arXiv subjects

Jovan Stojkovic

Publications and source records attributed to Jovan Stojkovic.

11 recordsLinked to original sources

arXiv2026

Gutenberg: Taming Latency-Critical Cloud Services with Near-Data-Processing

Latency-critical cloud services place growing pressure on memory while requiring isolation, fairness, and predictable QoS. Near-data processing (NDP) reduces data movement by executing requests close to memory, and prior systems further improve locality through caching and replication. However, writes make replica maintenance expensive, while uneven compute and memory traffic can overload a few NDP units and increase tail latency. Existing throughput-oriented schedulers do not fully address these challenges for co-located cloud services. We present Gutenberg, a CPU+NDP for mutable, latency-critical cloud services. Gutenberg stages subpage updates in a CPU-resident delta buffer, allowing hot writable pages to remain replicated without eager full-page synchronization. It also adopts CPU helper cores to assist request execution when NDP execution or replica maintenance becomes costly. An online controller jointly decides page placement, replication, CPU/NDP execution, and routing using access patterns, queue pressure, and feedback from prior decisions. The system further enforces isolation and fair resource allocation across services. We also model-check CPU--NDP coordination protocol for correctness. We evaluate on TailBench using ZSim with Ramulator-calibrated memory timing. Across evaluated services, Gutenberg outperforms prior systems, reducing average and p99 latency by up to 80.4% and 85.8%. It also improves isolation and fairness while adapting to changing workload behaviors.

cs.DC↗

arXiv2026

Architectural Implications of Agentic AI Workflows

Agentic AI is emerging in datacenters, but its architectural implications remain unexplored. We organize agentic workflows in a taxonomy and present its first architectural characterization with a production study at Microsoft Azure and a controlled study of open-source frameworks. We show that agentic execution is fragmented and heterogeneous. Requests expand into a workflow of LLM inferences, tool invocations, and orchestration decisions that repeatedly cross the CPU-GPU boundary. Our taxonomy explains how this fragmentation turns into resource demand. As orchestration and tools run on the host, the CPU sits on the critical path. Execution structure sets the load over time, which stays low with sudden spikes. Model composition sets how evenly the workflow uses the GPUs. Diversity in tasks and tools widens this range even further. These characteristics expose architectural mismatches of conventional uniform servers. Fragmented execution strands CPU and GPU capacity despite bursty demand. Different software roles make homogeneous CPU provisioning inefficient. Finally, multiplexing many agents onto shared cores degrades microarchitectural locality. Guided by our findings, we derive implications for agentic servers and examine them through Agora, our prototype for commodity servers. Agora dynamically harvests idle CPU cores for co-located throughput work, while protecting agentic tail latency against tool spikes. It oversubscribes GPU memory by placing more agents on each GPU, prefetching the next agent's state to hide swap latency. To match the machine to the heterogeneous roles, Agora pools cores by role and applies affinity-aware scheduling to restore locality. It automatically tunes mechanisms to the workload. Agora improves utilization and server throughput while preserving agent tail latency. Our insights also identify key directions for future server architectures for agentic AI.

cs.AI↗

arXiv2026

AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane Policies

The efficiency of a datacenter rests on its control plane policies. Designing these policies is increasingly hard: the hardware-software stack grows fast, the design space is vast and interdependent, and prototyping a single policy takes months. Agentic AI promises to automate this search. Off the shelf, however, it falls short on three fronts. It is not formal: with no structured, searchable statement of the problem, the search has little structure to exploit and hard constraints are not guaranteed. It is not transferable: each task is solved from scratch, so nothing learned on one task carries to the next. Finally, it is not systematic: relying on the LLM as the sole source of candidates, it explores a narrow slice of the design space and settles into local optima. We introduce AtumAI, a framework that generates datacenter control-plane policies with agentic AI, making the process formal, transferable, and systematic. From a goal stated in plain language, AtumAI autonomously proposes, tests, and refines candidate policies until one satisfies the request. It does so through two components. The Datacenter Task Compiler automates problem formulation: it compiles the request into a formal, machine-checkable, and searchable specification of the task's objectives, constraints, decision variables, and evaluation methodology. The Evolutionary Design Discovery Loop then searches this specification, expanding the search beyond the LLM itself via a diffusion model, an evolutionary algorithm, and a surrogate model. Together, they reduce onboarding a new task from months of engineering to writing its description. We evaluate AtumAI on three control-plane tasks with distinct problem scopes, design spaces, and trade-offs: workload placement, resource scaling, and power management. Across all tasks, the policies generated by AtumAI consistently outperform expert-engineered baselines.

