Guided Tensor Lifting

• URL: http://arxiv.org/abs/2504.19705v1
• Date: Mon, 28 Apr 2025 12:00:10 GMT
• Title: Guided Tensor Lifting
• Authors: Yixuan Li, José Wesley de Souza Magalhães, Alexander Brauckmann, Michael F. P. O'Boyle, Elizabeth Polgreen,
• Abstract summary: Domain-specific languages (s) for machine learning are revolutionizing the speed and efficiency of machine learning workloads.<n>To take advantage of these capabilities, a user must first translate their legacy code from the language it is currently written in, into the new DSL.<n>Process of automatically lifting code into these DSLs has been identified by several recent works, which propose program synthesis as a solution.
• Score: 54.10411390218929
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Domain-specific languages (DSLs) for machine learning are revolutionizing the speed and efficiency of machine learning workloads as they enable users easy access to high-performance compiler optimizations and accelerators. However, to take advantage of these capabilities, a user must first translate their legacy code from the language it is currently written in, into the new DSL. The process of automatically lifting code into these DSLs has been identified by several recent works, which propose program synthesis as a solution. However, synthesis is expensive and struggles to scale without carefully designed and hard-wired heuristics. In this paper, we present an approach for lifting that combines an enumerative synthesis approach with a Large Language Model used to automatically learn the domain-specific heuristics for program lifting, in the form of a probabilistic grammar. Our approach outperforms the state-of-the-art tools in this area, despite only using learned heuristics.

Related papers

• MIREncoder: Multi-modal IR-based Pretrained Embeddings for Performance Optimizations [6.919817502555546]
  In this paper, we propose MIREncoder, a Multi-modal IR-based Auto-Encoder that can be pre-trained to generate a learned embedding space. A multi-modal approach enables us to better extract features from compilable programs. Our evaluations will show that our proposed approach can outperform the state of the art while reducing overhead.
  arXiv  Detail & Related papers  (2024-07-02T13:00:19Z)
• Meaning-Typed Programming: Language-level Abstractions and Runtime for GenAI Applications [8.308424118055981]
  Software is rapidly evolving from logical code to neuro-integrated applications that leverage generative AI and large language models (LLMs) for application functionality. This paper proposes meaning-typed programming (MTP), a novel approach to simplify the creation of neuro-integrated applications.
  arXiv  Detail & Related papers  (2024-05-14T21:12:01Z)
• On-the-Fly Syntax Highlighting: Generalisation and Speed-ups [2.208443815105053]
  On-the-fly syntax highlighting is the task of rapidly associating visual secondary notation values with each character of a language derivation. Speed constraints are essential to ensure tool usability, manifesting as responsiveness for end users accessing online source code. achieving precise highlighting is critical for enhancing code comprehensibility. addressing the development costs of such resolvers is imperative, given the multitude of programming language versions.
  arXiv  Detail & Related papers  (2024-02-13T19:43:22Z)
• Engineering A Large Language Model From Scratch [0.0]
  Atinuke is a Transformer-based neural network that optimises performance across various language tasks. It can emulate human-like language by extracting features and learning complex mappings. System achieves state-of-the-art results on natural language tasks whilst remaining interpretable and robust.
  arXiv  Detail & Related papers  (2024-01-30T04:29:48Z)
• LILO: Learning Interpretable Libraries by Compressing and Documenting Code [71.55208585024198]
  We introduce LILO, a neurosymbolic framework that iteratively synthesizes, compresses, and documents code. LILO combines LLM-guided program synthesis with recent algorithmic advances in automated from Stitch. We find that AutoDoc boosts performance by helping LILO's synthesizer to interpret and deploy learned abstractions.
  arXiv  Detail & Related papers  (2023-10-30T17:55:02Z)
• Using Document Similarity Methods to create Parallel Datasets for Code Translation [60.36392618065203]
  Translating source code from one programming language to another is a critical, time-consuming task. We propose to use document similarity methods to create noisy parallel datasets of code. We show that these models perform comparably to models trained on ground truth for reasonable levels of noise.
  arXiv  Detail & Related papers  (2021-10-11T17:07:58Z)
• Leveraging Language to Learn Program Abstractions and Search Heuristics [66.28391181268645]
  We introduce LAPS (Language for Abstraction and Program Search), a technique for using natural language annotations to guide joint learning of libraries and neurally-guided search models for synthesis. When integrated into a state-of-the-art library learning system (DreamCoder), LAPS produces higher-quality libraries and improves search efficiency and generalization.
  arXiv  Detail & Related papers  (2021-06-18T15:08:47Z)
• Learning Adaptive Language Interfaces through Decomposition [89.21937539950966]
  We introduce a neural semantic parsing system that learns new high-level abstractions through decomposition. Users interactively teach the system by breaking down high-level utterances describing novel behavior into low-level steps.
  arXiv  Detail & Related papers  (2020-10-11T08:27:07Z)
• Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients [6.09170287691728]
  This paper presents Enzyme, a high-performance automatic differentiation (AD) compiler plugin for the LLVM compiler framework. Enzyme synthesizes gradients for programs written in any language whose compiler targets LLVM intermediate representation (IR) On a machine-learning focused benchmark suite including Microsoft's ADBench, AD on optimized IR achieves a geometric mean speedup of 4.5x over AD on IR.
  arXiv  Detail & Related papers  (2020-10-04T22:32:51Z)
• Synthetic Datasets for Neural Program Synthesis [66.20924952964117]
  We propose a new methodology for controlling and evaluating the bias of synthetic data distributions over both programs and specifications. We demonstrate, using the Karel DSL and a small Calculator DSL, that training deep networks on these distributions leads to improved cross-distribution generalization performance.
  arXiv  Detail & Related papers  (2019-12-27T21:28:10Z)

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.