pbdDEMO (version 0.2-0)

LinAlgVerify: At-Scale Verification Routines for Distributed Linear Algebra

Description

At-scale verification routines for distributed linear algebra.

Usage

verify.svd(nrows=1e3, ncols=1e3, mean=0, sd=1, bldim=8, tol=1e-7, 
             ICTXT = .DEMO.CT$ictxt)
  verify.chol(nrows=1e3, mean=0, sd=1, bldim=8, tol=1e-7,
             ICTXT = .DEMO.CT$ictxt)
  verify.inverse(nrows=1e3, mean=0, sd=1, bldim=8, tol=1e-7, 
             ICTXT = .DEMO.CT$ictxt)
  verify.solve(nrows=1e3, mean=0, sd=1, const=1, bldim=8, tol=1e-7, 
             ICTXT = .DEMO.CT$ictxt)

Arguments

nrows, ncols

global dimension.

bldim

blocking dimension.

mean, sd

mean and standard deviation when sampling from a normal distribution.

const

numerical value for generating a constant ddmatrix.

tol

numeric tolerance for testing equality. Differences smaller than tol are considered equal.

ICTXT

BLACS context

Details

Finds the min, mean, and max execution time across all independent processes executing the operation timed.