Skip to content

Improve StencilTest input_data allocation and deallocation #968

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
iomaganaris wants to merge 132 commits into
base: main
Choose a base branch
from
Open

Improve StencilTest input_data allocation and deallocation #968

iomaganaris wants to merge 132 commits into from

Conversation

@iomaganaris
Copy link
Collaborator

@iomaganaris iomaganaris commented Dec 4, 2025

This PR fixes two issues of reallocations in the StencilTests.

  1. For every StencilTest variation the input_data get reallocated
  2. The input_data actual arrays get reallocates as GT4Py fields

This PR address those issues by allocating the input_data with class scope, so they are allocated once for each entry in STATIC_PARAMS.
Furthermore, since the data are reallocated as GT4Py fields, the original data can be deallocated.
Some more extra explicit deletion the properly_allocated_input_data are necessary. Also explicit calls to the python garbage collector might help.
Here is the memory usage across time for the following tests in main using memray:

PYTHONMALLOC=malloc python3.11 -m memray run --native -o $(pwd)/main.bin $(which pytest) -svx --benchmark-disable --backend=gtfn_cpu --grid=icon_benchmark_regional model/atmosphere/dycore/tests/dycore/stencil_tests/test_vertically_implicit_dycore_solver_at_*_step.py
image

and those are the corresponding results after the changes of this PR:
image

DropD and others added 30 commits September 4, 2025 14:42
@DropD
add first batch of program tests to continuous benchmarking
a460d50
@DropD @havogt
fix static params for apply_diffusion_to_vn
84abc04 
Co-authored-by: Hannes Vogt <hannes@havogt.de>
@DropD @havogt
improve static params for apply_diffusion_to_w_... test
50e8365 
Co-authored-by: Hannes Vogt <hannes@havogt.de>
@DropD
Merge branch 'main' into expand-continuous-benchmarking
ad8d449
@DropD
add static params and remove indirectly used prog from benchmarking
aacd35b
@DropD
update dockerfile to trigger a rebuild with newer bencher CLI
d042c98
@DropD
add compute_derived_horizontal_winds_... to benchmarking
ba94c10
@DropD
Merge branch 'main' into expand-continuous-benchmarking
4571a34
@DropD
temporarily remove failing parametrization case.
3dcdd34
@DropD
add compute_advection_in_vertical... program
367ba1f
@DropD
add benchmarking for advection_in_horizontal... program
c4b33c3
@DropD
add benchmarking for compute_perturbed... program
bdc3296
@DropD
add benchmarking for 'compute_hydrostatic...' program
5836fbf
@DropD
fix precommit messages
7d041d5
@OngChia @DropD
fix a bug in grid-savepoint reading during driver initialization (#866)
a30e5da 
Fix bug in the input arguments of
`IconSerialDataProvider.from_grid_savepoint` in
`initialization_utils.py` of the driver package after this PR
#829 is merged.
@havogt @DropD
Fix cupy cfl reduction performance by raveling the array (#872)
ca2f4f2 
On the mch-ch1_medium experiment
- this is 4% faster on the full timestep compared to the version without
`ravel`;
- within fluctuations there is no difference between no reduction and
this version.
@philip-paul-mueller @edopao @DropD
Update to GT4Py v1.0.9 (dace fix) (#840)
36f5583 
Co-authored-by: Edoardo Paone <edoardo.paone@cscs.ch>
@halungge @DropD
delete outdated top level README.md from tools (#870)
510dfae 
delete top level README.md from tools
@dependabot @DropD
Bump actions/setup-python from 5 to 6 (#863)
3824293 
Bumps [actions/setup-python](https://github.com/actions/setup-python)
from 5 to 6.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/actions/setup-python/releases">actions/setup-python's
releases</a>.</em></p>
<blockquote>
<h2>v6.0.0</h2>
<h2>What's Changed</h2>
<h3>Breaking Changes</h3>
<ul>
<li>Upgrade to node 24 by <a
href="https://github.com/salmanmkc"><code>@​salmanmkc</code></a> in <a
href="https://redirect.github.com/actions/setup-python/pull/1164">actions/setup-python#1164</a></li>
</ul>
<p>Make sure your runner is on version v2.327.1 or later to ensure
compatibility with this release. <a
href="https://github.com/actions/runner/releases/tag/v2.327.1">See
Release Notes</a></p>
<h3>Enhancements:</h3>
<ul>
<li>Add support for <code>pip-version</code> by <a
href="https://github.com/priyagupta108"><code>@​priyagupta108</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1129">actions/setup-python#1129</a></li>
<li>Enhance reading from .python-version by <a
href="https://github.com/krystof-k"><code>@​krystof-k</code></a> in <a
href="https://redirect.github.com/actions/setup-python/pull/787">actions/setup-python#787</a></li>
<li>Add version parsing from Pipfile by <a
href="https://github.com/aradkdj"><code>@​aradkdj</code></a> in <a
href="https://redirect.github.com/actions/setup-python/pull/1067">actions/setup-python#1067</a></li>
</ul>
<h3>Bug fixes:</h3>
<ul>
<li>Clarify pythonLocation behaviour for PyPy and GraalPy in environment
variables by <a
href="https://github.com/aparnajyothi-y"><code>@​aparnajyothi-y</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1183">actions/setup-python#1183</a></li>
<li>Change missing cache directory error to warning by <a
href="https://github.com/aparnajyothi-y"><code>@​aparnajyothi-y</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1182">actions/setup-python#1182</a></li>
<li>Add Architecture-Specific PATH Management for Python with --user
Flag on Windows by <a
href="https://github.com/aparnajyothi-y"><code>@​aparnajyothi-y</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1122">actions/setup-python#1122</a></li>
<li>Include python version in PyPy python-version output by <a
href="https://github.com/cdce8p"><code>@​cdce8p</code></a> in <a
href="https://redirect.github.com/actions/setup-python/pull/1110">actions/setup-python#1110</a></li>
<li>Update docs: clarification on pip authentication with setup-python
by <a
href="https://github.com/priya-kinthali"><code>@​priya-kinthali</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1156">actions/setup-python#1156</a></li>
</ul>
<h3>Dependency updates:</h3>
<ul>
<li>Upgrade idna from 2.9 to 3.7 in /<strong>tests</strong>/data by <a
href="https://github.com/dependabot"><code>@​dependabot</code></a>[bot]
in <a
href="https://redirect.github.com/actions/setup-python/pull/843">actions/setup-python#843</a></li>
<li>Upgrade form-data to fix critical vulnerabilities <a
href="https://redirect.github.com/actions/setup-python/issues/182">#182</a>
&amp; <a
href="https://redirect.github.com/actions/setup-python/issues/183">#183</a>
by <a
href="https://github.com/aparnajyothi-y"><code>@​aparnajyothi-y</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1163">actions/setup-python#1163</a></li>
<li>Upgrade setuptools to 78.1.1 to fix path traversal vulnerability in
PackageIndex.download by <a
href="https://github.com/aparnajyothi-y"><code>@​aparnajyothi-y</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1165">actions/setup-python#1165</a></li>
<li>Upgrade actions/checkout from 4 to 5 by <a
href="https://github.com/dependabot"><code>@​dependabot</code></a>[bot]
in <a
href="https://redirect.github.com/actions/setup-python/pull/1181">actions/setup-python#1181</a></li>
<li>Upgrade <code>@​actions/tool-cache</code> from 2.0.1 to 2.0.2 by <a
href="https://github.com/dependabot"><code>@​dependabot</code></a>[bot]
in <a
href="https://redirect.github.com/actions/setup-python/pull/1095">actions/setup-python#1095</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a href="https://github.com/krystof-k"><code>@​krystof-k</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/setup-python/pull/787">actions/setup-python#787</a></li>
<li><a href="https://github.com/cdce8p"><code>@​cdce8p</code></a> made
their first contribution in <a
href="https://redirect.github.com/actions/setup-python/pull/1110">actions/setup-python#1110</a></li>
<li><a href="https://github.com/aradkdj"><code>@​aradkdj</code></a> made
their first contribution in <a
href="https://redirect.github.com/actions/setup-python/pull/1067">actions/setup-python#1067</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/actions/setup-python/compare/v5...v6.0.0">https://github.com/actions/setup-python/compare/v5...v6.0.0</a></p>
<h2>v5.6.0</h2>
<h2>What's Changed</h2>
<ul>
<li>Workflow updates related to Ubuntu 20.04 by <a
href="https://github.com/aparnajyothi-y"><code>@​aparnajyothi-y</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1065">actions/setup-python#1065</a></li>
<li>Fix for Candidate Not Iterable Error by <a
href="https://github.com/aparnajyothi-y"><code>@​aparnajyothi-y</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1082">actions/setup-python#1082</a></li>
<li>Upgrade semver and <code>@​types/semver</code> by <a
href="https://github.com/dependabot"><code>@​dependabot</code></a> in <a
href="https://redirect.github.com/actions/setup-python/pull/1091">actions/setup-python#1091</a></li>
<li>Upgrade prettier from 2.8.8 to 3.5.3 by <a
href="https://github.com/dependabot"><code>@​dependabot</code></a> in <a
href="https://redirect.github.com/actions/setup-python/pull/1046">actions/setup-python#1046</a></li>
<li>Upgrade ts-jest from 29.1.2 to 29.3.2 by <a
href="https://github.com/dependabot"><code>@​dependabot</code></a> in <a
href="https://redirect.github.com/actions/setup-python/pull/1081">actions/setup-python#1081</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/actions/setup-python/compare/v5...v5.6.0">https://github.com/actions/setup-python/compare/v5...v5.6.0</a></p>
<h2>v5.5.0</h2>
<h2>What's Changed</h2>
<h3>Enhancements:</h3>
<ul>
<li>Support free threaded Python versions like '3.13t' by <a
href="https://github.com/colesbury"><code>@​colesbury</code></a> in <a
href="https://redirect.github.com/actions/setup-python/pull/973">actions/setup-python#973</a></li>
<li>Enhance Workflows: Include ubuntu-arm runners, Add e2e Testing for
free threaded and Upgrade <code>@​action/cache</code> from 4.0.0 to
4.0.3 by <a
href="https://github.com/priya-kinthali"><code>@​priya-kinthali</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1056">actions/setup-python#1056</a></li>
<li>Add support for .tool-versions file in setup-python by <a
href="https://github.com/mahabaleshwars"><code>@​mahabaleshwars</code></a>
in <a
href="https://redirect.github.com/actions/setup-python/pull/1043">actions/setup-python#1043</a></li>
</ul>
<h3>Bug fixes:</h3>
<ul>
<li>Fix architecture for pypy on Linux ARM64 by <a
href="https://github.com/mayeut"><code>@​mayeut</code></a> in <a
href="https://redirect.github.com/actions/setup-python/pull/1011">actions/setup-python#1011</a>
This update maps arm64 to aarch64 for Linux ARM64 PyPy
installations.</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/actions/setup-python/commit/e797f83bcb11b83ae66e0230d6156d7c80228e7c"><code>e797f83</code></a>
Upgrade to node 24 (<a
href="https://redirect.github.com/actions/setup-python/issues/1164">#1164</a>)</li>
<li><a
href="https://github.com/actions/setup-python/commit/3d1e2d2ca0a067f27da6fec484fce7f5256def85"><code>3d1e2d2</code></a>
Revert &quot;Enhance cache-dependency-path handling to support files
outside the w...</li>
<li><a
href="https://github.com/actions/setup-python/commit/65b071217a8539818fdb8b54561bcbae40380a54"><code>65b0712</code></a>
Clarify pythonLocation behavior for PyPy and GraalPy in environment
variables...</li>
<li><a
href="https://github.com/actions/setup-python/commit/5b668cf7652160527499ee14ceaff4be9306cb88"><code>5b668cf</code></a>
Bump actions/checkout from 4 to 5 (<a
href="https://redirect.github.com/actions/setup-python/issues/1181">#1181</a>)</li>
<li><a
href="https://github.com/actions/setup-python/commit/f62a0e252fe7114e86949abfa6e1e89f85bb38c2"><code>f62a0e2</code></a>
Change missing cache directory error to warning (<a
href="https://redirect.github.com/actions/setup-python/issues/1182">#1182</a>)</li>
<li><a
href="https://github.com/actions/setup-python/commit/9322b3ca74000aeb2c01eb777b646334015ddd72"><code>9322b3c</code></a>
Upgrade setuptools to 78.1.1 to fix path traversal vulnerability in
PackageIn...</li>
<li><a
href="https://github.com/actions/setup-python/commit/fbeb884f69f0ac1c0257302f62aa524c2824b649"><code>fbeb884</code></a>
Bump form-data to fix critical vulnerabilities <a
href="https://redirect.github.com/actions/setup-python/issues/182">#182</a>
&amp; <a
href="https://redirect.github.com/actions/setup-python/issues/183">#183</a>
(<a
href="https://redirect.github.com/actions/setup-python/issues/1163">#1163</a>)</li>
<li><a
href="https://github.com/actions/setup-python/commit/03bb6152f4f691b9d64579a1bd791904a083c452"><code>03bb615</code></a>
Bump idna from 2.9 to 3.7 in /<strong>tests</strong>/data (<a
href="https://redirect.github.com/actions/setup-python/issues/843">#843</a>)</li>
<li><a
href="https://github.com/actions/setup-python/commit/36da51d563b70a972897150555bb025096d65565"><code>36da51d</code></a>
Add version parsing from Pipfile (<a
href="https://redirect.github.com/actions/setup-python/issues/1067">#1067</a>)</li>
<li><a
href="https://github.com/actions/setup-python/commit/3c6f142cc0036d53007e92fa1e327564a4cfb7aa"><code>3c6f142</code></a>
update documentation (<a
href="https://redirect.github.com/actions/setup-python/issues/1156">#1156</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/actions/setup-python/compare/v5...v6">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=actions/setup-python&package-manager=github_actions&previous-version=5&new-version=6)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
@iomaganaris @OngChia @DropD
Clean up 41_to_60 for better performance (#784)
1c899eb 
- Removed `vertical_mass_flux_at_cells_on_half_levels`,
`tridiagonal_alpha_coeff_at_cells_on_half_levels`,
`tridiagonal_beta_coeff_at_cells_on_model_levels`, `exner_explicit_term`
and `rho_explicit_term` from intermediate fields passed around
- Combined
`_vertically_implicit_solver_at_corrector/predictor_step_before/after_solving_w`
- Improved initialization of scans (level 0 and 80) (together with
@philip-paul-mueller )
- Removed any unnecessary initializations related to them (i.e.
`next_w`)
  - Handle related unit tests
- Make sure that the values for the `n_lev` vertical level are passed
from `_set_surface_boundary_condtion_for_computation_of_w` to
`_vertically_implicit_solver_at_corrector/predictor_step_before_solving_w`
properly
  - Improves DaCe handling of temporaries