cs.AI↗

arXiv2026

Provisioning to Runtime Optimization of a 100 MW-Scale AI Cluster

The electric power supply for AI data centers is now the most significant bottleneck in the race toward Artificial General Intelligence, surpassing even the constraint of AI accelerator availability. To our knowledge, this paper is the first to describe the end-to-end power management process for a hyper-scale AI datacenter; from early power planning to accommodate next-generation accelerators 6--12 months before their general availability, to tuning power settings after large scale deployment, and finally to dynamic, runtime power management for evolving workloads. We present detailed power measurements for a 150 MW datacenter hosting a cluster of 83K GB200 GPUs. We share insights from building this state-of-the-art AI cluster. We hope this work encourages practitioners across the industry to share their own experiences as well.

cs.AR↗

arXiv2026

Nexus: Transparent I/O Offloading for High-Density Serverless Computing

Serverless computing relies on extreme multi-tenancy to remain economically viable, driving providers to rely on virtual machines (VMs) that ensure strong isolation and seamless ecosystem compatibility with the FaaS programming model. However, current architectures tightly couple application processing logic with I/O processing, forcing every VM to duplicate a heavy communication fabric (cloud SDK, RPC, and TCP/IP). Our analysis reveals this duplication consumes over 25% of a function's memory footprint, and may double the CPU cycles in VMs compared to bare-metal execution. While prior systems attempt to solve this using WebAssembly or library OSes, they naively sacrifice ecosystem compatibility, forcing developers to migrate code and dependencies to new languages. We introduce Nexus, a serverless-native KVM-based hypervisor that transparently decouples compute from I/O. Nexus shifts the execution model by intercepting communication fabric at the API boundary and offloading it to an always-on host shared backend via zero-copy shared memory. This removes the heavyweight communication fabric from the guest VM, while preserving the conventional serverless programming model. By structurally separating these domains, Nexus unlocks asynchronous I/O optimizations: overlapping input payload prefetching with VM restoration from a snapshot and writing output payloads back to storage off the critical path. Compared to the production baseline, Nexus reduces overall node-level CPU and memory consumption by up to 44% and 31%, respectively, thus increasing deployment density by 37%. Also, Nexus reduces warm- and cold-start latency by 39% and 10%, respectively, bringing the response time within 20% of that of a WASM-based, ecosystem-incompatible hypervisor.

cs.DC↗

arXiv2025

Rearchitecting Datacenter Lifecycle for AI: A TCO-Driven Framework

The rapid rise of large language models (LLMs) has been driving an enormous demand for AI inference infrastructure, mainly powered by high-end GPUs. While these accelerators offer immense computational power, they incur high capital and operational costs due to frequent upgrades, dense power consumption, and cooling demands, making total cost of ownership (TCO) for AI datacenters a critical concern for cloud providers. Unfortunately, traditional datacenter lifecycle management (designed for general-purpose workloads) struggles to keep pace with AI's fast-evolving models, rising resource needs, and diverse hardware profiles. In this paper, we rethink the AI datacenter lifecycle scheme across three stages: building, hardware refresh, and operation. We show how design choices in power, cooling, and networking provisioning impact long-term TCO. We also explore refresh strategies aligned with hardware trends. Finally, we use operation software optimizations to reduce cost. While these optimizations at each stage yield benefits, unlocking the full potential requires rethinking the entire lifecycle. Thus, we present a holistic lifecycle management framework that coordinates and co-optimizes decisions across all three stages, accounting for workload dynamics, hardware evolution, and system aging. Our system reduces the TCO by up to 40\% over traditional approaches. Using our framework we provide guidelines on how to manage AI datacenter lifecycle for the future.

cs.AI↗

arXiv2025

TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms

The rising demand for generative large language models (LLMs) poses challenges for thermal and power management in cloud datacenters. Traditional techniques often are inadequate for LLM inference due to the fine-grained, millisecond-scale execution phases, each with distinct performance, thermal, and power profiles. Additionally, LLM inference workloads are sensitive to various configuration parameters (e.g., model parallelism, size, and quantization) that involve trade-offs between performance, temperature, power, and output quality. Moreover, clouds often co-locate SaaS and IaaS workloads, each with different levels of visibility and flexibility. We propose TAPAS, a thermal- and power-aware framework designed for LLM inference clusters in the cloud. TAPAS enhances cooling and power oversubscription capabilities, reducing the total cost of ownership (TCO) while effectively handling emergencies (e.g., cooling and power failures). The system leverages historical temperature and power data, along with the adaptability of SaaS workloads, to: (1) efficiently place new GPU workload VMs within cooling and power constraints, (2) route LLM inference requests across SaaS VMs, and (3) reconfigure SaaS VMs to manage load spikes and emergency situations. Our evaluation on a large GPU cluster demonstrates significant reductions in thermal and power throttling events, boosting system efficiency.

