Sep 4, 2023 · We developed LoopTune, a deep reinforcement learning compiler that optimizes tensor computations in deep learning models for the CPU.
Sep 4, 2023 · To address this, we developed LoopTune, a deep reinforcement learning compiler that optimizes tensor computations in deep learning models for ...
LoopTune optimizes tensor traversal order while using the ultra-fast lightweight code generator LoopNest to perform hardware-specific optimizations. With a ...
A deep reinforcement learning-based framework for optimizing tensor computations. LoopTune extends ultra-fast lightweight code generator LoopStack.
We introduce a novel paradigm in compiler optimization powered by Large Language Models with compiler feedback to optimize the code size of LLVM assembly.
LoopTune: Optimizing Tensor Computations with Reinforcement Learning. Paper • 2309.01825 • Published Sep 4, 2023 • 1 · Utility-based Perturbed Gradient Descent ...
Proceedings of the 4th Workshop on Machine Learning and Systems, 91-97, 2024. 3, 2024. LoopTune: Optimizing Tensor Computations with Reinforcement Learning. D ...
LoopTune: Optimizing Tensor Computations with Reinforcement Learning · no code ... Profile Guided Optimization without Profiles: A Machine Learning Approach.
We propose a. Reinforcement Learning (RL) approach combined with Graph Neural Networks (GNN) to address the contraction ordering problem. The problem is ...
Missing: LoopTune: | Show results with:LoopTune:
LoopTune defines a novel action space shown in Figure 3 and introduces the abstraction of an agent that traverses loop nests and applies actions on each loop.