---------

Co-authored-by: "Ong Chia Rui" <chiarui.ong@c2sm.ethz.ch>
@edopao @DropD
Fix memory allocator for zero fields in velocity advection tests (#874)
937128b 
Fix an issue in velocity advection tests, that caused the dace programs
to fail: a cupy array was expected as argument, a numpy array was
passed.
@edopao @DropD
Add dace backend to default CI pipeline (#822)
c1bfd1c 
This PR enables CI tests on the dace backend.
- In the Github Actions, we run the stencil tests on the CPU backend.
- In the CSCS CI, we run the tests with serialized data on the GPU
backend, only for diffusion and dycore in order to save compute
resources.
@DropD
Merge branch 'main' into expand-continuous-benchmarking
02d031f
@DropD
add benchmarking for 'vertically_implicit_solver...' program
bddb09d
@DropD
avoid dace backend corner cases in stencil tests
48c9b08
@DropD
Merge branch 'main' into expand-continuous-benchmarking
4ea9499
@DropD
add benchmarking for 'interpolate_rho_theta...' program
70e1720
@DropD
fix typing for static variants in stencil tests
1479e80
@DropD
add benchmarking for 'apply_divergence_damping...' program
cf730e8
@DropD
add benchmarking for 'vertically_implicit...corrector...' program
47d647a
@github-actions
Copy link

github-actions bot commented Dec 4, 2025

Mandatory Tests

Please make sure you run these tests via comment before you merge!

  • cscs-ci run default

Optional Tests

To run benchmarks you can use:

  • cscs-ci run benchmark-bencher

To run tests and benchmarks with the DaCe backend you can use:

  • cscs-ci run dace

To run test levels ignored by the default test suite (mostly simple datatest for static fields computations) you can use:

  • cscs-ci run extra

For more detailed information please look at CI in the EXCLAIM universe.

@iomaganaris
Copy link
Collaborator Author

iomaganaris commented Dec 4, 2025

cscs-ci run default

@iomaganaris
Copy link
Collaborator Author

iomaganaris commented Dec 4, 2025

cscs-ci run benchmark-bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:dace_cpu:icon_benchmark_regional

🚨 3 Alerts

BenchmarkMeasure
Units		ViewBenchmark Result
(Result Δ%)		Upper Boundary
(Limit %)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[False]-compile_time_domain]Latency
milliseconds (ms)		📈 plot
🚷 threshold
🚨 alert (🔔)		563.21 ms
(+163.40%)Baseline: 213.82 ms
235.21 ms
(239.45%)

TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[True]-compile_time_domain]Latency
milliseconds (ms)		📈 plot
🚷 threshold
🚨 alert (🔔)		578.94 ms
(+164.35%)Baseline: 219.01 ms
240.91 ms
(240.31%)

TestFusedVelocityAdvectionStencilVMomentum[compile_time_domain]Latency
milliseconds (ms)		📈 plot
🚷 threshold
🚨 alert (🔔)		230.05 ms
(+142.05%)Baseline: 95.04 ms
104.55 ms
(220.04%)

