An input-adaptive and in-place approach to dense tensor-times-matrix multiply
An input-adaptive and in-place approach to dense tensor-times-matrix multiply
复制标题
DOI：
10.1145/2807591.2807671
复制
发表时间：
2015-11
期刊：
影响因子：
--
通讯作者：
Jiajia Li;Casey Battaglino;Ioakeim Perros;Jimeng Sun;R. Vuduc
中科院分区：
文献类型：
--
作者：
Jiajia Li;Casey Battaglino;Ioakeim Perros;Jimeng Sun;R. Vuduc
本文描述了一种新的框架，称为InTensLi（“强烈”），用于产生快速的单节点实现的密集张量倍矩阵乘法（Ttm）的任意维度。而传统的Ttm实现依赖于显式地将输入张量操作数转换为矩阵-为了能够使用任何可用的和快速的通用矩阵-矩阵乘法（Gemm）实现-我们框架的策略是就地执行Ttm，避免这种复制。由于由此产生的实现暴露的调整参数，本文还描述了一个启发式的经验模型，用于选择一个最佳的配置TTM的输入的基础上。与张量工具箱和Cyclops张量框架（Ctf）中广泛使用的单节点Ttm实现相比，In-TensLi的就地和输入自适应Ttm实现了4倍和13倍的加速比，在各种输入上显示出类似Gemm的性能大小。
This paper describes a novel framework, called InTensLi ("intensely"), for producing fast single-node implementations of dense tensor-times-matrix multiply (Ttm) of arbitrary dimension. Whereas conventional implementations of Ttm rely on explicitly converting the input tensor operand into a matrix---in order to be able to use any available and fast general matrix-matrix multiply (Gemm) implementation---our framework's strategy is to carry out the Ttm in-place, avoiding this copy. As the resulting implementations expose tuning parameters, this paper also describes a heuristic empirical model for selecting an optimal configuration based on the Ttm's inputs. When compared to widely used single-node Ttm implementations that are available in the Tensor Toolbox and Cyclops Tensor Framework (Ctf), In-TensLi's in-place and input-adaptive Ttm implementations achieve 4× and 13× speedups, showing Gemm-like performance on a variety of input sizes.