Package org.apache.sysds.hops.estim
package org.apache.sysds.hops.estim
-
ClassDescriptionBasic average case estimator for matrix sparsity: sp = 1 - Math.pow(1-sp1*sp2, k)Basic average case estimator for matrix sparsity: sp = Math.min(1, sp1 * k) * Math.min(1, sp2 * k).This estimator implements a naive but rather common approach of boolean matrix multiplies which allows to infer the exact non-zero structure and thus is also useful for sparse result preallocation.This class represents a boolean matrix and provides key operations.This estimator implements an approach called density maps, as introduced in David Kernert, Frank Köhler, Wolfgang Lehner: SpMacho - Optimizing Sparse Linear Algebra Expressions with Probabilistic Density Estimation.This estimator implements an approach based on a so-called layered graph, introduced in Edith Cohen.This estimator implements a remarkably simple yet effective approach for incorporating structural properties into sparsity estimation.This estimator implements an approach based on row-wise sparsity estimation, introduced in Lin, Chunxu, Wensheng Luo, Yixiang Fang, Chenhao Ma, Xilin Liu and Yuchi Ma: On Efficient Large Sparse Matrix Chain Multiplication.This estimator implements an approach based on row/column sampling Yongyang Yu, MingJie Tang, Walid G.This estimator implements an approach based on row/column sampling Rasmus Resen Amossen, Andrea Campagna, Rasmus Pagh: Better Size Estimation for Sparse Matrix Products.Helper class to represent matrix multiply operators in a DAG along with references to its abstract data handles.