Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 488 publications
CrossCheck: Input Validation for WAN Control Systems
Rishabh Iyer
Isaac Keslassy
Sylvia Ratnasamy
Networked Systems Design and Implementation (NSDI) (2026) (to appear)
Preview abstract
We present CrossCheck, a system that validates inputs to the Software-Defined Networking (SDN) controller in a Wide Area Network (WAN). By detecting incorrect inputs—often stemming from bugs in the SDN control infrastructure—CrossCheck alerts operators before they trigger network outages.
Our analysis at a large-scale WAN operator identifies invalid inputs as a leading cause of major outages, and we show how CrossCheck would have prevented those incidents. We deployed CrossCheck as a shadow validation system for four weeks in a production WAN, during which it accurately detected the single incident of invalid inputs that occurred while sustaining a 0% false positive rate under normal operation, hence imposing little additional burden on operators. In addition, we show through simulation that CrossCheck reliably detects a wide range of invalid inputs (e.g., detecting demand perturbations as small as 5% with 100% accuracy) and maintains a near-zero false positive rate for realistic levels of noisy, missing, or buggy telemetry data (e.g., sustaining zero false positives with up to 30% of corrupted telemetry data).
View details
Preview abstract
This talk addresses the challenges of operating Google's monitoring systems at scale, handling terabytes of telemetry data and preventing overload from diverse workloads. We'll explore how Google's internal client library and Monarch, its planet-scale time-series database, work together for cost-effective data collection. Key principles include a distributed push model, dynamic client-side data reduction, centralized retention, and periodic metric analysis. The session will then bridge these concepts to the open-source world, discussing our work with OpenTelemetry's OpAMP protocol to achieve similar scalable and efficient telemetry collection. Attendees will gain insights into adapting these principles for cost savings and learn about our collaboration with the OpAMP SIG to benefit the broader community.
View details
Preview abstract
The rapid expansion of the Internet of Things (IoT) and smart home ecosystems has led to a fragmented landscape of user data management across consumer electronics (CE) such as Smart TVs, gaming consoles, and set-top boxes. Current onboarding processes on these devices are characterized by high friction due to manual data entry and opaque data-sharing practices. This paper introduces the User Data Sharing System (UDSS), a platform-agnostic framework designed to facilitate secure, privacy-first PII (Personally Identifiable Information) exchange between device platforms and third-party applications. Our system implements a Contextual Scope Enforcement (CSE) mechanism that programmatically restricts data exposure based on user intent—specifically distinguishing between Sign-In and Sign-Up workflows. Unlike cloud-anchored identity standards such as FIDO2/WebAuthn, UDSS is designed for shared, device-centric CE environments where persistent user-to-device bind-ing cannot be assumed. We further propose a tiered access model that balances developer needs with regulatory compliance (GDPR/CCPA). A proof-of-concept implementation on a reference ARMv8 Linux-based middleware demonstrates that UDSS reduces user onboarding latency by 65% and measurably reduces PII over-exposure risk through protocol-enforced data minimization. This framework provides a standardized approach to identity management in the heterogeneous CE market.
View details
XProf: An Open, Scalable and Extensible Profiling System for the Modern ML Stack
Robert Hundt
Naveen Kumar
Jose Baiocchi Paredes
Scott Goodson
Kelvin Le
Yin Zhang
Kan Cai
Sai Ganesh Bandiatmakuri
Yogesh SY
Ani Udipi
Vikas Aggarwal
Ninth Conference on Machine Learning and Systems (2026)
Preview abstract
Optimizing Large Models across thousands of accelerators requires deep system expertise. To address modern machine learning (ML) optimization needs, we present XProf, the ML profiler for the OpenXLA ecosystem. XProf delivers actionable optimization suggestions and in-depth performance analysis, empowering ML researchers and framework users to improve efficiency without specialized systems knowledge. XProf provides a unified, full-stack view of both host (CPU) and device (accelerator - TPUs/GPUs) performance, leveraging tools like the Roofline Model for comprehensive analysis. XProf’s distributed architecture is designed to monitor thousands of chips with minimal workload overhead (<1%). This architecture is made pluggable through the open-source PJRT C API extension, which has facilitated its adoption by third-party accelerator vendors. XProf has been instrumental in achieving significant efficiency gains at Google and winning MLPerf submissions. This paper presents the design and architecture of XProf, showcases its differentiating tools and capabilities, and highlights its impact within Google and across the industry as a state of the art ML profiler. XProf is available as part of the OpenXLA project at https://github.com/openxla/xprof.
