-
Notifications
You must be signed in to change notification settings - Fork 98
SpMV_Struct_Benchmarks
Luc Berger edited this page Feb 24, 2020
·
15 revisions
This page gathers instructions and references to conduct performance tests of the spmv_struct algorithms in Kokkos-Kernels.
The first table shows the comparison of performance on 2D problems using FD (5pt) and FE (9pt) stencils
Matrix size | FD Struct | FD Unstr | FE Struct | FD Unstr |
---|---|---|---|---|
50 | 0.03615 | 0.02654 | 0.03738 | 0.02720 |
100 | 0.04266 | 0.03411 | 0.04668 | 0.04069 |
150 | 0.05323 | 0.05426 | 0.06753 | 0.07118 |
225 | 0.07749 | 0.09979 | 0.10876 | 0.12682 |
300 | 0.10972 | 0.15491 | 0.16904 | 0.20675 |
400 | 0.16881 | 0.25213 | 0.26955 | 0.33847 |
1,000 | 0.88039 | 1.42716 | 1.55607 | 1.86464 |
2,000 | 3.30934 | 4.35175 | 5.36563 | 5.63246 |
3D problems
Matrix size | FD Struct | FD Unstr | FE Struct | FD Unstr |
---|---|---|---|---|
30 | 0.06985 | 0.08438 | 0.14827 | 0.14980 |
40 | 0.12008 | 0.18496 | 0.31668 | 0.33553 |
50 | 0.19112 | 0.30912 | 0.56940 | 0.60685 |
60 | 0.30857 | 0.50288 | 1.01198 | 1.03442 |
80 | 0.69584 | 1.09019 | 2.31828 | 2.26498 |
100 | 1.29433 | 2.09743 | 4.26691 | 3.95687 |
200 | 8.35539 | 11.51226 | 26.04506 | 29.12328 |
The first table shows the comparison of performance on 2D problems using FD (5pt) and FE (9pt) stencils
Matrix size | FD Struct | FD Unstr | FE Struct | FD Unstr |
---|---|---|---|---|
50 | 0.02639 | 0.02654 | 0.02062 | 0.01521 |
100 | 0.02071 | 0.01825 | 0.02106 | 0.01716 |
150 | 0.02959 | 0.04015 | 0.02340 | 0.02078 |
225 | 0.02780 | 0.02477 | 0.03321 | 0.05163 |
300 | 0.03654 | 0.06123 | 0.04925 | 0.07147 |
400 | 0.04875 | 0.09654 | 0.06846 | 0.12177 |
1,000 | 0.20233 | 0.53389 | 0.32596 | 0.66484 |
2,000 | 0.74472 | 2.10274 | 1.23610 | 2.48697 |
3D problems
Matrix size | FD Struct | FD Unstr | FE Struct | FD Unstr |
---|---|---|---|---|
30 | 0.02234 | 0.02195 | 0.03912 | 0.04365 |
40 | 0.03450 | 0.06202 | 0.06745 | 0.07851 |
50 | 0.05008 | 0.12886 | 0.11510 | 0.13937 |
60 | 0.07094 | 0.19252 | 0.18333 | 0.22314 |
80 | 0.14351 | 0.42709 | 0.41497 | 0.51883 |
100 | 0.26672 | 0.83247 | 0.81861 | 0.98918 |
200 | 1.92387 | 6.64503 | 5.90622 | 7.67507 |
The first table shows the comparison of performance on 2D problems using FD (5pt) and FE (9pt) stencils
Matrix size | FD Struct | FD Unstr | FE Struct | FD Unstr |
---|---|---|---|---|
50 | 0.03056 | 0.02188 | 0.03115 | 0.02220 |
100 | 0.03232 | 0.02172 | 0.03031 | 0.02195 |
150 | 0.03136 | 0.02402 | 0.03019 | 0.02473 |
225 | 0.03112 | 0.02805 | 0.03287 | 0.03042 |
300 | 0.03637 | 0.03732 | 0.04661 | 0.05548 |
400 | 0.04830 | 0.06672 | 0.06471 | 0.07642 |
1,000 | 0.15807 | 0.26555 | 0.26101 | 0.32376 |
2,000 | 0.54528 | 0.97901 | 0.95689 | 1.21262 |
3D problems
Matrix size | FD Struct | FD Unstr | FE Struct | FD Unstr |
---|---|---|---|---|
30 | 0.03067 | 0.02682 | 0.03695 | 0.03710 |
40 | 0.03346 | 0.03476 | 0.05807 | 0.05522 |
50 | 0.04701 | 0.09018 | 0.08597 | 0.08433 |
60 | 0.06112 | 0.14238 | 0.13661 | 0.12506 |
80 | 0.10333 | 0.31182 | 0.28189 | 0.26293 |
100 | 0.17906 | 0.58095 | 0.52572 | 0.49094 |
200 | 1.25908 | 4.44227 | 4.20244 | 3.92674 |