arXiv subjects

Sujay Yadalam

Publications and source records attributed to Sujay Yadalam.

4 recordsLinked to original sources

arXiv2025

Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search

Systems resource management tasks rely primarily on hand-designed heuristics. However, growing hardware heterogeneity and workload diversity require heuristics specialized to particular deployment instances, making manual design expensive and difficult to scale. In this paper, we explore how to synthesize systems heuristics using LLMs. The main challenge is ensuring that generated heuristics execute safely, integrate correctly with the surrounding system, and still achieve strong performance. We propose Vulcan, a framework that identifies LLM-friendly interfaces that isolate core decision logic from the rest of the implementation. With Vulcan, LLM-generated code is restricted to simple stateless decision functions, while trusted runtime abstractions provide rich derived statistics for meaningful policy exploration without system-integration bugs. To ensure execution safety, LLMs synthesize heuristics in a restricted language, Anvil, that guarantees important properties by construction. We evaluate Vulcan across three well-studied domains and demonstrate up to 4.9x higher savings for spot-VM scheduling, up to 2x lower miss ratios for cache eviction, and up to 10% higher application performance for tiered-memory systems, while ensuring execution safety throughout.

cs.OS↗

arXiv2025

ARMS: Adaptive and Robust Memory Tiering System

Memory tiering systems seek cost-effective memory scaling by adding multiple tiers of memory. For maximum performance, frequently accessed (hot) data must be placed close to the host in faster tiers and infrequently accessed (cold) data can be placed in farther slower memory tiers. Existing tiering solutions such as HeMem, Memtis, and TPP use rigid policies with pre-configured thresholds to make data placement and migration decisions. We perform a thorough evaluation of the threshold choices and show that there is no single set of thresholds that perform well for all workloads and configurations, and that tuning can provide substantial speedups. Our evaluation identified three primary reasons why tuning helps: better hot/cold page identification, reduced wasteful migrations, and more timely migrations. Based on this study, we designed ARMS - Adaptive and Robust Memory tiering System - to provide high performance without tunable thresholds. We develop a novel hot/cold page identification mechanism relying on short-term and long-term moving averages, an adaptive migration policy based on cost/benefit analysis, and a bandwidth-aware batched migration scheduler. Combined, these approaches provide out-of-the-box performance within 3% the best tuned performance of prior systems, and between 1.26x-2.3x better than prior systems without tuning.

cs.OS↗

arXiv2025

From Good to Great: Improving Memory Tiering Performance Through Parameter Tuning

Memory tiering systems achieve memory scaling by adding multiple tiers of memory wherein different tiers have different access latencies and bandwidth. For maximum performance, frequently accessed (hot) data must be placed close to the host in faster tiers and infrequently accessed (cold) data can be placed in farther slower memory tiers. Existing tiering solutions employ heuristics and pre-configured thresholds to make data placement and migration decisions. Unfortunately, these systems fail to adapt to different workloads and the underlying hardware, so perform sub-optimally. In this paper, we improve performance of memory tiering by using application behavior knowledge to set various parameters (knobs) in existing tiering systems. To do so, we leverage Bayesian Optimization to discover the good performing configurations that capture the application behavior and the underlying hardware characteristics. We find that Bayesian Optimization is able to learn workload behaviors and set the parameter values that result in good performance. We evaluate this approach with existing tiering systems, HeMem and HMSDK. Our evaluation reveals that configuring the parameter values correctly can improve performance by 2x over the same systems with default configurations and 1.56x over state-of-the-art tiering system.

cs.OS↗

arXiv2024

Herding LLaMaS: Using LLMs as an OS Module

Computer systems are becoming increasingly heterogeneous with the emergence of new memory technologies and compute devices. GPUs alongside CPUs have become commonplace and CXL is poised to be a mainstay of cloud systems. The operating system is responsible for managing these hardware resources, requiring modification every time a new device is released. Years of research and development are sunk into tuning the OS for high performance with each new heterogeneous device. With the recent explosion in memory technologies and domain-specific accelerators, it would be beneficial to have an OS that could provide high performance for new devices without significant effort. We propose LLaMaS which can adapt to new devices easily. LLaMaS uses Large Language Models (LLMs) to extract the useful features of new devices from their textual description and uses these features to make operating system decisions at runtime. Adding support to LLaMaS for a new device is as simple as describing the system and new device properties in plaintext. LLaMaS reduces the burden on system administrators to enable easy integration of new devices into production systems. Preliminary evaluation using ChatGPT shows that LLMs are capable of extracting device features from text and make correct OS decisions based on those features.

cs.OS↗