View details
Preview abstract
Large language models (LLMs) are increasingly deployed as economic agents in marketplaces, auctions, and bidding settings. Anticipating their behavior in any specific deployment is hard. Existing strategic-reasoning benchmarks evaluate models on fixed canonical games. These benchmarks may saturate as the frontier improves, and they do not allow evaluators to generalize with confidence from benchmark performance to the varied and messy strategic environments that actual deployments involve. We introduce GENSTRAT, which uses procedurally generated strategic environments to address these challenges. Concretely, we generate a distribution of two-player zero-sum imperfect-information card games. The generator can draw fresh games on demand, allowing for evergreen evaluation and resistance to contamination. We pair the game distribution with a capability-profile methodology that decomposes model competence across six axes (state space, temporal depth, information sensitivity, opponent modeling, risk, and brittleness). We also introduce a jaggedness measure of within-distribution smoothness that detects when a model’s advantage jumps unpredictably between strategically similar games. We sample 50 benchmark games from a 2,000-game generated pool and evaluate nine frontier and open-weight LLMs in a head-to-head tournament with over 36,000 matches. Newer frontier-tier models score higher on average. Beyond that average, models with near-identical overall strength show qualitatively different capability profiles, and two of the top three leaderboard models (gpt-5 and claude) are noticeably more locally volatile than the third (gemini-3.1-pro), despite being close in overall strength. Together, the capability profile and the jaggedness measure give a deployment-relevant diagnostic that the overall ranking alone cannot provide.
View details
A simple and efficient implementation of strong call by need by an abstract machine
Małgorzata Biernacka
Witold Charatonik
Journal of Functional Programming, Volume 36 (2026)
Preview abstract
We present an abstract machine for a strong call-by-need strategy in the lambda calculus. The machine has been derived automatically from a higher-order evaluator that uses the technique of memothunks to implement laziness. The derivation has been done with the use of an off-the-shelf transformation tool implementing the "functional correspondence" between higher-order interpreters and abstract machines, and it yields a simple and concise description of the machine. We prove that the resulting machine conservatively extends the lazy version of Krivine machine for the weak call-by-need strategy, and that it simulates the normal-order strategy in bilinear number of steps.
View details
QProf: Fleetwide Transitive Cost Profiling for Warehouse-Scale Computers
Sam Xi
Ali Sheikh
Vance Lankhaar
Symposium on Operating Systems Principles (2026)
Preview abstract
Warehouse-scale services form the backbone of major cloud services relied on by billions of users every day. As these systems grow increasingly complex, understanding them and finding opportunities for optimization becomes more and more difficult. In this paper, we present QProf, a distributed systems profiler built upon RPC tracing. Going well beyond prior work that focuses on fleetwide profiling of single programs, QProf focuses on cost profiling of entire services. By treating a distributed program as if it were a single process, QProf can produce call-graph profiles of entire systems, so it can measure the transitive cost of services through the entire stack of backend dependencies. QProf is backed by a novel tracing mechanism called skeletal tracing which is exceedingly low-overhead and invisible to applications, ensuring that tracing minimally perturbs application behavior. An ambient per-query CPU profiler ensures high profiling coverage across thousands of microservices without manual instrumentation, and new fan-in APIs provide support for representing batched requests in a tracing data model that is tree-centric. QProf processes billions of traces per day to produce aggregated datasets which can be queried by engineers. Despite the sampled nature of traces, QProf is highly accurate in measuring QPS and CPU across thousands of microservices in an extremely diverse datacenter fleet. QProf has been deployed for every job in Google’s production fleet for several years. It has a myriad of use cases, and we present several case studies showing how it has been used to find the “room-at-the-top” in complex systems and optimize them across many dimensions.
