SparseAlgebra

Published configurations

Sparse products and reductions on manufactured finite-element systems.

Measured operation

Isolates the Math operations used inside constrained CG iterations.

Matrices are the actual constrained Poisson, conductivity and scalar reaction--diffusion operators, not synthetic dimension-dependent stencils. Mesh/space construction, original-kernel comparison, matrix assembly, vector allocation and numerical checks precede timing. Products overwrite a preallocated output; reductions return a scalar. These scopes exclude preconditioner setup, solver control and assembly.

Numerical guards

An independent serial traversal accumulates products and Hermitian dot products using long double (whose precision is reported, not assumed). Non-collinear complex vector components exercise conjugation. Manufactured coefficients separately check the assembled equation. Wrong outputs must be rejected. No timing assertion, CTest entry, storage-layout change or relaxed arithmetic is introduced.

Recorded results

Each case retains its original inputs, iteration policy and correctness checks. Raw reports preserve counters, repetitions and the Google Benchmark context. CPU, wall and manually supplied times are labeled separately; unlike operations and configurations are not averaged together.

Timing history

RodinSparseAlgebraBenchmarks · auto · slow · ranks: 1