Click to view all benchmark results
BenchmarkLatencyBenchmark Result
microseconds (µs)
(Result Δ%)		Upper Boundary
microseconds (µs)
(Limit %)
TestApplyDiffusionToVn[compile_time_domain]📈 view plot
🚷 view threshold		2,380.26 µs
(-0.90%)Baseline: 2,401.85 µs
2,642.03 µs
(90.09%)
TestApplyDiffusionToWAndComputeHorizontalGradientsForTurbulence[compile_time_domain]📈 view plot
🚷 view threshold		20,481.41 µs
(+1.30%)Baseline: 20,217.77 µs
22,239.54 µs
(92.09%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[False]__second_order_divdamp_factor[0.032]-compile_time_domain]📈 view plot
🚷 view threshold		573,359.98 µs
(0.00%)Baseline: 573,359.98 µs
630,695.98 µs
(90.91%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[True]__second_order_divdamp_factor[0.012]-compile_time_domain]📈 view plot
🚷 view threshold		769,115.22 µs
(0.00%)Baseline: 769,115.22 µs
846,026.74 µs
(90.91%)
TestCalculateNabla2AndSmagCoefficientsForVn[compile_time_domain]📈 view plot
🚷 view threshold		2,533.14 µs
(+0.50%)Baseline: 2,520.48 µs
2,772.53 µs
(91.37%)
TestCalculateNabla4[compile_time_domain]📈 view plot
🚷 view threshold		1,236.42 µs
(-0.52%)Baseline: 1,242.83 µs
1,367.11 µs
(90.44%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[False]-compile_time_domain]📈 view plot
🚷 view threshold		2,905.35 µs
(0.00%)Baseline: 2,905.35 µs
3,195.89 µs
(90.91%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[True]-compile_time_domain]📈 view plot
🚷 view threshold		2,842.23 µs
(0.00%)Baseline: 2,842.23 µs
3,126.45 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[False]-compile_time_domain]📈 view plot
🚷 view threshold		39,950.15 µs
(0.00%)Baseline: 39,950.15 µs
43,945.16 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[True]-compile_time_domain]📈 view plot
🚷 view threshold		37,247.61 µs
(0.00%)Baseline: 37,247.61 µs
40,972.37 µs
(90.91%)
TestComputeHorizontalVelocityQuantitiesAndFluxes[compile_time_domain]📈 view plot
🚷 view threshold		8,019.54 µs
(+0.68%)Baseline: 7,965.59 µs
8,762.15 µs
(91.52%)
TestComputeHydrostaticCorrectionTerm[compile_time_domain]📈 view plot
🚷 view threshold		2,455.16 µs
(-17.48%)Baseline: 2,975.19 µs
3,272.71 µs
(75.02%)
TestComputePerturbedQuantitiesAndInterpolation[compile_time_domain]📈 view plot
🚷 view threshold		13,507.94 µs
(-2.89%)Baseline: 13,909.35 µs
15,300.28 µs
(88.29%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold
🚨 view alert (🔔)		563,209.29 µs
(+163.40%)Baseline: 213,822.83 µs
235,205.11 µs
(239.45%)

TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold
🚨 view alert (🔔)		578,944.03 µs
(+164.35%)Baseline: 219,010.77 µs
240,911.85 µs
(240.31%)

TestFusedVelocityAdvectionStencilVMomentum[compile_time_domain]📈 view plot
🚷 view threshold
🚨 view alert (🔔)		230,049.55 µs
(+142.05%)Baseline: 95,042.69 µs
104,546.96 µs
(220.04%)

TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[False]-compile_time_domain]📈 view plot
🚷 view threshold		9,579.19 µs
(0.00%)Baseline: 9,579.19 µs
10,537.11 µs
(90.91%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[True]-compile_time_domain]📈 view plot
🚷 view threshold		15,164.77 µs
(0.00%)Baseline: 15,164.77 µs
16,681.24 µs
(90.91%)
TestInitCellKdimFieldWithZeroWp[compile_time_domain]📈 view plot
🚷 view threshold		806.27 µs
(-0.73%)Baseline: 812.19 µs
893.41 µs
(90.25%)
TestInterpolateRhoThetaVToHalfLevelsAndComputePressureBuoyancyAcceleration[compile_time_domain]📈 view plot
🚷 view threshold		2,815.66 µs
(-11.55%)Baseline: 3,183.19 µs
3,501.50 µs
(80.41%)
TestMoIntpRbfRbfVecInterpolVertex[compile_time_domain]📈 view plot
🚷 view threshold		1,172.23 µs
(-8.23%)Baseline: 1,277.43 µs
1,405.17 µs
(83.42%)
TestUpdateMassFluxWeighted[compile_time_domain]📈 view plot
🚷 view threshold		852.01 µs
(-12.03%)Baseline: 968.51 µs
1,065.36 µs
(79.97%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		573,764.62 µs
(0.00%)Baseline: 573,764.62 µs
631,141.08 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[True]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		596,470.05 µs
(0.00%)Baseline: 596,470.05 µs
656,117.05 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		856,382.87 µs
(0.00%)Baseline: 856,382.87 µs
942,021.16 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[True]__lprep_adv[True]__is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		810,121.84 µs
(0.00%)Baseline: 810,121.84 µs
891,134.03 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[False]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		286,829.50 µs
(0.00%)Baseline: 286,829.50 µs
315,512.45 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		535,521.72 µs
(0.00%)Baseline: 535,521.72 µs
589,073.89 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[True]__divdamp_type[3]-compile_time_domain]📈 view plot
🚷 view threshold		439,998.81 µs
(0.00%)Baseline: 439,998.81 µs
483,998.69 µs
(90.91%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:gtfn_gpu:icon_benchmark_regional
Click to view all benchmark results
BenchmarkLatencyBenchmark Result
microseconds (µs)
(Result Δ%)		Upper Boundary
microseconds (µs)
(Limit %)
TestApplyDiffusionToVn[compile_time_domain]📈 view plot
🚷 view threshold		103.17 µs
(+0.31%)Baseline: 102.84 µs
113.13 µs
(91.19%)
TestApplyDiffusionToWAndComputeHorizontalGradientsForTurbulence[compile_time_domain]📈 view plot
🚷 view threshold		98.36 µs
(+0.63%)Baseline: 97.75 µs
107.52 µs
(91.48%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[False]__second_order_divdamp_factor[0.032]-compile_time_domain]📈 view plot
🚷 view threshold		191.94 µs
(0.00%)Baseline: 191.94 µs
211.13 µs
(90.91%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[True]__second_order_divdamp_factor[0.012]-compile_time_domain]📈 view plot
🚷 view threshold		180.53 µs
(0.00%)Baseline: 180.53 µs
198.59 µs
(90.91%)
TestCalculateNabla2AndSmagCoefficientsForVn[compile_time_domain]📈 view plot
🚷 view threshold		223.14 µs
(-0.18%)Baseline: 223.54 µs
245.89 µs
(90.75%)
TestCalculateNabla4[compile_time_domain]📈 view plot
🚷 view threshold		85.87 µs
(-25.54%)Baseline: 115.32 µs
126.86 µs
(67.69%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[False]-compile_time_domain]📈 view plot
🚷 view threshold		182.78 µs
(0.00%)Baseline: 182.78 µs
201.06 µs
(90.91%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[True]-compile_time_domain]📈 view plot
🚷 view threshold		153.04 µs
(0.00%)Baseline: 153.04 µs
168.35 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[False]-compile_time_domain]📈 view plot
🚷 view threshold		517.35 µs
(0.00%)Baseline: 517.35 µs
569.08 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[True]-compile_time_domain]📈 view plot
🚷 view threshold		475.25 µs
(0.00%)Baseline: 475.25 µs
522.77 µs
(90.91%)
TestComputeHorizontalVelocityQuantitiesAndFluxes[compile_time_domain]📈 view plot
🚷 view threshold		336.49 µs
(+1.31%)Baseline: 332.13 µs
365.34 µs
(92.10%)
TestComputeHydrostaticCorrectionTerm[compile_time_domain]📈 view plot
🚷 view threshold		19.96 µs
(+1.46%)Baseline: 19.67 µs
21.64 µs
(92.24%)
TestComputePerturbedQuantitiesAndInterpolation[compile_time_domain]📈 view plot
🚷 view threshold		319.60 µs
(+1.31%)Baseline: 315.48 µs
347.03 µs
(92.10%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		1,010.56 µs
(+0.76%)Baseline: 1,002.90 µs
1,103.19 µs
(91.60%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		1,019.89 µs
(+0.22%)Baseline: 1,017.64 µs
1,119.40 µs
(91.11%)
TestFusedVelocityAdvectionStencilVMomentum[compile_time_domain]📈 view plot
🚷 view threshold		358.44 µs
(-0.27%)Baseline: 359.40 µs
395.34 µs
(90.67%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[False]-compile_time_domain]📈 view plot
🚷 view threshold		167.73 µs
(0.00%)Baseline: 167.73 µs
184.50 µs
(90.91%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[True]-compile_time_domain]📈 view plot
🚷 view threshold		240.19 µs
(0.00%)Baseline: 240.19 µs
264.21 µs
(90.91%)
TestInitCellKdimFieldWithZeroWp[compile_time_domain]📈 view plot
🚷 view threshold		19.37 µs
(-0.78%)Baseline: 19.52 µs
21.47 µs
(90.20%)
TestInterpolateRhoThetaVToHalfLevelsAndComputePressureBuoyancyAcceleration[compile_time_domain]📈 view plot
🚷 view threshold		135.89 µs
(-0.39%)Baseline: 136.43 µs
150.07 µs
(90.55%)
TestMoIntpRbfRbfVecInterpolVertex[compile_time_domain]📈 view plot
🚷 view threshold		46.31 µs
(-0.83%)Baseline: 46.70 µs
51.37 µs
(90.15%)
TestUpdateMassFluxWeighted[compile_time_domain]📈 view plot
🚷 view threshold		57.80 µs
(+0.29%)Baseline: 57.63 µs
63.39 µs
(91.17%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		593.09 µs
(0.00%)Baseline: 593.09 µs
652.40 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[True]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		596.00 µs
(0.00%)Baseline: 596.00 µs
655.60 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		583.73 µs
(0.00%)Baseline: 583.73 µs
642.10 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[True]__lprep_adv[True]__is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		599.33 µs
(0.00%)Baseline: 599.33 µs
659.27 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[False]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		611.32 µs
(0.00%)Baseline: 611.32 µs
672.45 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		586.90 µs
(0.00%)Baseline: 586.90 µs
645.59 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[True]__divdamp_type[3]-compile_time_domain]📈 view plot
🚷 view threshold		602.13 µs
(0.00%)Baseline: 602.13 µs
662.34 µs
(90.91%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:gtfn_gpu:icon_benchmark_regional
Click to view all benchmark results
BenchmarkLatencyBenchmark Result
microseconds (µs)
(Result Δ%)		Upper Boundary
microseconds (µs)
(Limit %)
model/atmosphere/diffusion/tests/diffusion/integration_tests/test_benchmark_diffusion.py::test_diffusion_benchmark📈 view plot
🚷 view threshold		700.12 µs
(-0.82%)Baseline: 705.91 µs
776.50 µs
(90.16%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-False]📈 view plot
🚷 view threshold		3,110.62 µs
(-1.99%)Baseline: 3,173.82 µs
3,491.21 µs
(89.10%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-True]📈 view plot
🚷 view threshold		3,099.38 µs
(-2.16%)Baseline: 3,167.70 µs
3,484.47 µs
(88.95%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[True-False]📈 view plot
🚷 view threshold		3,565.31 µs
(-2.62%)Baseline: 3,661.20 µs
4,027.32 µs
(88.53%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:gtfn_cpu:icon_benchmark_regional