View details
When “Correct” Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
Corina Pasareanu
Haizhong Zheng
Beidi Chen
Ravi Mangal
Xinyu Yang
James Song
Yibo Peng
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, San Diego, California, United States (2026), 15514–15546
Preview abstract
Code agents are increasingly trusted to autonomously fix bugs on platforms such as GitHub, yet their security evaluation focuses almost exclusively on functional correctness. In this paper, we reveal a novel type of threat to real-world code agents: Functionally Correct yet Vulnerable (FCV) patches, which pass all test cases but contain vulnerable code. With our proposed FCV-Attack, which can be deliberately crafted by malicious attackers or implicitly introduced by benign developers, we show that SOTA LLMs (e.g., ChatGPT and Claude) and agent scaffolds (e.g., SWE-agent and OpenHands) are all vulnerable to this FCV threat; across 12 agent-model combinations on SWE-Bench, the attack only requires black-box access and a single query to the code agent to perform the attack. For example, for CWE-538 (information exposure vulnerability), the FCV-Attack attains an attack success rate of 40.7% on GPT-5 Mini + OpenHands. Our results reveal an important security threat overlooked by current evaluation paradigms and urge the development of security-aware defenses for code agents.
View details
Preview abstract
Large-scale software systems frequently suffer from architectural rigidity caused by monolithic designs, tightly coupled integrations, and legacy technology stacks. Backend-forFrontend (BFF) architectures are increasingly adopted to address these challenges by decoupling frontend-specific requirements from backend domain services. However, designing a BFF layer requires a series of irreversible technology decisions across compute platforms, traffic routing, programming languages, frameworks, and API protocols. These decisions directly influence system latency, scalability, operational complexity, and long-term maintainability. This paper proposes a structured, metrics-driven decision framework to guide architects through foundational technology choices when designing BFF architectures. The framework decomposes the decision space into independent sub-problems, introduces weighted evaluation criteria, and applies quantitative scoring models to enable objective trade-off analysis. The approach is validated through a representative modernization scenario, demonstrating how systematic evaluation reduces architectural risk, resolves stakeholder disagreement, and improves performance and developer efficiency. The proposed framework is generic, repeatable, and applicable to a wide range of cloudnative system modernization efforts.
View details
ITHICA: Intra-Thread Instruction Checking Approach for Defect-Induced Silent Data Corruptions
Ioanna Vavelidou
Eric Xue Liu
Mike Fuller
Subhasish Mitra
Caroline Trippel
59th IEEE/ACM International Symposium on Microarchitecture (MICRO) (2026)
Preview abstract
Hyperscalers are reporting silent data corruptions (SDCs), presumed to be caused by silicon manufacturing defects, as a threat to datacenter reliability. To support datacenter testing efforts to detect defective CPU servers, this paper presentsITHICA, an approach and tool for automatically generating functional tests for defect-induced errors from arbitrary programs by inserting intra-thread, instruction-level error checks, primarily leveraging instruction duplication and output comparison. Our key insight is that the most pernicious defects (those most likely to escape manufacturing testing) cause inconsistent errors: two executions of the same instruction given the same inputs within the same thread can produce different architectural outputs depending on the execution context in which they run. By exploiting this insight, ITHICA uniquely enables arbitrary programs to serve as tests and localizes affected instructions concurrently with error detection. We use ITHICA to transform industrial hyperscaler tests (our baseline), datacenter programs, and common libraries into functional tests, and evaluate them on over 3,000 CPU servers. ITHICA checks detect 39% more defective servers than baseline industrial checks and yield novel findings on defect behavior that challenge conclusions drawn by prior hyperscaler fleet studies.
