterative planning, tool use, and reasoning based on observed outcomes. Despite its popularity, its system-level behavior remains poorly understood, particularly for complex datasets and agent architectures-owing to highly non-deterministic execution, prohibitive evaluation costs, and limited visibility into proprietary models. This paper presents GAIATrace, the first token-level trace dataset of two state-of-the-art agentic systems (MiroThinker and OWL) running GAIA, a benchmark composed of a heterogeneous mix of general-purpose tasks. Unlike prior trace datasets, GAIATrace captures full reasoning tokens, task-level structures, and activities of every major participating LLMs, enabling in-depth systems research. Complementing the dataset, we present Vidur-Agent, a trace-driven simulator that can replay GAIATrace to perform reproducible, low-cost system evaluation across diverse simulated environments. Using both artifacts, we characterize how modern agentic systems handle general tasks and how various system design choices shape their behavior, yielding several unique findings.

Xin Huang, Jongryool Kim, Bradley Rees et al.

Graph neural networks (GNNs) have received great attention due to their success in various graph-related learning tasks. Several GNN frameworks have then been developed for fast and easy implementation of GNN models. Despite their popularity, they are not well documented, and their implementations and system performance have not been well understood. In particular, unlike the traditional GNNs that are trained based on the entire graph in a full-batch manner, recent GNNs have been developed with different graph sampling techniques for mini-batch training of GNNs on large graphs. While they improve the scalability, their training times still depend on the implementations in the frameworks as sampling and its associated operations can introduce non-negligible overhead and computational cost. In addition, it is unknown how much the frameworks are 'eco-friendly' from a green computing perspective. In this paper, we provide an in-depth study of two mainstream GNN frameworks along with three state-of-the-art GNNs to analyze their performance in terms of runtime and power/energy consumption. We conduct extensive benchmark experiments at several different levels and present detailed analysis results and observations, which could be helpful for further improvement and optimization.

Xi Wang, Jie Liu, Shuangyan Yang et al.

Memory tiering provides a cost-effective solution to increase memory capacity, utilization, and even bandwidth. Memory tiering relies on system software for memory profiling, detection of frequently accessed pages, and page migration. Such a system software often comes with system parameters. The configurations of those parameters impact application performance. We comprehensively classify system parameters, and characterize the sensitivity of application performance to them using representative memory tiering solutions. Furthermore, we introduce a lightweight and user-friendly framework PTMT, which automates tuning of parameters at runtime for various memory tiering solutions. We identify major challenges for online tuning of memory tiering. PTMT uses a hybrid "offline + online" tuning method: while the offline phase builds a performance database for online queries and reduces runtime overhead, the online phase uses reinforcement learning (customized to memory tiering) to tune. PTMT improves performance by 30%, 26%, 21%, and 14%, on four memory tiering solutions (TPP, UPM, Colloid, and AutoNUMA), compared to using the default configurations. PTMT outperforms the state-of-the-art by 32% on average.

Wentao Ni, Kangqi Zhang, Zhongming Yu et al.

As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse attention for scalable inference. Fixed-budget top-k sparse attention cannot adapt to heterogeneous attention distributions across heads and layers, whereas top-p sparse attention directly preserves attention mass and provides stronger accuracy guarantees. Existing top-p methods, however, fail to jointly optimize top-p accuracy, selection overhead, and sparse attention cost, which limits their overall efficiency. We present Double-P, a hierarchical sparse attention framework that optimizes all three stages. Double-P first performs coarse-grained top-p estimation at the cluster level using size-weighted centroids, then adaptively refines computation through a second top-p stage that allocates token-level attention only when needed. Across long-context benchmarks, Double-P consistently achieves near-zero accuracy drop, reducing attention computation overhead by up to 1.8x and delivers up to 1.3x end-to-end decoding speedup over state-of-the-art fixed-budget sparse attention methods.

Xin Huang, Weipeng Zhuo, Minh Phu Vuong et al.

Graph neural networks have been shown successful in recent years. While different GNN architectures and training systems have been developed, GNN training on large-scale real-world graphs still remains challenging. Existing distributed systems load the entire graph in memory for graph partitioning, requiring a huge memory space to process large graphs and thus hindering GNN training on such large graphs using commodity workstations. In this paper, we propose CATGNN, a cost-efficient and scalable distributed GNN training system which focuses on scaling GNN training to billion-scale or larger graphs under limited computational resources. Among other features, it takes a stream of edges as input, instead of loading the entire graph in memory, for partitioning. We also propose a novel streaming partitioning algorithm named SPRING for distributed GNN training. We verify the correctness and effectiveness of CATGNN with SPRING on 16 open datasets. In particular, we demonstrate that CATGNN can handle the largest publicly available dataset with limited memory, which would have been infeasible without increasing the memory space. SPRING also outperforms state-of-the-art partitioning algorithms significantly, with a 50% reduction in replication factor on average.

Donghwan Kim, Xin Gu, Jinho Baek et al.

Machine learning (ML) models memorize and leak training data, causing serious privacy issues to data owners. Training algorithms with differential privacy (DP), such as DP-SGD, have been gaining attention as a solution. However, DP-SGD adds a noise at each training iteration, which degrades the accuracy of the trained model. To improve accuracy, a new family of approaches adds carefully designed correlated noises, so that noises cancel out each other across iterations. We performed an extensive characterization study of these new mechanisms, for the first time to the best of our knowledge, and show they incur non-negligible overheads when the model is large or uses large embedding tables. Motivated by the analysis, we propose Cocoon, a hardware-software co-designed framework for efficient training with correlated noises. Cocoon accelerates models with embedding tables through pre-computing and storing correlated noises in a coalesced format (Cocoon-Emb), and supports large models through a custom near-memory processing device (Cocoon-NMP). On a real system with an FPGA-based NMP device prototype, Cocoon improves the performance by 2.33-10.82x(Cocoon-Emb) and 1.55-3.06x (Cocoon-NMP).

Luyi Kang, Yuqi Xue, Weiwei Jia et al.

In-storage computing with modern solid-state drives (SSDs) enables developers to offload programs from the host to the SSD. It has been proven to be an effective approach to alleviate the I/O bottleneck. To facilitate in-storage computing, many frameworks have been proposed. However, few of them treat the in-storage security as the first citizen. Specifically, since modern SSD controllers do not have a trusted execution environment, an offloaded (malicious) program could steal, modify, and even destroy the data stored in the SSD. In this paper, we first investigate the attacks that could be conducted by offloaded in-storage programs. To defend against these attacks, we build a lightweight trusted execution environment, named IceClave for in-storage computing. IceClave enables security isolation between in-storage programs and flash management functions that include flash address translation, data access control, and garbage collection, with TrustZone extensions. IceClave also achieves security isolation between in-storage programs by enforcing memory integrity verification of in-storage DRAM with low overhead. To protect data loaded from flash chips, IceClave develops a lightweight data encryption/decryption mechanism in flash controllers. We develop IceClave with a full system simulator. We evaluate IceClave with a variety of data-intensive applications such as databases. Compared to state-of-the-art in-storage computing approaches, IceClave introduces only 7.6% performance overhead, while enforcing security isolation in the SSD controller with minimal hardware cost. IceClave still keeps the performance benefit of in-storage computing by delivering up to 2.31$\times$ better performance than the conventional host-based trusted computing approach.