Reimplement background checkerboard rendering#4034
Reimplement background checkerboard rendering#4034timon-schelling wants to merge 16 commits intomasterfrom
Conversation
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
There was a problem hiding this comment.
5 issues found across 14 files
Confidence score: 2/5
- There is a high-confidence functional risk in
node-graph/nodes/gstd/src/render_cache.rs:store_regions()only evicts before insertion, so cache usage can remain aboveMAX_CACHE_MEMORY_BYTES, which can cause sustained memory pressure/regression. node-graph/libraries/wgpu-executor/src/lib.rsalso has a concrete runtime risk: zero-sized texture requests are not clamped to at least 1x1, which can lead to invalidcreate_texturecalls on edge-case inputs.- Other findings in
node-graph/libraries/wgpu-executor/src/texture_cache.rs(quadratic eviction-path scanning and unconditionalprintln!) plus the PR title wording issue are lower-severity, but they add avoidable performance/operational noise. - Pay close attention to
node-graph/nodes/gstd/src/render_cache.rs,node-graph/libraries/wgpu-executor/src/lib.rs, andnode-graph/libraries/wgpu-executor/src/texture_cache.rs- memory-limit enforcement and texture-size validation are the key correctness risks, with cache-path efficiency/logging cleanup as follow-up priorities.
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="node-graph/nodes/gstd/src/render_cache.rs">
<violation number="1" location="node-graph/nodes/gstd/src/render_cache.rs:186">
P1: `store_regions()` evicts before insertion but not after, so cache memory can exceed `MAX_CACHE_MEMORY_BYTES` and remain over budget.</violation>
</file>
<file name="node-graph/libraries/wgpu-executor/src/lib.rs">
<violation number="1" location="node-graph/libraries/wgpu-executor/src/lib.rs:1">
P2: Custom agent: **PR title enforcement**
PR title uses the non-standard abbreviation "bg", which violates the no-abbreviations-in-prose requirement.</violation>
<violation number="2" location="node-graph/libraries/wgpu-executor/src/lib.rs:100">
P2: Clamp requested texture size to at least 1x1 before forwarding to the cache; otherwise zero-sized inputs can trigger invalid `create_texture` calls.</violation>
</file>
<file name="node-graph/libraries/wgpu-executor/src/texture_cache.rs">
<violation number="1" location="node-graph/libraries/wgpu-executor/src/texture_cache.rs:57">
P2: Remove unconditional `println!` from the texture allocation path to avoid production log spam and I/O overhead.</violation>
<violation number="2" location="node-graph/libraries/wgpu-executor/src/texture_cache.rs:72">
P2: `evict_until_fits` has quadratic scanning in the hot eviction path; track free-bytes incrementally to avoid O(n²) work.</violation>
</file>
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a texture caching system and a GPU-based texture blending mechanism to improve rendering performance and memory management. It refactors the rendering pipeline to use these new components, removes the hide_artboards parameter, and updates the node graph to support background composition. I have identified a high-severity issue in the blending shader where the formula incorrectly handles premultiplied alpha, as well as medium-severity issues regarding hardcoded pixel sizes and the use of println! in library code.
timon-schelling
changed the title
Performance Benchmark Results
|
There was a problem hiding this comment.
1 issue found across 2 files (changes from recent commits).
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="node-graph/libraries/wgpu-executor/src/texture_cache.rs">
<violation number="1" location="node-graph/libraries/wgpu-executor/src/texture_cache.rs:79">
P2: `free_bytes -= entry.bytes` can underflow because `free_bytes` is a stale snapshot while `Arc::strong_count` is re-evaluated later per entry.</violation>
</file>
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
Performance Benchmark Results
|
Performance Benchmark Results
|
There was a problem hiding this comment.
1 issue found across 2 files (changes from recent commits).
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="node-graph/interpreted-executor/src/util.rs">
<violation number="1" location="node-graph/interpreted-executor/src/util.rs:54">
P1: `render_background_intermediate` still requires `FOOTPRINT`, but this wiring now declares only `VARARGS`. That can break context dependency tracking and cause incorrect/stale background rendering when viewport footprint changes.</violation>
</file>
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
Performance Benchmark Results
|
Performance Benchmark Results
|
There was a problem hiding this comment.
2 issues found across 5 files (changes from recent commits).
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="node-graph/libraries/rendering/src/background.rs">
<violation number="1" location="node-graph/libraries/rendering/src/background.rs:24">
P2: Checkerboard background rendering lost the `to_canvas()` guard, so non-canvas passes (e.g. thumbnail/mask) can now incorrectly include checkerboards.</violation>
</file>
<file name="node-graph/libraries/rendering/src/renderer.rs">
<violation number="1" location="node-graph/libraries/rendering/src/renderer.rs:333">
P2: `backgrounds` merge logic can keep stale metadata when incoming data has the same length, causing outdated checkerboard placement after region merges.</violation>
</file>
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
There was a problem hiding this comment.
1 issue found across 1 file (changes from recent commits).
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="node-graph/libraries/rendering/src/renderer.rs">
<violation number="1" location="node-graph/libraries/rendering/src/renderer.rs:368">
P2: This merge uses `Vec::contains` inside the loop, making background merges quadratic. If background lists grow with graph size, this will scale poorly. Consider using a `HashSet` to track seen backgrounds while pushing into the vec.</violation>
</file>
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
| vector_data.extend(other.vector_data.iter().map(|(id, data)| (*id, data.clone()))); | ||
|
|
||
| // TODO: Find a better non O(n^2) way to merge backgrounds | ||
| for background in &other.backgrounds { |
There was a problem hiding this comment.
P2: This merge uses Vec::contains inside the loop, making background merges quadratic. If background lists grow with graph size, this will scale poorly. Consider using a HashSet to track seen backgrounds while pushing into the vec.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At node-graph/libraries/rendering/src/renderer.rs, line 368:
<comment>This merge uses `Vec::contains` inside the loop, making background merges quadratic. If background lists grow with graph size, this will scale poorly. Consider using a `HashSet` to track seen backgrounds while pushing into the vec.</comment>
<file context>
@@ -363,9 +363,12 @@ impl RenderMetadata {
- *backgrounds = other.backgrounds.clone();
+
+ // TODO: Find a better non O(n^2) way to merge backgrounds
+ for background in &other.backgrounds {
+ if !backgrounds.contains(background) {
+ backgrounds.push(background.clone());
</file context>
a661a14 to
64feff4
Compare
1 participant
Improves the implementation from #4022. Closes #4021.