View details
LibEvoBench: Probing Temporal Knowledge Startification in Code Generation Models
Daniele Cipollone
Sergey Titov
Egor Bogomolov
Arie van Deursen
Advances in Neural Information Processing Systems (NeurIPS) (2026)
Preview abstract
Large software projects often depend on older versions of libraries, even as APIs continue to evolve across releases. This creates a challenge for LLMs: they must maintain knowledge of multiple API versions, not merely the latest or most common one. However, current LLMs, trained on temporally mixed corpora and lack explicit mechanisms for such version-specific reasoning, leading to anachronistic errors -- calling APIs as they exist in a different library version. To systematically evaluate this phenomenon, we introduce LibEvoBench, a multi-task benchmark spanning multiple versions of widely used Python libraries, along with a new metric, the Software Evolution Understanding Score (SEUS), to measure models' consistency when working with evolving APIs. Our results show that state-of-the-art models are largely version-oblivious: performance degrades for evolving APIs, while for stable APIs it remains the same across versions. Moreover, simply specifying the target version provides no benefit, while relevant documentation significantly boosts models' accuracy. These findings highlight a systematic limitation of current training paradigms and motivate new approaches for temporally grounded knowledge in code generation.
View details
From Unfinished to Done: Bridging the MDE Implementation Gap with Constrained LLMs
Jörg Christian Kirchhof
Lukas Netz
Dennis Mertens
Bernhard Rumpe
Proceedings of the ACM/IEEE 29th International Conference on Model Driven Engineering Languages and Systems, ACM (2026), pp. 152-163
Preview abstract
Model-driven engineering (MDE) excels at ensuring architectural consistency and managing complexity, yet extending generated code skeletons with project-specific business logic often remains a time-consuming manual task. Conversely, large language models (LLMs) offer immense flexibility in coding but may produce vibe-coded results—software that looks correct but fails to adhere to intended architectures and implicit requirements. An open challenge lies in harnessing the adaptability of LLMs to handle implementation details without sacrificing the deterministic correctness of the MDE scaffolding. Previous attempts have largely relied on unconstrained coding assistants or required a human in the loop for interacting with the LLM. To overcome this, we introduce Agentic Gap Filling, a hybrid pipeline where LLM prompts are embedded directly within the model to drive the generation of code skeletons. The generated code contains protected TODO regions, which LLM agents subsequently resolve and a jury of LLM review agents and separate testing agents immediately validates. We integrate this approach into the MontiThings framework, demonstrating a workflow where models define the architecture of a project while artificial intelligence (AI) agents act as developers and reviewers, filling in the logic. This synergy ensures the structural integrity of the generated system while providing the flexibility of LLMs to adapt to various domain requirements. Our evaluation across 32 test configurations demonstrates that this multiagent workflow achieves up to 93.21% functional accuracy after four iterations, while preserving the structural integrity of the generated system.
