-
Notifications
You must be signed in to change notification settings - Fork 0
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.
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
try performance.now() for stabler results #22
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -17,9 +17,7 @@ jobs: | |
node-version: 20 | ||
cache: "yarn" | ||
|
||
- uses: calcit-lang/[email protected] | ||
with: | ||
bundler: false | ||
- uses: calcit-lang/[email protected] | ||
|
||
- name: "compiles calcit to js" | ||
run: caps --ci && cr -1 js | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,5 +1,6 @@ | ||
|
||
{} | ||
:calcit-version |0.9.6 | ||
:dependencies $ {} | ||
|calcit-lang/lilac |main | ||
|calcit-lang/memof |main | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -11,7 +11,7 @@ export let loadRenderer = async (canvas: HTMLCanvasElement) => { | |
seedSize, | ||
seedData: makeSeed(seedSize, 0), | ||
getParams: (dt) => [ | ||
dt * 0.04, // deltaT | ||
dt * 2, // deltaT | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 💡 Codebase verification The deltaT change is inconsistent with other attractors Looking at the deltaT values across all attractor implementations:
The change from 🔗 Analysis chainVerify stability with the 50x larger time step The change from
Let's check if similar changes were made consistently across other attractors: 🏁 Scripts executedThe following scripts were executed for the analysis: Script: #!/bin/bash
# Description: Check deltaT modifications across all attractor files
# Expected: Similar deltaT changes in other attractor implementations
# Search for deltaT parameter changes in attractor files
rg -B2 -A2 "deltaT" "src/apps/attractor/*.mts"
Length of output: 111 Script: #!/bin/bash
# Let's first find all attractor files
fd ".*\.mts$" src/apps/attractor/
# Then search for deltaT in these files
rg -B2 -A2 "dt.*deltaT" src/apps/attractor/
Length of output: 4022 |
||
20.0, // scale | ||
0.008, // width | ||
0.99, // opacity | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
💡 Codebase verification
Time step multiplier is significantly larger than other attractors
Looking at all attractor implementations, the Bouali attractor's time step multiplier of 1.0 is unusually large compared to other attractors:
The large time step could lead to numerical instability. Consider using a smaller multiplier:
🔗 Analysis chain
Consider the stability implications of increasing deltaT
The change increases the time step by 100x (from 0.01 to 1.0), which could lead to numerical instability in the Bouali attractor simulation. The Bouali system has small coefficients (0.1, 0.02, 0.01) in its equations, and using such a large time step might cause:
Consider a more conservative approach:
Let's verify if similar changes were made to other attractors:
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
Length of output: 117
Script:
Length of output: 937
Script:
Length of output: 5827