Finding Compiler-Platform Interaction Bugs in Deep Learning Pipelines via Cross-Layer Constraints

• URL: http://arxiv.org/abs/2606.18421v1
• Date: Tue, 16 Jun 2026 19:15:17 GMT
• Title: Finding Compiler-Platform Interaction Bugs in Deep Learning Pipelines via Cross-Layer Constraints
• Abstract summary: Testing deep learning (DL) compilers is challenging as correctness depends on implicit constraints embedded throughout the compilation stack.<n>Existing testing approaches largely take type constraints to restrict input model generation.<n>We propose a scalable, automated DL compiler testing framework for, in tandem, finding compiler-platform interaction bugs.
• Score: 6.16235197336957
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The growing deployment of artificial intelligence (AI) necessitates robust deep learning (DL) compilers, such as TVM and ONNX-MLIR. These compilers take as input high-level AI models, lower them through multi-layer transformations, and specialize them to diverse hardware. Testing such compilers is uniquely challenging as correctness depends on implicit constraints embedded throughout the compilation stack. Existing testing approaches largely take type constraints to restrict input model generation and therefore emphasize type validation and monitor compilation crashes or coverage gains. This focus overlooks compiler-platform interaction bugs that arise from interleaved effects across compilation and execution environments. In this work, we propose a scalable, automated DL compiler testing framework for, in tandem, (1) finding compiler-platform interaction bugs and (2) enabling behavior equivalence partitioning. Our key insight is that these bugs are caused by violated assumptions arising from interactions across compilation passes and hardware platforms. Therefore, we move beyond constraining input generation and derive full-stack constraints. Our approach is three-fold. First, we design an automated approach to extract full-stack constraints that jointly guide model generation and characterize compilation behaviors. Second, we prioritize constraints that expose interaction-sensitive behaviors, so our generated models are capable of exercising deep compilation logic. Third, we enable behavior equivalence partitioning by automatically inserting assertions to monitor distinct compilation symptoms that coverage or pass/fail signals miss. We evaluated our tool, XCheck, on three widely-used DL compilers and found 2,034 bug-revealing cases, including memory overflows, integer overflows, and silent unexpected compilations that were rooted in compiler-platform interactions.

Related papers

• Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling [65.03665015319457]
  We propose an action-class-oriented diagnostic framework that decomposes multi-turn failures into two modes: action-class miscalibration and action-execution failure.<n>We validate it on a panel of tool-calling models across multiple multi-turn benchmarks.
  arXiv  Detail & Related papers  (2026-09-01T09:08:15Z)
• Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code [43.07697210931911]
  We introduce generative compilation, the first approach to obtaining compiler feedback on partial programs during generation.<n>We show that generative compilation reduces non-compiling outputs and improves functional correctness, relative to standard post-generation feedback.
  arXiv  Detail & Related papers  (2026-07-15T15:00:22Z)
• PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation [51.92442051257354]
  PairCoder improves essentially every benchmark whose artifact is verifiable, on full official metric suites rather than execution alone.<n>TikZ compile rate up 10 to 30 points on every model, at 2.9 to 9.2 times single model cost.
  arXiv  Detail & Related papers  (2026-07-02T08:36:02Z)
• ParityFuzz: Finding Inconsistencies across Solidity Compilers via Fine-Grained Mutation and Differential Analysis [37.31248744457945]
  ParityFuzz is a cross-compiler differential testing framework for Solidity.<n>It derives mutation rules, including syntax- and boundary-oriented rules, by analyzing compilers and execution environments.<n>It compiles and executes programs across multiple compilers, then normalizes and compares results to detect inconsistencies.
  arXiv  Detail & Related papers  (2026-05-09T16:53:45Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Isolating Compiler Bugs through Compilation Steps Analysis [5.783745108952491]
  CompSCAN is a novel compiler bug isolation technique that applies analysis over the sequence of compilation steps.<n>We evaluate CompSCAN on 185 real-world LLVM and GCC bugs.<n>Compared with ETEM and ODFL, CompSCAN achieves relative improvements of 44.51% / 50.18% / 36.24% / 24.49% over ETEM, and 31.58% / 49.12% / 44.93% / 21.78% over ODFL on those metrics.
  arXiv  Detail & Related papers  (2025-10-15T03:58:02Z)
• SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving [90.32201622392137]
  We present SwingArena, a competitive evaluation framework for Large Language Models (LLMs)<n>Unlike traditional static benchmarks, SwingArena models the collaborative process of software by pairing LLMs as iterations, who generate patches, and reviewers, who create test cases and verify the patches through continuous integration (CI) pipelines.
  arXiv  Detail & Related papers  (2025-05-29T18:28:02Z)
• Type-Constrained Code Generation with Language Models [51.03439021895432]
  We introduce a type-constrained decoding approach that leverages type systems to guide code generation.<n>For this purpose, we develop novel prefix automata and a search over inhabitable types, forming a sound approach to enforce well-typedness on LLM-generated code.<n>Our approach reduces compilation errors by more than half and significantly increases functional correctness in code synthesis, translation, and repair tasks.
  arXiv  Detail & Related papers  (2025-04-12T15:03:00Z)
• Commit0: Library Generation from Scratch [77.38414688148006]
  Commit0 is a benchmark that challenges AI agents to write libraries from scratch.<n>Agents are provided with a specification document outlining the library's API as well as a suite of interactive unit tests.<n> Commit0 also offers an interactive environment where models receive static analysis and execution feedback on the code they generate.
  arXiv  Detail & Related papers  (2024-12-02T18:11:30Z)
• Evolutionary Generative Fuzzing for Differential Testing of the Kotlin Compiler [14.259471945857431]
  We investigate the effectiveness of differential testing in finding bugs within the Kotlin compilers developed at JetBrains. We propose a black-box generative approach that creates input programs for the K1 and K2 compilers. Our case study shows that the proposed approach effectively detects bugs in K1 and K2; these bugs have been confirmed and (some) fixed by JetBrains developers.
  arXiv  Detail & Related papers  (2024-01-12T16:01:12Z)
• Weak Memory Demands Model-based Compiler Testing [0.0]
  A compiler bug arises if the behaviour of a compiled concurrent program, as allowed by its architecture memory model, is not a behaviour permitted by the source program under its source model. We observe that processor implementations are increasingly exploiting the behaviour of relaxed architecture models.
  arXiv  Detail & Related papers  (2024-01-12T15:50:32Z)
• Effective Random Test Generation for Deep Learning Compilers [16.065653480978092]
  Isra is a domain-specific constraint solver that resolves the constraints from the semantic specifications without backtracking.<n>We implement and apply our approach to three popular real-world deep learning compilers including TVM, Glow, and a commercial compiler named SophGo.<n>Isra is more effective than the state-of-the-art approaches and the baseline approaches on constructing valid test inputs for compiler-bug detection.
  arXiv  Detail & Related papers  (2023-02-02T03:00:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.