ALT: Breaking the Wall between Data Layout and Loop Optimizations for Deep Learning Compilation
Zhiying Xu, Jiafan Xu, Hongding Peng, Wei Wang, Xiaoliang Wang, Haoran Wan, Haipeng Dai, Yixu Xu, Hao Cheng, Kun Wang, Guihai Chen
Abstract
Deep learning models rely on highly optimized tensor libraries for efficient inference on heterogeneous hardware. Current deep compilers typically predetermine layouts of tensors and then optimize loops of operators. However, such unidirectional and one-off workflow strictly separates graph-level optimization and operator-level optimization into different system layers, missing opportunities for unified tuning.
Topics & Concepts
Computer scienceWorkflowDeep learningCompilerInferenceLoop (graph theory)GraphOperator (biology)Optimizing compilerTheoretical computer scienceArtificial intelligenceParallel computingProgramming languageMathematicsDatabaseCombinatoricsTranscription factorBiochemistryGeneChemistryRepressorParallel Computing and Optimization TechniquesAdvanced Neural Network ApplicationsFerroelectric and Negative Capacitance Devices