首页> 外国专利> Winograd algorithm on a matrix processing architecture

Winograd algorithm on a matrix processing architecture

机译:基于矩阵处理架构的Winograd算法

摘要

In one embodiment, a matrix operation may be performed, wherein the matrix operation comprises a matrix multiplication operation on a plurality of matrix operands. Matrix data may be received from a multi-dimensional memory, wherein the matrix data is associated with the plurality of matrix operands. The plurality of matrix operands may be extracted from the matrix data, wherein the plurality of matrix operands comprises a first matrix operand and a second matrix operand. A first transform may be performed on the first matrix operand to obtain a transformed matrix operand, wherein performing matrix multiplication using the transformed matrix operand is faster than performing matrix multiplication using the first matrix operand. Matrix multiplication may be performed on the transformed matrix operand to obtain a partial result. A second transform may be performed on the partial result to obtain a result of the matrix multiplication operation.
机译:在一实施例中,可执行矩阵运算,其中矩阵运算包括对多个矩阵操作数的矩阵乘法运算。可以从多维存储器接收矩阵数据,其中,矩阵数据与多个矩阵操作数相关联。可以从矩阵数据中提取多个矩阵操作数,其中,多个矩阵操作数包括第一矩阵操作数和第二矩阵操作数。可以对第一矩阵操作数执行第一变换以获得变换的矩阵操作数,其中使用变换的矩阵操作数执行矩阵乘法比使用第一矩阵操作数执行矩阵乘法更快。可以对变换后的矩阵操作数执行矩阵乘法以获得部分结果。可以对部分结果执行第二变换以获得矩阵乘法运算的结果。

著录项

  • 公开/公告号US10482155B2

    专利类型

  • 公开/公告日2019-11-19

    原文格式PDF

  • 申请/专利权人 INTEL CORPORATION;

    申请/专利号US201615395542

  • 发明设计人 TONY L. WERNER;ARAVIND KALAIAH;

    申请日2016-12-30

  • 分类号G06F17/16;G06F15/80;G06F17/14;G06F17/15;

  • 国家 US

  • 入库时间 2022-08-21 11:28:35

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号