A Code Generator for High-Performance Tensor Contractions on GPUs
- 1 February 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 85-95
Abstract
Tensor contractions are higher dimensional generalizations of matrix-matrix multiplication. They form the compute-intensive core of many applications in computational science and data science. In this paper, we describe a high-performance GPU code generator for arbitrary tensor contractions. It exploits domain-specific properties about data reuse in tensor contractions to devise an effective code generation schema, coupled with an effective model-driven search, to determine parameters for mapping of computation to threads and staging of data through the GPU memory hierarchy. Experimental evaluation using a set of tensor contraction benchmarks demonstrates performance improvement and/or significantly reduced code generation time over other state-of-the-art tensor contraction libraries and code generators.Keywords
This publication has 13 references indexed in Scilit:
- High-Performance Tensor Contraction without TranspositionSIAM Journal on Scientific Computing, 2018
- A high performance data parallel tensor contraction framework: Application to coupled electro-mechanicsComputer Physics Communications, 2017
- HPTT: a high-performance tensor transposition C++ library2017
- Tensor Contractions with Extended BLAS Kernels on CPU and GPU2016
- TTC: a tensor transposition compiler for multiple architectures2016
- An efficient tensor transpose algorithm for multicore CPU, Intel Xeon Phi, and NVidia Tesla GPUComputer Physics Communications, 2015
- Polyhedral parallel code generation for CUDAACM Transactions on Architecture and Code Optimization, 2013
- Optimizing tensor contraction expressions for hybrid CPU-GPU executionCluster Computing, 2011
- Automatic code generation for many-body electronic structure methods: the tensor contraction engine‡‡Molecular Physics, 2006
- An Introduction to Coupled Cluster Theory for Computational Chemists2000