🚨 1 Alert

BenchmarkMeasure
Units		ViewBenchmark Result
(Result Δ%)		Upper Boundary
(Limit %)
TestFusedVelocityAdvectionStencilVMomentum[compile_time_domain]Latency
milliseconds (ms)		📈 plot
🚷 threshold
🚨 alert (🔔)		24.67 ms
(+15.02%)Baseline: 21.45 ms
23.60 ms
(104.56%)

Click to view all benchmark results
BenchmarkLatencyBenchmark Result
microseconds (µs)
(Result Δ%)		Upper Boundary
microseconds (µs)
(Limit %)
TestApplyDiffusionToVn[compile_time_domain]📈 view plot
🚷 view threshold		1,286.31 µs
(+2.30%)Baseline: 1,257.39 µs
1,383.13 µs
(93.00%)
TestApplyDiffusionToWAndComputeHorizontalGradientsForTurbulence[compile_time_domain]📈 view plot
🚷 view threshold		6,142.29 µs
(-0.28%)Baseline: 6,159.46 µs
6,775.40 µs
(90.66%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[False]__second_order_divdamp_factor[0.032]-compile_time_domain]📈 view plot
🚷 view threshold		17,011.86 µs
(0.00%)Baseline: 17,011.86 µs
18,713.04 µs
(90.91%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[True]__second_order_divdamp_factor[0.012]-compile_time_domain]📈 view plot
🚷 view threshold		8,970.25 µs
(0.00%)Baseline: 8,970.25 µs
9,867.27 µs
(90.91%)
TestCalculateNabla2AndSmagCoefficientsForVn[compile_time_domain]📈 view plot
🚷 view threshold		1,286.67 µs
(-11.13%)Baseline: 1,447.81 µs
1,592.59 µs
(80.79%)
TestCalculateNabla4[compile_time_domain]📈 view plot
🚷 view threshold		832.52 µs
(-9.42%)Baseline: 919.11 µs
1,011.02 µs
(82.34%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[False]-compile_time_domain]📈 view plot
🚷 view threshold		3,099.09 µs
(0.00%)Baseline: 3,099.09 µs
3,409.00 µs
(90.91%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[True]-compile_time_domain]📈 view plot
🚷 view threshold		2,824.38 µs
(0.00%)Baseline: 2,824.38 µs
3,106.82 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[False]-compile_time_domain]📈 view plot
🚷 view threshold		43,208.54 µs
(0.00%)Baseline: 43,208.54 µs
47,529.39 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[True]-compile_time_domain]📈 view plot
🚷 view threshold		42,945.85 µs
(0.00%)Baseline: 42,945.85 µs
47,240.43 µs
(90.91%)
TestComputeHorizontalVelocityQuantitiesAndFluxes[compile_time_domain]📈 view plot
🚷 view threshold		12,076.09 µs
(-6.49%)Baseline: 12,914.05 µs
14,205.45 µs
(85.01%)
TestComputeHydrostaticCorrectionTerm[compile_time_domain]📈 view plot
🚷 view threshold		823.24 µs
(+6.77%)Baseline: 771.07 µs
848.17 µs
(97.06%)
TestComputePerturbedQuantitiesAndInterpolation[compile_time_domain]📈 view plot
🚷 view threshold		14,028.19 µs
(+1.64%)Baseline: 13,802.17 µs
15,182.38 µs
(92.40%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		35,527.45 µs
(-10.59%)Baseline: 39,733.57 µs
43,706.92 µs
(81.29%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		37,381.79 µs
(-17.41%)Baseline: 45,263.83 µs
49,790.21 µs
(75.08%)
TestFusedVelocityAdvectionStencilVMomentum[compile_time_domain]📈 view plot
🚷 view threshold
🚨 view alert (🔔)		24,672.79 µs
(+15.02%)Baseline: 21,451.76 µs
23,596.93 µs
(104.56%)

TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[False]-compile_time_domain]📈 view plot
🚷 view threshold		8,511.22 µs
(0.00%)Baseline: 8,511.22 µs
9,362.34 µs
(90.91%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[True]-compile_time_domain]📈 view plot
🚷 view threshold		9,551.49 µs
(0.00%)Baseline: 9,551.49 µs
10,506.64 µs
(90.91%)
TestInitCellKdimFieldWithZeroWp[compile_time_domain]📈 view plot
🚷 view threshold		781.93 µs
(+1.22%)Baseline: 772.48 µs
849.73 µs
(92.02%)
TestInterpolateRhoThetaVToHalfLevelsAndComputePressureBuoyancyAcceleration[compile_time_domain]📈 view plot
🚷 view threshold		2,760.96 µs
(-2.29%)Baseline: 2,825.59 µs
3,108.15 µs
(88.83%)
TestMoIntpRbfRbfVecInterpolVertex[compile_time_domain]📈 view plot
🚷 view threshold		791.55 µs
(-4.46%)Baseline: 828.55 µs
911.40 µs
(86.85%)
TestUpdateMassFluxWeighted[compile_time_domain]📈 view plot
🚷 view threshold		780.30 µs
(+0.36%)Baseline: 777.51 µs
855.26 µs
(91.23%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		35,615.91 µs
(0.00%)Baseline: 35,615.91 µs
39,177.50 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[True]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		40,719.19 µs
(0.00%)Baseline: 40,719.19 µs
44,791.11 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		37,613.10 µs
(0.00%)Baseline: 37,613.10 µs
41,374.41 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[True]__lprep_adv[True]__is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		41,993.95 µs
(0.00%)Baseline: 41,993.95 µs
46,193.34 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[False]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		39,664.55 µs
(0.00%)Baseline: 39,664.55 µs
43,631.01 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		29,254.89 µs
(0.00%)Baseline: 29,254.89 µs
32,180.37 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[True]__divdamp_type[3]-compile_time_domain]📈 view plot
🚷 view threshold		34,180.41 µs
(0.00%)Baseline: 34,180.41 µs
37,598.45 µs
(90.91%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:gtfn_cpu:icon_benchmark_global
Click to view all benchmark results
BenchmarkLatencyBenchmark Result
milliseconds (ms)
(Result Δ%)		Upper Boundary
milliseconds (ms)
(Limit %)
model/atmosphere/diffusion/tests/diffusion/integration_tests/test_benchmark_diffusion.py::test_diffusion_benchmark📈 view plot
🚷 view threshold		167.98 ms
(+2.26%)Baseline: 164.26 ms
180.68 ms
(92.97%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-False]📈 view plot
🚷 view threshold		915.92 ms
(-2.25%)Baseline: 937.00 ms
1,030.70 ms
(88.86%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-True]📈 view plot
🚷 view threshold		850.27 ms
(-8.62%)Baseline: 930.52 ms
1,023.57 ms
(83.07%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[True-False]📈 view plot
🚷 view threshold		1,022.62 ms
(-7.36%)Baseline: 1,103.84 ms
1,214.22 ms
(84.22%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:gtfn_cpu:icon_benchmark_regional
Click to view all benchmark results
BenchmarkLatencyBenchmark Result
milliseconds (ms)
(Result Δ%)		Upper Boundary
milliseconds (ms)
(Limit %)
model/atmosphere/diffusion/tests/diffusion/integration_tests/test_benchmark_diffusion.py::test_diffusion_benchmark📈 view plot
🚷 view threshold		24.46 ms
(-10.69%)Baseline: 27.39 ms
30.12 ms
(81.19%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-False]📈 view plot
🚷 view threshold		189.10 ms
(+8.05%)Baseline: 175.00 ms
192.50 ms
(98.23%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-True]📈 view plot
🚷 view threshold		149.62 ms
(-12.51%)Baseline: 171.02 ms
188.12 ms
(79.54%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[True-False]📈 view plot
🚷 view threshold		235.06 ms
(+6.26%)Baseline: 221.20 ms
243.32 ms
(96.60%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:dace_cpu:icon_benchmark_global

