paper-with-me

Papers

LoopTune: Optimizing Tensor Computations with Reinforcement Learning

2023-09-04 · Dejan Grubisic, Bram Wasti, Chris Cummins, John Mellor-Crummey, Aleksandar Zlateski

Advanced compiler technology is crucial for enabling machine learning applications to run on novel hardware, but traditional compilers fail to deliver performance, popular auto-tuners have long search times and expert-optimized libraries introduce unsustainable costs. To address this, we developed LoopTune, a deep reinforcement learning compiler that optimizes tensor computations in deep learning models for the CPU. LoopTune optimizes tensor traversal order while using the ultra-fast lightweight code generator LoopNest to perform hardware-specific optimizations. With a novel graph-based representation and action space, LoopTune speeds up LoopNest by 3.2x, generating an order of magnitude faster code than TVM, 2.8x faster than MetaSchedule, and 1.08x faster than AutoTVM, consistently performing at the level of the hand-tuned library Numpy. Moreover, LoopTune tunes code in order of seconds.

📄 PDF Abstract BibTeX arXiv:2309.01825

Code (0)

등록된 구현이 없습니다.

Tasks

CPUDeep Reinforcement Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Library 설명 없음
fail 설명 없음

Similar Papers 제목 키워드 기반

Quantum Circuit Optimization with AlphaTensor

2024-02-22 · Francisco J. R. Ruiz, Tuomas Laakkonen, Johannes Bausch, Matej Balog 외

A key challenge in realizing fault-tolerant quantum computers is circuit optimization. Focusing on the most expensive gates in fault-tolerant quantum computation (namely, the T gates), we address the problem of T-count o…

Deep Reinforcement LearningTensor Decomposition

Discovering faster matrix multiplication algorithms with reinforcement learning

2022-10-05 · Nature 2022 10 · Alhussein Fawzi, Matej Balog, Aja Huang, Thomas Hubert 외

Improving the efficiency of algorithms for fundamental computations can have a widespread impact, as it can affect the overall speed of a large amount of computations. Matrix multiplication is one such primitive task, oc…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

TensorIR: An Abstraction for Automatic Tensorized Program Optimization

2022-07-09 · Siyuan Feng, Bohan Hou, Hongyi Jin, Wuwei Lin 외

Deploying deep learning models on various devices has become an important topic. The wave of hardware specialization brings a diverse set of acceleration primitives for multi-dimensional tensor computations. These new ac…

BIG-bench Machine LearningDeep Learning

Atari games and Intel processors

2017-05-19 · Robert Adamski, Tomasz Grel, Maciej Klimek, Henryk Michalewski

The asynchronous nature of the state-of-the-art reinforcement learning algorithms such as the Asynchronous Advantage Actor-Critic algorithm, makes them exceptionally suitable for CPU computations. However, given the fact…

Atari GamesBIG-bench Machine LearningCPUDeep Reinforcement Learning+4

Reinforcement Learning for Optimizing Large Qubit Array based Quantum Sensor Circuits

2025-08-28 · Laxmisha Ashok Attisara, Sathish Kumar arxiv

As the number of qubits in a sensor increases, the complexity of designing and controlling the quantum circuits grows exponentially. Manually optimizing these circuits becomes infeasible. Optimizing entanglement distribu…

Quantum Machine LearningReinforcement Learning