ACM SIGPLAN Notices · 2016 · 11 citations · 23 references
ComputingComputer EngineeringComputer ScienceComputer ArchitectureMachine LearningNatural Language ProcessingData ParallelismDeep LearningDistributed Memory ParallelismHardware AccelerationNeural NetworksSpeech RecognitionAbstractionCommunication RuntimeDistributed MemoryHigh PerformanceHigh-level Synthesis For Machine LearningMachine Code GenerationMachine Code OptimizationTask Parallelism In Distributed Memory Systems
Deep neural networks (DNNs) have undergone a surge in popularity with consistent advances in the state of the art for tasks including image recognition, natural language processing, and speech recognition. The computationally expensive nature of these networks has led to the proliferation of implementations that sacrifice abstraction for high performance. In this paper, we present Latte, a domain-specific language for DNNs that provides a natural abstraction for specifying new layers without sacrificing performance. Users of Latte express DNNs as ensembles of neurons with connections between them. The Latte compiler synthesizes a program based on the user specification, applies a suite of domain-specific and general optimizations, and emits efficient machine code for heterogeneous architectures. Latte also includes a communication runtime for distributed memory data-parallelism. Using networks described using Latte, we demonstrate 3-6x speedup over Caffe (C++/MKL) on the three state-of-the-art ImageNet models executing on an Intel Xeon E5-2699 v3 x86 CPU.
23
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky, Jia Deng, Hao Su et al. · International Journal of Computer Vision · 2015 · 40.2K citations
Multilayer feedforward networks are universal approximators
Kurt Hornik, Maxwell B. Stinchcombe, Halbert White · Neural Networks · 1989 · 21.2K citations