Advection, weak scaling: np8

Filter regionsRegionsall 5Depthall levels

np8.h52026-10-17 12:00 UTCsynthetic CPU8 ranks5 regions0.187039 s profiled

← Advection, weak scaling · ‹ np4

Summary

Wall time187 mssetup to finalize

Ranks8

Regions5

In regions98%of the session

Top hotspotsolve69.7% of the session

Load imbalance+10%solve, slowest on rank 0

solve (in simulation) is the largest hotspot: 976 ms over 80 calls, 69.7% of the session.
The three largest hotspots account for 98% of the session.

Hotspots

The leaves of the call tree with the most time: regions without nested regions, and the own time parents spend outside theirs. Shares are of the session. Click one to find it in the table.

Region statistics

region

% session

total [s]

trend

scope_profiler.session (8x)

100.00%

1.400433

└─ (own)

2.29%

0.032000

Per rank

rank	calls	total [s]	avg [s]	min [s]	max [s]
0	1	0.187039	0.187039	0.187039	0.187039
1	1	0.173247	0.173247	0.173247	0.173247
2	1	0.182664	0.182664	0.182664	0.182664
3	1	0.167301	0.167301	0.167301	0.167301
4	1	0.176259	0.176259	0.176259	0.176259
5	1	0.17824	0.17824	0.17824	0.17824
6	1	0.163835	0.163835	0.163835	0.163835
7	1	0.171847	0.171847	0.171847	0.171847

└─ simulation (8x)

97.71%

1.368433

│ └─ (own)

0.00%

0.000000

Per rank

rank	calls	total [s]	avg [s]	min [s]	max [s]
0	1	0.183039	0.183039	0.183039	0.183039
1	1	0.169247	0.169247	0.169247	0.169247
2	1	0.178664	0.178664	0.178664	0.178664
3	1	0.163301	0.163301	0.163301	0.163301
4	1	0.172259	0.172259	0.172259	0.172259
5	1	0.17424	0.17424	0.17424	0.17424
6	1	0.159835	0.159835	0.159835	0.159835
7	1	0.167847	0.167847	0.167847	0.167847

│ └─ setup (8x)

2.29%

0.032000

Per rank

rank	calls	total [s]	avg [s]	min [s]	max [s]
0	1	0.004	0.004	0.004	0.004
1	1	0.004	0.004	0.004	0.004
2	1	0.004	0.004	0.004	0.004
3	1	0.004	0.004	0.004	0.004
4	1	0.004	0.004	0.004	0.004
5	1	0.004	0.004	0.004	0.004
6	1	0.004	0.004	0.004	0.004
7	1	0.004	0.004	0.004	0.004

│ └─ solve (80x)

69.72%

0.976433

Per rank

rank	calls	total [s]	avg [s]	min [s]	max [s]
0	10	0.134039	0.0134039	0.0134039	0.0134039
1	10	0.120247	0.0120247	0.0120247	0.0120247
2	10	0.129664	0.0129664	0.0129664	0.0129664
3	10	0.114301	0.0114301	0.0114301	0.0114301
4	10	0.123259	0.0123259	0.0123259	0.0123259
5	10	0.12524	0.012524	0.012524	0.012524
6	10	0.110835	0.0110835	0.0110835	0.0110835
7	10	0.118847	0.0118847	0.0118847	0.0118847

│ └─ exchange (80x)

25.71%

0.360000

Per rank

rank	calls	total [s]	avg [s]	min [s]	max [s]
0	10	0.045	0.0045	0.0045	0.0045
1	10	0.045	0.0045	0.0045	0.0045
2	10	0.045	0.0045	0.0045	0.0045
3	10	0.045	0.0045	0.0045	0.0045
4	10	0.045	0.0045	0.0045	0.0045
5	10	0.045	0.0045	0.0045	0.0045
6	10	0.045	0.0045	0.0045	0.0045
7	10	0.045	0.0045	0.0045	0.0045

Durations are in seconds. (own) rows show a region's time excluding its children. % session uses wall-clock coverage; overlapping recursive calls count once. Click a row for its call site and per-rank breakdown.

Load balance

Each region's own time per rank, excluding nested regions, so a parent does not repeat its children's imbalance. Excess is how much longer the slowest rank spends than the average rank: the most balancing that region could save. Regions are ordered by it.

region	mean	min	max	imbalance	excess
solve	122 ms	111 ms	134 ms	+10%	12 ms
setup	4 ms	4 ms	4 ms	+0%	0 s
exchange	45 ms	45 ms	45 ms	+0%	0 s

Rank comparison

Each cell compares one rank's time in a region with the region's mean over the ranks. Rank 0, in red in the header, spends the most time in regions overall. Hover a cell for its time.

faster than the meanslower

region	mean	0	1	2	3	4	5	6	7
solve	122 ms	+9.8%	−1.5%	+6.2%	−6.4%	+1.0%	+2.6%	−9.2%	−2.6%
exchange	45 ms	0%	0%	0%	0%	0%	0%	0%	0%
setup	4 ms	0%	0%	0%	0%	0%	0%	0%	0%
all regions	171 ms	+7.0%	−1.1%	+4.4%	−4.5%	+0.7%	+1.9%	−6.6%	−1.9%

Charts

Region durations

Each bar shows a region's total recorded duration, summed over the selected ranks, longest first.

stack children

Timeline: np8 (rank 0)

Each bar is one recorded region call on rank 0. Its position and width show when the call started and how long it ran; colors identify regions.

Rank imbalance

Each line compares a region's total duration by rank; its dashed line marks the mean across ranks. Points far from the mean identify stragglers.

Rank heatmap

This heatmap uses exclusive timings. Exclusive duration is the time spent in a region itself, excluding time spent in nested child regions; this prevents the enclosing session region from dominating the heatmap.

Metadata

commit	`0000000`
system	`synthetic`
chip_information	`synthetic CPU`
mpi_size	`8`
num_nodes	`2`
omp_num_threads	`1`
platform	`synthetic`
scope_profiler_version	`sample`
timestamp	`2026-10-17T12:00:00Z`
total_cores	`8`