🚨 1 Alert

BenchmarkMeasure
Units		ViewBenchmark Result
(Result Δ%)		Upper Boundary
(Limit %)
TestApplyDiffusionToWAndComputeHorizontalGradientsForTurbulence[compile_time_domain]Latency
milliseconds (ms)		📈 plot
🚷 threshold
🚨 alert (🔔)		407.27 ms
(+21.67%)Baseline: 334.72 ms
368.20 ms
(110.61%)

Click to view all benchmark results
BenchmarkLatencyBenchmark Result
microseconds (µs)
(Result Δ%)		Upper Boundary
microseconds (µs)
(Limit %)
TestApplyDiffusionToVn[compile_time_domain]📈 view plot
🚷 view threshold		6,629.78 µs
(-10.43%)Baseline: 7,401.69 µs
8,141.86 µs
(81.43%)
TestApplyDiffusionToWAndComputeHorizontalGradientsForTurbulence[compile_time_domain]📈 view plot
🚷 view threshold
🚨 view alert (🔔)		407,265.13 µs
(+21.67%)Baseline: 334,723.96 µs
368,196.36 µs
(110.61%)

TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[False]__second_order_divdamp_factor[0.032]-compile_time_domain]📈 view plot
🚷 view threshold		2,636,617.16 µs
(0.00%)Baseline: 2,636,617.16 µs
2,900,278.88 µs
(90.91%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[True]__second_order_divdamp_factor[0.012]-compile_time_domain]📈 view plot
🚷 view threshold		3,893,352.84 µs
(0.00%)Baseline: 3,893,352.84 µs
4,282,688.13 µs
(90.91%)
TestCalculateNabla2AndSmagCoefficientsForVn[compile_time_domain]📈 view plot
🚷 view threshold		16,515.14 µs
(+7.55%)Baseline: 15,356.25 µs
16,891.87 µs
(97.77%)
TestCalculateNabla4[compile_time_domain]📈 view plot
🚷 view threshold		5,534.61 µs
(-20.37%)Baseline: 6,950.78 µs
7,645.85 µs
(72.39%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[False]-compile_time_domain]📈 view plot
🚷 view threshold		18,041.16 µs
(0.00%)Baseline: 18,041.16 µs
19,845.27 µs
(90.91%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[True]-compile_time_domain]📈 view plot
🚷 view threshold		17,783.41 µs
(0.00%)Baseline: 17,783.41 µs
19,561.75 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[False]-compile_time_domain]📈 view plot
🚷 view threshold		811,162.95 µs
(0.00%)Baseline: 811,162.95 µs
892,279.25 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[True]-compile_time_domain]📈 view plot
🚷 view threshold		681,424.19 µs
(0.00%)Baseline: 681,424.19 µs
749,566.61 µs
(90.91%)
TestComputeHorizontalVelocityQuantitiesAndFluxes[compile_time_domain]📈 view plot
🚷 view threshold		39,115.87 µs
(-4.46%)Baseline: 40,940.77 µs
45,034.84 µs
(86.86%)
TestComputeHydrostaticCorrectionTerm[compile_time_domain]📈 view plot
🚷 view threshold		23,437.71 µs
(-16.35%)Baseline: 28,018.26 µs
30,820.08 µs
(76.05%)
TestComputePerturbedQuantitiesAndInterpolation[compile_time_domain]📈 view plot
🚷 view threshold		54,022.07 µs
(-6.76%)Baseline: 57,940.17 µs
63,734.19 µs
(84.76%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		1,887,461.55 µs
(-8.73%)Baseline: 2,067,981.34 µs
2,274,779.48 µs
(82.97%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		1,974,845.92 µs
(-8.48%)Baseline: 2,157,939.17 µs
2,373,733.09 µs
(83.20%)
TestFusedVelocityAdvectionStencilVMomentum[compile_time_domain]📈 view plot
🚷 view threshold		2,076,340.67 µs
(-0.25%)Baseline: 2,081,500.37 µs
2,289,650.41 µs
(90.68%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[False]-compile_time_domain]📈 view plot
🚷 view threshold		1,522,013.29 µs
(0.00%)Baseline: 1,522,013.29 µs
1,674,214.62 µs
(90.91%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[True]-compile_time_domain]📈 view plot
🚷 view threshold		1,555,672.03 µs
(0.00%)Baseline: 1,555,672.03 µs
1,711,239.23 µs
(90.91%)
TestInitCellKdimFieldWithZeroWp[compile_time_domain]📈 view plot
🚷 view threshold		992.75 µs
(-2.08%)Baseline: 1,013.85 µs
1,115.23 µs
(89.02%)
TestInterpolateRhoThetaVToHalfLevelsAndComputePressureBuoyancyAcceleration[compile_time_domain]📈 view plot
🚷 view threshold		20,138.11 µs
(-2.55%)Baseline: 20,664.38 µs
22,730.81 µs
(88.59%)
TestMoIntpRbfRbfVecInterpolVertex[compile_time_domain]📈 view plot
🚷 view threshold		5,721.14 µs
(-0.08%)Baseline: 5,725.51 µs
6,298.06 µs
(90.84%)
TestUpdateMassFluxWeighted[compile_time_domain]📈 view plot
🚷 view threshold		5,765.66 µs
(+1.65%)Baseline: 5,672.17 µs
6,239.39 µs
(92.41%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		2,448,180.27 µs
(0.00%)Baseline: 2,448,180.27 µs
2,692,998.30 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[True]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		2,959,194.49 µs
(0.00%)Baseline: 2,959,194.49 µs
3,255,113.94 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		3,420,953.29 µs
(0.00%)Baseline: 3,420,953.29 µs
3,763,048.62 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[True]__lprep_adv[True]__is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		3,463,704.29 µs
(0.00%)Baseline: 3,463,704.29 µs
3,810,074.72 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[False]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		3,249,465.05 µs
(0.00%)Baseline: 3,249,465.05 µs
3,574,411.56 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		2,414,989.73 µs
(0.00%)Baseline: 2,414,989.73 µs
2,656,488.70 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[True]__divdamp_type[3]-compile_time_domain]📈 view plot
🚷 view threshold		2,989,175.46 µs
(0.00%)Baseline: 2,989,175.46 µs
3,288,093.00 µs
(90.91%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:gtfn_gpu:icon_benchmark_global
Click to view all benchmark results
BenchmarkLatencyBenchmark Result
microseconds (µs)
(Result Δ%)		Upper Boundary
microseconds (µs)
(Limit %)
TestApplyDiffusionToVn[compile_time_domain]📈 view plot
🚷 view threshold		670.15 µs
(-0.48%)Baseline: 673.39 µs
740.73 µs
(90.47%)
TestApplyDiffusionToWAndComputeHorizontalGradientsForTurbulence[compile_time_domain]📈 view plot
🚷 view threshold		832.39 µs
(+0.07%)Baseline: 831.78 µs
914.96 µs
(90.98%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[False]__second_order_divdamp_factor[0.032]-compile_time_domain]📈 view plot
🚷 view threshold		1,381.26 µs
(0.00%)Baseline: 1,381.26 µs
1,519.38 µs
(90.91%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[True]__second_order_divdamp_factor[0.012]-compile_time_domain]📈 view plot
🚷 view threshold		1,323.28 µs
(0.00%)Baseline: 1,323.28 µs
1,455.61 µs
(90.91%)
TestCalculateNabla2AndSmagCoefficientsForVn[compile_time_domain]📈 view plot
🚷 view threshold		1,715.83 µs
(+0.05%)Baseline: 1,714.98 µs
1,886.48 µs
(90.95%)
TestCalculateNabla4[compile_time_domain]📈 view plot
🚷 view threshold		511.58 µs
(-15.75%)Baseline: 607.18 µs
667.90 µs
(76.60%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[False]-compile_time_domain]📈 view plot
🚷 view threshold		1,100.21 µs
(0.00%)Baseline: 1,100.21 µs
1,210.23 µs
(90.91%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[True]-compile_time_domain]📈 view plot
🚷 view threshold		941.46 µs
(0.00%)Baseline: 941.46 µs
1,035.61 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[False]-compile_time_domain]📈 view plot
🚷 view threshold		3,424.61 µs
(0.00%)Baseline: 3,424.61 µs
3,767.07 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[True]-compile_time_domain]📈 view plot
🚷 view threshold		3,082.96 µs
(0.00%)Baseline: 3,082.96 µs
3,391.25 µs
(90.91%)
TestComputeHorizontalVelocityQuantitiesAndFluxes[compile_time_domain]📈 view plot
🚷 view threshold		2,127.28 µs
(+0.33%)Baseline: 2,120.33 µs
2,332.37 µs
(91.21%)
TestComputeHydrostaticCorrectionTerm[compile_time_domain]📈 view plot
🚷 view threshold		109.62 µs
(+1.93%)Baseline: 107.54 µs
118.30 µs
(92.66%)
TestComputePerturbedQuantitiesAndInterpolation[compile_time_domain]📈 view plot
🚷 view threshold		2,037.78 µs
(+0.18%)Baseline: 2,034.06 µs
2,237.46 µs
(91.08%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		4,382.92 µs
(-0.04%)Baseline: 4,384.47 µs
4,822.92 µs
(90.88%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		4,424.82 µs
(-0.29%)Baseline: 4,437.76 µs
4,881.54 µs
(90.64%)
TestFusedVelocityAdvectionStencilVMomentum[compile_time_domain]📈 view plot
🚷 view threshold		2,599.13 µs
(+0.04%)Baseline: 2,598.06 µs
2,857.87 µs
(90.95%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[False]-compile_time_domain]📈 view plot
🚷 view threshold		1,319.82 µs
(0.00%)Baseline: 1,319.82 µs
1,451.80 µs
(90.91%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[True]-compile_time_domain]📈 view plot
🚷 view threshold		1,809.55 µs
(0.00%)Baseline: 1,809.55 µs
1,990.51 µs
(90.91%)
TestInitCellKdimFieldWithZeroWp[compile_time_domain]📈 view plot
🚷 view threshold		72.32 µs
(-0.17%)Baseline: 72.45 µs
79.69 µs
(90.75%)
TestInterpolateRhoThetaVToHalfLevelsAndComputePressureBuoyancyAcceleration[compile_time_domain]📈 view plot
🚷 view threshold		936.70 µs
(-0.49%)Baseline: 941.27 µs
1,035.40 µs
(90.47%)
TestMoIntpRbfRbfVecInterpolVertex[compile_time_domain]📈 view plot
🚷 view threshold		513.51 µs
(-0.55%)Baseline: 516.36 µs
568.00 µs
(90.41%)
TestUpdateMassFluxWeighted[compile_time_domain]📈 view plot
🚷 view threshold		369.63 µs
(+0.44%)Baseline: 368.03 µs
404.83 µs
(91.31%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		3,640.60 µs
(0.00%)Baseline: 3,640.60 µs
4,004.66 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[True]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		3,691.03 µs
(0.00%)Baseline: 3,691.03 µs
4,060.14 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		3,547.31 µs
(0.00%)Baseline: 3,547.31 µs
3,902.04 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[True]__lprep_adv[True]__is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		3,693.05 µs
(0.00%)Baseline: 3,693.05 µs
4,062.35 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[False]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		3,797.66 µs
(0.00%)Baseline: 3,797.66 µs
4,177.42 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		3,722.80 µs
(0.00%)Baseline: 3,722.80 µs
4,095.08 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[True]__divdamp_type[3]-compile_time_domain]📈 view plot
🚷 view threshold		3,832.95 µs
(0.00%)Baseline: 3,832.95 µs
4,216.24 µs
(90.91%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:dace_cpu:icon_benchmark_regional