View details
CATWILD: Compiler Autotuning For TPU workloads in the Wild
Kirill Gugaev
Mike Burrows
Mangpo Phothilimthana
Naveen Kumar
Idan Nachman
Nacho Cano
David Liu
Zongwei Zhou
Tengyu Sun
Berkin Ilbeyi
Jie Sun
Vineetha Govindaraj
Ziqiang Feng
Hyojun Kim
Matheus Camargo
Chao Wang
Alex Wertheim
Domagoj Babic
Aleksey Orekhov
Emma Sevastian
Wenqi Cao
Shobha Vasudevan
Karthik Srinivasa Murthy
Jose Baiocchi Paredes
Emma Wang
Ryan Lefever
Arissa Wongpanich
Νikhil Sarda
Mehrdad Khani
Matt Bierbaum
Sami Abu-El-Haija
Samrat Ghosh
2026
Preview abstract
Compilers play a fundamental role at achieving peak performance for machine learning (ML) workloads. However, given the diverse nature of workloads and accelerators, compilers' heuristics and analytical cost models often result in sub-optimal performance, and thus waste precious datacenter resources. Furthermore, the multitude of tunable parameters and their complex interplay often make it impossible for human experts to manually find optimal configurations. In this paper, we present
CATWILD, a system that automatically optimizes ML jobs in Google's TPU fleet using compiler autotuning techniques. We describe CATWILD’s design and implementation, and evaluate its performance using a handful of representative metrics. We further report experiences and lessons learned from its five-year development and operation. To the best of our knowledge, CATWILD represents the first ML compiler autotuning solution deployed in datacenters at scale. Its successful rollout yielded substantial benefits, optimizing over 70\% of daily TPU training jobs and achieving significant chip savings
View details
Quantum Computing for Programmers, 2nd Edition
Robert Hundt
Cambridge University Press, Cambridge CB2 8BS, United Kingdom (2025)
Preview abstract
This introduction to quantum computing from a classical programmer's perspective is meant for students and practitioners alike. More than 50 quantum techniques and algorithms are explained with mathematical derivations and code for simulation, using an open-source code base in Python and C++. New material throughout this fully revised and expanded second edition includes new chapters on Quantum Machine Learning, State Preparation, and Similarity Tests. Coverage includes algorithms exploiting entanglement, black-box algorithms, the quantum Fourier transform, phase estimation, quantum walks, and foundational QML algorithms. Readers will find detailed, easy-to-follow derivations and implementations of Shor's algorithm, Grover's algorithm, SAT3, graph coloring, the Solovay-Kitaev algorithm, Moettoenen's algorithm, quantum mean, median, and minimum finding, Deutsch's algorithm, Bernstein-Vazirani, quantum teleportation and superdense coding, the CHSH game, and, from QML, the HHL algorithm, Euclidean distance, and PCA. The book also discusses productivity issues like quantum noise, error correction, quantum programming languages, compilers, and techniques for transpilation.
View details
PreFix: Optimizing the Performance of Heap-Intensive Applications
Chaitanya Mamatha Ananda
Rajiv Gupta
Han Shen
CGO 2025: International Symposium on Code Generation and Optimization, Las Vegas, NV, USA (to appear)
Preview abstract
Analyses of heap-intensive applications show that a small fraction of heap objects account for the majority of heap accesses and data cache misses. Prior works like HDS and HALO have shown that allocating hot objects in separate memory regions can improve spatial locality leading to better application performance. However, these techniques are constrained in two primary ways, limiting their gains. First, these techniques have Imperfect Separation, polluting the hot memory region with several cold objects. Second, reordering of objects across allocations is not possible as the original object allocation order is preserved. This paper presents a novel technique that achieves near perfect separation of hot objects via a new context mechanism that efficiently identifies hot objects with high precision. This technique, named PreFix, is based upon Preallocating memory for a Fixed small number of hot objects. The program, guided by profiles, is instrumented to compute context information derived from
dynamic object identifiers, that precisely identifies hot object allocations that are then placed at predetermined locations in the preallocated memory. The preallocated memory region for hot objects provides the flexibility to reorder objects across allocations and allows colocation of objects that are part of a hot data stream (HDS), improving spatial locality. The runtime overhead of identifying hot objects is not significant as this optimization is only focused on a small number of static hot allocation sites and dynamic hot objects. While there is an increase in the program’s memory foot-print, it is manageable and can be controlled by limiting the size of the preallocated memory. In addition, PreFix incorporates an object recycling optimization that reuses the same preallocated space to store different objects whose lifetimes are not expected to overlap. Our experiments with 13 heap-intensive applications yields reductions in execution times ranging from 2.77% to 74%. On average PreFix reduces execution time by 21.7% compared to 7.3% by HDS and 14% by HALO. This is due to PreFix’s precision in hot object identification, hot object colocation, and low runtime overhead.
View details
