Increase default NPS for the Sphere and the Sphere SDDR#516
Conversation
WalkthroughThe PR updates the Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Review rate limit: 0/1 reviews remaining, refill in 60 minutes.Comment |
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
src/jade/resources/default_cfg/run_cfg.yml (1)
189-209:⚠️ Potential issue | 🟡 MinorDuplicate benchmark entries with inconsistent configurations.
The configuration contains duplicate entries that should be resolved:
- IPPE-DT appears twice (lines 189-198 and 310-319) with identical configurations
- IPPE-CF appears twice (lines 200-209 and 321-330) with different NPS values (1e9 vs 1e8)
The IPPE-CF duplication with conflicting NPS values is particularly concerning, as it's unclear which configuration should take precedence. This could lead to unexpected behavior depending on how the YAML is parsed.
Would you like me to help identify the correct configuration and generate a cleanup patch to remove these duplicates?
</comment_end -->Also applies to: 310-330
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/jade/resources/default_cfg/run_cfg.yml` around lines 189 - 209, There are duplicate benchmark keys IPPE-DT and IPPE-CF; remove the repeated blocks and consolidate into a single canonical entry for each (keep the IPPE-DT block once and merge identical fields for codes, custom_input, nps, description, only_input), and for IPPE-CF resolve the conflicting nps by choosing the correct value (replace the two IPPE-CF blocks with one entry using the intended nps of either 1e9 or 1e8), ensuring the merged block preserves codes, custom_input, description and only_input from the authoritative source; finally run a YAML linter to validate the file and confirm no duplicate keys remain.
🧹 Nitpick comments (1)
src/jade/resources/default_cfg/run_cfg.yml (1)
10-10: Verify resource impact of 10x NPS increase and consider adding validation.Increasing NPS from
1e8to1e9significantly increases computational time, memory consumption, and storage requirements. While the codebase shows awareness of extended execution times (see commented-out timeouts inbenchmark.py), no bounds validation currently prevents excessive NPS values.Consider:
- Confirming test and production environments can handle the extended execution
- Adding optional bounds validation in
BenchmarkRunConfigto prevent accidentally setting extreme valuesNote: The YAML file also contains duplicate benchmark entries (IPPE-DT at lines 189–198 and 310–319; IPPE-CF at lines 200–209 and 321–330) with inconsistent NPS values (1e9 vs 1e8 for IPPE-CF), which should be consolidated during cleanup.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/jade/resources/default_cfg/run_cfg.yml` at line 10, The NPS was bumped from 1e8 to 1e9 causing potential resource/execution issues and duplicate/inconsistent benchmark entries; add protection by implementing optional bounds validation in BenchmarkRunConfig (e.g., add a max_nps parameter and a validate_nps method called during construction or from_yaml parsing) that raises or clamps values above a safe threshold, update benchmark.py to respect/propagate this validation (and any timeout adjustments), and consolidate duplicate IPPE-DT/IPPE-CF entries in run_cfg.yml so each benchmark has a single canonical NPS value (ensure IPPE-CF isn’t left with inconsistent 1e8 vs 1e9 values).
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Outside diff comments:
In `@src/jade/resources/default_cfg/run_cfg.yml`:
- Around line 189-209: There are duplicate benchmark keys IPPE-DT and IPPE-CF;
remove the repeated blocks and consolidate into a single canonical entry for
each (keep the IPPE-DT block once and merge identical fields for codes,
custom_input, nps, description, only_input), and for IPPE-CF resolve the
conflicting nps by choosing the correct value (replace the two IPPE-CF blocks
with one entry using the intended nps of either 1e9 or 1e8), ensuring the merged
block preserves codes, custom_input, description and only_input from the
authoritative source; finally run a YAML linter to validate the file and confirm
no duplicate keys remain.
---
Nitpick comments:
In `@src/jade/resources/default_cfg/run_cfg.yml`:
- Line 10: The NPS was bumped from 1e8 to 1e9 causing potential
resource/execution issues and duplicate/inconsistent benchmark entries; add
protection by implementing optional bounds validation in BenchmarkRunConfig
(e.g., add a max_nps parameter and a validate_nps method called during
construction or from_yaml parsing) that raises or clamps values above a safe
threshold, update benchmark.py to respect/propagate this validation (and any
timeout adjustments), and consolidate duplicate IPPE-DT/IPPE-CF entries in
run_cfg.yml so each benchmark has a single canonical NPS value (ensure IPPE-CF
isn’t left with inconsistent 1e8 vs 1e9 values).
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: af8f24c1-8ebd-4462-8851-0fda9aba900c
📒 Files selected for processing (1)
src/jade/resources/default_cfg/run_cfg.yml
Codecov Report✅ All modified and coverable lines are covered by tests. 🚀 New features to boost your workflow:
|
This pull request applies an increase in the default NPS of the Sphere and the Sphere SDDR benchmarks from 1E8 to 1E9.
This change is applied to the
run_cfg.ymlfile.After the comparison between OpenMC (run with 1E8 particles) and MCNP (run with 1E9 particles) Sphere results, the benefit of applying this modification was highlighted. For example, for subcase

Sphere_68164_Er-164:Summary by CodeRabbit