🚨 2 Alerts

BenchmarkMeasure
Units		ViewBenchmark Result
(Result Δ%)		Upper Boundary
(Limit %)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-False]Latency
seconds (s)		📈 plot
🚷 threshold
🚨 alert (🔔)		2.10 s
(+59.97%)Baseline: 1.31 s
1.45 s
(145.42%)

model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-True]Latency
seconds (s)		📈 plot
🚷 threshold
🚨 alert (🔔)		2.04 s
(+10.30%)Baseline: 1.85 s
2.03 s
(100.28%)

Click to view all benchmark results
BenchmarkLatencyBenchmark Result
milliseconds (ms)
(Result Δ%)		Upper Boundary
milliseconds (ms)
(Limit %)
model/atmosphere/diffusion/tests/diffusion/integration_tests/test_benchmark_diffusion.py::test_diffusion_benchmark📈 view plot
🚷 view threshold		53.03 ms
(-8.81%)Baseline: 58.16 ms
63.97 ms
(82.90%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-False]📈 view plot
🚷 view threshold
🚨 view alert (🔔)		2,103.31 ms
(+59.97%)Baseline: 1,314.84 ms
1,446.32 ms
(145.42%)

model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-True]📈 view plot
🚷 view threshold
🚨 view alert (🔔)		2,039.66 ms
(+10.30%)Baseline: 1,849.13 ms
2,034.04 ms
(100.28%)

model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[True-False]📈 view plot
🚷 view threshold		2,035.27 ms
(-4.96%)Baseline: 2,141.43 ms
2,355.57 ms
(86.40%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:dace_gpu:icon_benchmark_regional
Click to view all benchmark results
BenchmarkLatencyBenchmark Result
microseconds (µs)
(Result Δ%)		Upper Boundary
microseconds (µs)
(Limit %)
TestApplyDiffusionToVn[compile_time_domain]📈 view plot
🚷 view threshold		100.91 µs
(+0.56%)Baseline: 100.35 µs
110.38 µs
(91.42%)
TestApplyDiffusionToWAndComputeHorizontalGradientsForTurbulence[compile_time_domain]📈 view plot
🚷 view threshold		127.46 µs
(+0.13%)Baseline: 127.30 µs
140.03 µs
(91.02%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[False]__second_order_divdamp_factor[0.032]-compile_time_domain]📈 view plot
🚷 view threshold		210.24 µs
(0.00%)Baseline: 210.24 µs
231.26 µs
(90.91%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[True]__second_order_divdamp_factor[0.012]-compile_time_domain]📈 view plot
🚷 view threshold		261.68 µs
(0.00%)Baseline: 261.68 µs
287.85 µs
(90.91%)
TestCalculateNabla2AndSmagCoefficientsForVn[compile_time_domain]📈 view plot
🚷 view threshold		125.41 µs
(+1.29%)Baseline: 123.81 µs
136.19 µs
(92.08%)
TestCalculateNabla4[compile_time_domain]📈 view plot
🚷 view threshold		88.14 µs
(-10.56%)Baseline: 98.54 µs
108.39 µs
(81.31%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[False]-compile_time_domain]📈 view plot
🚷 view threshold		199.13 µs
(0.00%)Baseline: 199.13 µs
219.04 µs
(90.91%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[True]-compile_time_domain]📈 view plot
🚷 view threshold		144.84 µs
(0.00%)Baseline: 144.84 µs
159.32 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[False]-compile_time_domain]📈 view plot
🚷 view threshold		440.67 µs
(0.00%)Baseline: 440.67 µs
484.74 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[True]-compile_time_domain]📈 view plot
🚷 view threshold		404.19 µs
(0.00%)Baseline: 404.19 µs
444.61 µs
(90.91%)
TestComputeHorizontalVelocityQuantitiesAndFluxes[compile_time_domain]📈 view plot
🚷 view threshold		316.70 µs
(+1.80%)Baseline: 311.11 µs
342.22 µs
(92.54%)
TestComputeHydrostaticCorrectionTerm[compile_time_domain]📈 view plot
🚷 view threshold		16.67 µs
(+4.30%)Baseline: 15.98 µs
17.58 µs
(94.82%)
TestComputePerturbedQuantitiesAndInterpolation[compile_time_domain]📈 view plot
🚷 view threshold		304.96 µs
(+4.11%)Baseline: 292.91 µs
322.20 µs
(94.65%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		731.30 µs
(+1.50%)Baseline: 720.51 µs
792.56 µs
(92.27%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		746.17 µs
(+2.15%)Baseline: 730.44 µs
803.48 µs
(92.87%)
TestFusedVelocityAdvectionStencilVMomentum[compile_time_domain]📈 view plot
🚷 view threshold		238.59 µs
(+2.08%)Baseline: 233.72 µs
257.10 µs
(92.80%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[False]-compile_time_domain]📈 view plot
🚷 view threshold		171.20 µs
(0.00%)Baseline: 171.20 µs
188.32 µs
(90.91%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[True]-compile_time_domain]📈 view plot
🚷 view threshold		215.00 µs
(0.00%)Baseline: 215.00 µs
236.50 µs
(90.91%)
TestInitCellKdimFieldWithZeroWp[compile_time_domain]📈 view plot
🚷 view threshold		18.13 µs
(+2.38%)Baseline: 17.71 µs
19.48 µs
(93.07%)
TestInterpolateRhoThetaVToHalfLevelsAndComputePressureBuoyancyAcceleration[compile_time_domain]📈 view plot
🚷 view threshold		128.88 µs
(+1.27%)Baseline: 127.26 µs
139.98 µs
(92.07%)
TestMoIntpRbfRbfVecInterpolVertex[compile_time_domain]📈 view plot
🚷 view threshold		43.44 µs
(-0.17%)Baseline: 43.52 µs
47.87 µs
(90.75%)
TestUpdateMassFluxWeighted[compile_time_domain]📈 view plot
🚷 view threshold		56.76 µs
(+0.56%)Baseline: 56.45 µs
62.09 µs
(91.42%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		565.76 µs
(0.00%)Baseline: 565.76 µs
622.34 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[True]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		590.68 µs
(0.00%)Baseline: 590.68 µs
649.75 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		576.73 µs
(0.00%)Baseline: 576.73 µs
634.40 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[True]__lprep_adv[True]__is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		619.31 µs
(0.00%)Baseline: 619.31 µs
681.24 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[False]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		555.34 µs
(0.00%)Baseline: 555.34 µs
610.87 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		606.02 µs
(0.00%)Baseline: 606.02 µs
666.62 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[True]__divdamp_type[3]-compile_time_domain]📈 view plot
🚷 view threshold		621.86 µs
(0.00%)Baseline: 621.86 µs
684.05 µs
(90.91%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:gtfn_cpu:icon_benchmark_global