cs.DC↗

arXiv2024

Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments

The widespread adoption of LLMs has driven an exponential rise in their deployment, imposing substantial demands on inference clusters. These clusters must handle numerous concurrent queries for different LLM downstream tasks. To handle multi-task settings with vast LLM parameter counts, methods like Low-Rank Adaptation (LoRA) enable task-specific fine-tuning while sharing most of the base LLM model across tasks. Hence, they allow concurrent task serving with minimal memory requirements. However, existing LLM serving systems face inefficiencies: they overlook workload heterogeneity, impose high link bandwidth from frequent adapter loading, and suffer from head-of-line blocking in their schedulers. To address these challenges, we present Chameleon, a novel LLM serving system optimized for many adapter environments, that relies on two core ideas: adapter caching and adapter-aware scheduling. First, Chameleon caches popular adapters in GPU memory, minimizing the adapter loading times. Importantly, it uses the otherwise idle GPU memory, avoiding extra memory costs. Second, Chameleon uses a non-preemptive multi-queue scheduling to efficiently account for workload heterogeneity. In this way, Chameleon simultaneously prevents head of line blocking and starvation. We implement Chameleon on top of a state-of-the-art LLM serving platform and evaluate it with real-world production traces and open-source LLMs. Under high loads, Chameleon reduces P99 and P50 TTFT latency by 80.7% and 48.1%, respectively, while improving throughput by 1.5x compared to state-of-the-art baselines.

cs.DC↗

arXiv2024

DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency

The rapid evolution and widespread adoption of generative large language models (LLMs) have made them a pivotal workload in various applications. Today, LLM inference clusters receive a large number of queries with strict Service Level Objectives (SLOs). To achieve the desired performance, these models execute on power-hungry GPUs causing the inference clusters to consume large amount of energy and, consequently, result in excessive carbon emissions. Fortunately, we find that there is a great opportunity to exploit the heterogeneity in inference compute properties and fluctuations in inference workloads, to significantly improve energy-efficiency. However, such a diverse and dynamic environment creates a large search-space where different system configurations (e.g., number of instances, model parallelism, and GPU frequency) translate into different energy-performance trade-offs. To address these challenges, we propose DynamoLLM, the first energy-management framework for LLM inference environments. DynamoLLM automatically and dynamically reconfigures the inference cluster to optimize for energy and cost of LLM serving under the service's performance SLOs. We show that at a service-level, DynamoLLM conserves 53% energy and 38% operational carbon emissions, and reduces 61% cost to the customer, while meeting the latency SLOs.

cs.AI↗

arXiv2024

Workload Intelligence: Punching Holes Through the Cloud Abstraction

Today, cloud workloads are essentially opaque to the cloud platform. Typically, the only information the platform receives is the virtual machine (VM) type and possibly a decoration to the type (e.g., the VM is evictable). Similarly, workloads receive little to no information from the platform; generally, workloads might receive telemetry from their VMs or exceptional signals (e.g., shortly before a VM is evicted). The narrow interface between workloads and platforms has several drawbacks: (1) a surge in VM types and decorations in public cloud platforms complicates customer selection; (2) essential workload characteristics (e.g., low availability requirements, high latency tolerance) are often unspecified, hindering platform customization for optimized resource usage and cost savings; and (3) workloads may be unaware of potential optimizations or lack sufficient time to react to platform events. In this paper, we propose a framework, called Workload Intelligence (WI), for dynamic bi-directional communication between cloud workloads and cloud platform. Via WI, workloads can programmatically adjust their key characteristics, requirements, and even dynamically adapt behaviors like VM priorities. In the other direction, WI allows the platform to programmatically inform workloads about upcoming events, opportunities for optimization, among other scenarios. Because of WI, the cloud platform can drastically simplify its offerings, reduce its costs without fear of violating any workload requirements, and reduce prices to its customers on average by 48.8%.

cs.DC↗

arXiv2024

Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference

With the ubiquitous use of modern large language models (LLMs) across industries, the inference serving for these models is ever expanding. Given the high compute and memory requirements of modern LLMs, more and more top-of-the-line GPUs are being deployed to serve these models. Energy availability has come to the forefront as the biggest challenge for data center expansion to serve these models. In this paper, we present the trade-offs brought up by making energy efficiency the primary goal of LLM serving under performance SLOs. We show that depending on the inputs, the model, and the service-level agreements, there are several knobs available to the LLM inference provider to use for being energy efficient. We characterize the impact of these knobs on the latency, throughput, as well as the energy. By exploring these trade-offs, we offer valuable insights into optimizing energy usage without compromising on performance, thereby paving the way for sustainable and cost-effective LLM deployment in data center environments.

cs.AI↗