🚨 2 Alerts

BenchmarkMeasure
Units		ViewBenchmark Result
(Result Δ%)		Upper Boundary
(Limit %)
TestApplyDiffusionToVn[compile_time_domain]Latency
milliseconds (ms)		📈 plot
🚷 threshold
🚨 alert (🔔)		14.15 ms
(+10.10%)Baseline: 12.85 ms
14.13 ms
(100.09%)

TestUpdateMassFluxWeighted[compile_time_domain]Latency
milliseconds (ms)		📈 plot
🚷 threshold
🚨 alert (🔔)		6.12 ms
(+11.92%)Baseline: 5.47 ms
6.02 ms
(101.74%)

Click to view all benchmark results
BenchmarkLatencyBenchmark Result
microseconds (µs)
(Result Δ%)		Upper Boundary
microseconds (µs)
(Limit %)
TestApplyDiffusionToVn[compile_time_domain]📈 view plot
🚷 view threshold
🚨 view alert (🔔)		14,145.11 µs
(+10.10%)Baseline: 12,847.46 µs
14,132.21 µs
(100.09%)

TestApplyDiffusionToWAndComputeHorizontalGradientsForTurbulence[compile_time_domain]📈 view plot
🚷 view threshold		28,515.41 µs
(-12.21%)Baseline: 32,479.78 µs
35,727.76 µs
(79.81%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[False]__second_order_divdamp_factor[0.032]-compile_time_domain]📈 view plot
🚷 view threshold		106,620.83 µs
(0.00%)Baseline: 106,620.83 µs
117,282.91 µs
(90.91%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[True]__second_order_divdamp_factor[0.012]-compile_time_domain]📈 view plot
🚷 view threshold		50,727.03 µs
(0.00%)Baseline: 50,727.03 µs
55,799.73 µs
(90.91%)
TestCalculateNabla2AndSmagCoefficientsForVn[compile_time_domain]📈 view plot
🚷 view threshold		11,624.11 µs
(-17.91%)Baseline: 14,160.81 µs
15,576.89 µs
(74.62%)
TestCalculateNabla4[compile_time_domain]📈 view plot
🚷 view threshold		4,081.33 µs
(-49.48%)Baseline: 8,078.42 µs
8,886.27 µs
(45.93%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[False]-compile_time_domain]📈 view plot
🚷 view threshold		18,457.96 µs
(0.00%)Baseline: 18,457.96 µs
20,303.76 µs
(90.91%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[True]-compile_time_domain]📈 view plot
🚷 view threshold		18,686.17 µs
(0.00%)Baseline: 18,686.17 µs
20,554.79 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[False]-compile_time_domain]📈 view plot
🚷 view threshold		314,905.52 µs
(0.00%)Baseline: 314,905.52 µs
346,396.07 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[True]-compile_time_domain]📈 view plot
🚷 view threshold		309,579.27 µs
(0.00%)Baseline: 309,579.27 µs
340,537.19 µs
(90.91%)
TestComputeHorizontalVelocityQuantitiesAndFluxes[compile_time_domain]📈 view plot
🚷 view threshold		74,242.87 µs
(+3.88%)Baseline: 71,472.25 µs
78,619.48 µs
(94.43%)
TestComputeHydrostaticCorrectionTerm[compile_time_domain]📈 view plot
🚷 view threshold		1,920.08 µs
(-2.99%)Baseline: 1,979.27 µs
2,177.20 µs
(88.19%)
TestComputePerturbedQuantitiesAndInterpolation[compile_time_domain]📈 view plot
🚷 view threshold		64,103.99 µs
(+0.12%)Baseline: 64,025.62 µs
70,428.19 µs
(91.02%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		225,991.41 µs
(-1.07%)Baseline: 228,433.08 µs
251,276.39 µs
(89.94%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		229,841.14 µs
(-1.36%)Baseline: 233,016.03 µs
256,317.63 µs
(89.67%)
TestFusedVelocityAdvectionStencilVMomentum[compile_time_domain]📈 view plot
🚷 view threshold		154,042.88 µs
(-0.20%)Baseline: 154,354.32 µs
169,789.75 µs
(90.73%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[False]-compile_time_domain]📈 view plot
🚷 view threshold		46,407.01 µs
(0.00%)Baseline: 46,407.01 µs
51,047.71 µs
(90.91%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[True]-compile_time_domain]📈 view plot
🚷 view threshold		55,209.69 µs
(0.00%)Baseline: 55,209.69 µs
60,730.66 µs
(90.91%)
TestInitCellKdimFieldWithZeroWp[compile_time_domain]📈 view plot
🚷 view threshold		848.61 µs
(-2.01%)Baseline: 866.03 µs
952.64 µs
(89.08%)
TestInterpolateRhoThetaVToHalfLevelsAndComputePressureBuoyancyAcceleration[compile_time_domain]📈 view plot
🚷 view threshold		22,894.96 µs
(+4.88%)Baseline: 21,829.65 µs
24,012.62 µs
(95.35%)
TestMoIntpRbfRbfVecInterpolVertex[compile_time_domain]📈 view plot
🚷 view threshold		3,295.39 µs
(-4.60%)Baseline: 3,454.45 µs
3,799.90 µs
(86.72%)
TestUpdateMassFluxWeighted[compile_time_domain]📈 view plot
🚷 view threshold
🚨 view alert (🔔)		6,122.52 µs
(+11.92%)Baseline: 5,470.63 µs
6,017.69 µs
(101.74%)

TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		211,658.54 µs
(0.00%)Baseline: 211,658.54 µs
232,824.40 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[True]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		214,776.18 µs
(0.00%)Baseline: 214,776.18 µs
236,253.80 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		209,925.58 µs
(0.00%)Baseline: 209,925.58 µs
230,918.14 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[True]__lprep_adv[True]__is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		220,976.37 µs
(0.00%)Baseline: 220,976.37 µs
243,074.01 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[False]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		219,752.84 µs
(0.00%)Baseline: 219,752.84 µs
241,728.13 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		219,446.56 µs
(0.00%)Baseline: 219,446.56 µs
241,391.21 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[True]__divdamp_type[3]-compile_time_domain]📈 view plot
🚷 view threshold		213,896.92 µs
(0.00%)Baseline: 213,896.92 µs
235,286.61 µs
(90.91%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:dace_cpu:icon_benchmark_global

🚨 1 Alert

BenchmarkMeasure
Units		ViewBenchmark Result
(Result Δ%)		Upper Boundary
(Limit %)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-False]Latency
seconds (s)		📈 plot
🚷 threshold
🚨 alert (🔔)		13.31 s
(+13.98%)Baseline: 11.68 s
12.84 s
(103.62%)

Click to view all benchmark results
BenchmarkLatencyBenchmark Result
seconds (s)
(Result Δ%)		Upper Boundary
seconds (s)
(Limit %)
model/atmosphere/diffusion/tests/diffusion/integration_tests/test_benchmark_diffusion.py::test_diffusion_benchmark📈 view plot
🚷 view threshold		2.95 s
(+5.15%)Baseline: 2.81 s
3.09 s
(95.59%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-False]📈 view plot
🚷 view threshold
🚨 view alert (🔔)		13.31 s
(+13.98%)Baseline: 11.68 s
12.84 s
(103.62%)

model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-True]📈 view plot
🚷 view threshold		12.65 s
(+9.77%)Baseline: 11.52 s
12.67 s
(99.79%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[True-False]📈 view plot
🚷 view threshold		16.19 s
(+6.40%)Baseline: 15.21 s
16.73 s
(96.73%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:dace_gpu:icon_benchmark_regional
Click to view all benchmark results
BenchmarkLatencyBenchmark Result
microseconds (µs)
(Result Δ%)		Upper Boundary
microseconds (µs)
(Limit %)
model/atmosphere/diffusion/tests/diffusion/integration_tests/test_benchmark_diffusion.py::test_diffusion_benchmark📈 view plot
🚷 view threshold		672.23 µs
(-0.47%)Baseline: 675.37 µs
742.91 µs
(90.49%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-False]📈 view plot
🚷 view threshold		2,886.87 µs
(-0.69%)Baseline: 2,906.82 µs
3,197.50 µs
(90.29%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-True]📈 view plot
🚷 view threshold		2,920.89 µs
(-0.64%)Baseline: 2,939.74 µs
3,233.71 µs
(90.33%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[True-False]📈 view plot
🚷 view threshold		3,306.31 µs
(-1.16%)Baseline: 3,345.17 µs
3,679.69 µs
(89.85%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:dace_gpu:icon_benchmark_global
Click to view all benchmark results
BenchmarkLatencyBenchmark Result
microseconds (µs)
(Result Δ%)		Upper Boundary
microseconds (µs)
(Limit %)
TestApplyDiffusionToVn[compile_time_domain]📈 view plot
🚷 view threshold		686.13 µs
(+0.32%)Baseline: 683.92 µs
752.31 µs
(91.20%)
TestApplyDiffusionToWAndComputeHorizontalGradientsForTurbulence[compile_time_domain]📈 view plot
🚷 view threshold		746.70 µs
(+1.04%)Baseline: 739.05 µs
812.96 µs
(91.85%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[False]__second_order_divdamp_factor[0.032]-compile_time_domain]📈 view plot
🚷 view threshold		1,496.97 µs
(0.00%)Baseline: 1,496.97 µs
1,646.66 µs
(90.91%)
TestApplyDivergenceDampingAndUpdateVn[divdamp_order[24]__is_iau_active[True]__second_order_divdamp_factor[0.012]-compile_time_domain]📈 view plot
🚷 view threshold		1,819.45 µs
(0.00%)Baseline: 1,819.45 µs
2,001.40 µs
(90.91%)
TestCalculateNabla2AndSmagCoefficientsForVn[compile_time_domain]📈 view plot
🚷 view threshold		895.89 µs
(+0.69%)Baseline: 889.75 µs
978.73 µs
(91.54%)
TestCalculateNabla4[compile_time_domain]📈 view plot
🚷 view threshold		574.05 µs
(-4.64%)Baseline: 601.99 µs
662.19 µs
(86.69%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[False]-compile_time_domain]📈 view plot
🚷 view threshold		1,167.55 µs
(0.00%)Baseline: 1,167.55 µs
1,284.31 µs
(90.91%)
TestComputeAveragedVnAndFluxesAndPrepareTracerAdvection[prepare_advection[True]__at_first_substep[True]-compile_time_domain]📈 view plot
🚷 view threshold		945.21 µs
(0.00%)Baseline: 945.21 µs
1,039.73 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[False]-compile_time_domain]📈 view plot
🚷 view threshold		2,886.29 µs
(0.00%)Baseline: 2,886.29 µs
3,174.92 µs
(90.91%)
TestComputeDerivedHorizontalWindsAndKEAndHorizontalAdvectionofWAndContravariantCorrection[skip_compute_predictor_vertical_advection[True]-compile_time_domain]📈 view plot
🚷 view threshold		2,695.64 µs
(0.00%)Baseline: 2,695.64 µs
2,965.21 µs
(90.91%)
TestComputeHorizontalVelocityQuantitiesAndFluxes[compile_time_domain]📈 view plot
🚷 view threshold		2,103.53 µs
(-0.06%)Baseline: 2,104.87 µs
2,315.36 µs
(90.85%)
TestComputeHydrostaticCorrectionTerm[compile_time_domain]📈 view plot
🚷 view threshold		107.07 µs
(+1.59%)Baseline: 105.39 µs
115.93 µs
(92.36%)
TestComputePerturbedQuantitiesAndInterpolation[compile_time_domain]📈 view plot
🚷 view threshold		1,896.07 µs
(+0.45%)Baseline: 1,887.54 µs
2,076.29 µs
(91.32%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		3,516.87 µs
(+0.70%)Baseline: 3,492.46 µs
3,841.71 µs
(91.54%)
TestComputeThetaRhoPressureGradientAndUpdateVn[is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		3,585.04 µs
(+0.93%)Baseline: 3,551.97 µs
3,907.17 µs
(91.76%)
TestFusedVelocityAdvectionStencilVMomentum[compile_time_domain]📈 view plot
🚷 view threshold		1,546.12 µs
(+0.69%)Baseline: 1,535.50 µs
1,689.05 µs
(91.54%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[False]-compile_time_domain]📈 view plot
🚷 view threshold		1,109.43 µs
(0.00%)Baseline: 1,109.43 µs
1,220.37 µs
(90.91%)
TestFusedVelocityAdvectionStencilsHMomentum[apply_extra_diffusion_on_vn[True]-compile_time_domain]📈 view plot
🚷 view threshold		1,446.09 µs
(0.00%)Baseline: 1,446.09 µs
1,590.70 µs
(90.91%)
TestInitCellKdimFieldWithZeroWp[compile_time_domain]📈 view plot
🚷 view threshold		73.11 µs
(+1.32%)Baseline: 72.16 µs
79.37 µs
(92.11%)
TestInterpolateRhoThetaVToHalfLevelsAndComputePressureBuoyancyAcceleration[compile_time_domain]📈 view plot
🚷 view threshold		903.14 µs
(-0.14%)Baseline: 904.41 µs
994.85 µs
(90.78%)
TestMoIntpRbfRbfVecInterpolVertex[compile_time_domain]📈 view plot
🚷 view threshold		302.55 µs
(+0.55%)Baseline: 300.89 µs
330.98 µs
(91.41%)
TestUpdateMassFluxWeighted[compile_time_domain]📈 view plot
🚷 view threshold		363.73 µs
(+0.34%)Baseline: 362.50 µs
398.75 µs
(91.22%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		3,736.99 µs
(0.00%)Baseline: 3,736.99 µs
4,110.69 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[False]__at_last_substep[True]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		3,906.84 µs
(0.00%)Baseline: 3,906.84 µs
4,297.52 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[False]__lprep_adv[True]__is_iau_active[False]-compile_time_domain]📈 view plot
🚷 view threshold		3,830.93 µs
(0.00%)Baseline: 3,830.93 µs
4,214.03 µs
(90.91%)
TestVerticallyImplicitSolverAtCorrectorStep[at_first_substep[True]__at_last_substep[True]__lprep_adv[True]__is_iau_active[True]-compile_time_domain]📈 view plot
🚷 view threshold		4,140.68 µs
(0.00%)Baseline: 4,140.68 µs
4,554.75 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[False]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		3,799.87 µs
(0.00%)Baseline: 3,799.87 µs
4,179.85 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[False]__divdamp_type[32]-compile_time_domain]📈 view plot
🚷 view threshold		4,059.05 µs
(0.00%)Baseline: 4,059.05 µs
4,464.96 µs
(90.91%)
TestVerticallyImplicitSolverAtPredictorStep[at_first_substep[True]__is_iau_active[True]__divdamp_type[3]-compile_time_domain]📈 view plot
🚷 view threshold		4,171.17 µs
(0.00%)Baseline: 4,171.17 µs
4,588.29 µs
(90.91%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:gtfn_gpu:icon_benchmark_global
Click to view all benchmark results
BenchmarkLatencyBenchmark Result
milliseconds (ms)
(Result Δ%)		Upper Boundary
milliseconds (ms)
(Limit %)
model/atmosphere/diffusion/tests/diffusion/integration_tests/test_benchmark_diffusion.py::test_diffusion_benchmark📈 view plot
🚷 view threshold		5.73 ms
(-1.44%)Baseline: 5.81 ms
6.39 ms
(89.60%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-False]📈 view plot
🚷 view threshold		20.17 ms
(-0.17%)Baseline: 20.21 ms
22.23 ms
(90.75%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-True]📈 view plot
🚷 view threshold		20.21 ms
(-0.30%)Baseline: 20.27 ms
22.29 ms
(90.64%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[True-False]📈 view plot
🚷 view threshold		23.40 ms
(-0.37%)Baseline: 23.49 ms
25.84 ms
(90.57%)
🐰 View full continuous benchmarking report in Bencher

@gridtoolsjenkins
Copy link
Collaborator

gridtoolsjenkins commented Dec 4, 2025

🐰 Bencher Report

Branchfree_stencil_test_fixtures
Testbedci-runner:santis-gh200:dace_gpu:icon_benchmark_global
Click to view all benchmark results
BenchmarkLatencyBenchmark Result
milliseconds (ms)
(Result Δ%)		Upper Boundary
milliseconds (ms)
(Limit %)
model/atmosphere/diffusion/tests/diffusion/integration_tests/test_benchmark_diffusion.py::test_diffusion_benchmark📈 view plot
🚷 view threshold		4.88 ms
(-0.95%)Baseline: 4.93 ms
5.42 ms
(90.05%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-False]📈 view plot
🚷 view threshold		19.05 ms
(-0.12%)Baseline: 19.08 ms
20.99 ms
(90.80%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[False-True]📈 view plot
🚷 view threshold		19.27 ms
(-0.15%)Baseline: 19.30 ms
21.23 ms
(90.77%)
model/atmosphere/dycore/tests/dycore/integration_tests/test_benchmark_solve_nonhydro.py::test_benchmark_solve_nonhydro[True-False]📈 view plot
🚷 view threshold		21.91 ms
(-14.22%)Baseline: 25.54 ms
28.10 ms
(77.98%)
🐰 View full continuous benchmarking report in Bencher

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@egparedes egparedes Awaiting requested review from egparedes

@havogt havogt Awaiting requested review from havogt

At least 1 approving review is required to merge this pull request.

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

10 participants

@iomaganaris @gridtoolsjenkins @DropD @OngChia @havogt @philip-paul-mueller @halungge @edopao @kotsaloscv