Implement generic pipeline caching in WgpuExecutor by timon-schelling · Pull Request #4210 · GraphiteEditor/Graphite

timon-schelling · 2026-06-07T23:33:47Z

changing shader nodes to work with this will be done in a followup PR, for now they keep the separate ShaderRuntime.

This reverts commit e941bec.

gemini-code-assist

Code Review

This pull request refactors the WGPU pipeline execution model by introducing a dynamic, generic Pipeline trait system. Hardcoded compositor and resampler fields in WgpuExecutor are replaced with a thread-safe pipelines map that caches and runs pipelines dynamically. Additionally, the render_background and pixel_preview (renamed to render_pixel_preview) nodes have been refactored to use this new system. Feedback on these changes suggests adding an early return in render_background when viewport_zoom <= 0.0 to prevent uninitialized texture returns, simplifying the Pipeline trait using impl Future to avoid boxed future allocations, releasing the RwLockReadGuard earlier during pipeline retrieval, and cleaning up a verbose type signature in BackgroundCompositor::run.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

gemini-code-assist · 2026-06-07T23:36:16Z

+pub trait Pipeline: std::any::Any + Send + Sync + Sized {
+	type Args<'a>;
+	type Out: Send;
+
+	fn create(context: &WgpuContext) -> Self;
+
+	fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> PipelineFuture<'a, Self::Out>;
+}
+
+pub trait AsyncPipeline: std::any::Any + Send + Sync + Sized {
+	type Args<'a>;
+	type Out: Send;
+
+	fn create(context: &WgpuContext) -> Self;
+
+	fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> impl Future<Output = Self::Out> + Send + 'a;
+}
+
+impl<P: AsyncPipeline> Pipeline for P {
+	type Args<'a> = <P as AsyncPipeline>::Args<'a>;
+	type Out = <P as AsyncPipeline>::Out;
+
+	fn create(context: &WgpuContext) -> Self {
+		<P as AsyncPipeline>::create(context)
+	}
+
+	fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> PipelineFuture<'a, Self::Out> {
+		Box::pin(<P as AsyncPipeline>::run(self, executor, args))
+	}
+}


Since WgpuExecutor::run_pipeline always downcasts to the concrete pipeline type P, there is no need for a trait object or boxed futures. We can leverage Rust's support for impl Future in traits to define a single Pipeline trait without any boxing, eliminating the Box::pin allocation on every pipeline execution.

Suggested change

pub trait Pipeline: std::any::Any + Send + Sync + Sized {

type Args<'a>;

type Out: Send;

fn create(context: &WgpuContext) -> Self;

fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> PipelineFuture<'a, Self::Out>;

}

pub trait AsyncPipeline: std::any::Any + Send + Sync + Sized {

type Args<'a>;

type Out: Send;

fn create(context: &WgpuContext) -> Self;

fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> impl Future<Output = Self::Out> + Send + 'a;

}

impl<P: AsyncPipeline> Pipeline for P {

type Args<'a> = ::Args<'a>;

type Out = ::Out;

fn create(context: &WgpuContext) -> Self {

::create(context)

}

fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> PipelineFuture<'a, Self::Out> {

Box::pin(::run(self, executor, args))

}

}

pub trait Pipeline: std::any::Any + Send + Sync + Sized {

type Args<'a>;

type Out: Send;

fn create(context: &WgpuContext) -> Self;

fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> impl Future<Output = Self::Out> + Send + 'a;

}

No

error: lifetime bound not satisfied --> node-graph/nodes/gstd/src/render_background.rs:17:1 | 17 | #[node_macro::node(category(""))] | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this is a known limitation that will be removed in the future (see issue #100013 <https://github.com/rust-lang/rust/issues/100013> for more information) = note: this error originates in the attribute macro `node_macro::node` (in Nightly builds, run with -Z macro-backtrace for more info) error: lifetime bound not satisfied --> node-graph/nodes/gstd/src/render_pixel_preview.rs:13:1 | 13 | #[node_macro::node(category(""))] | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this is a known limitation that will be removed in the future (see issue #100013 <https://github.com/rust-lang/rust/issues/100013> for more information) = note: this error originates in the attribute macro `node_macro::node` (in Nightly builds, run with -Z macro-backtrace for more info)

cubic-dev-ai

7 issues found across 15 files

Confidence score: 2/5

There is a concrete user-facing regression risk in node-graph/nodes/gstd/src/render_background.rs: the zoom <= 0 early return can skip compositing/copying and produce a blank render output.
Several high-confidence panic paths were introduced (unwrap/expect and unwrapped application_io) across node-graph/nodes/gstd/src/render_background.rs and node-graph/libraries/wgpu-executor/src/lib.rs, which can crash runtime/executor flows instead of failing gracefully.
Additional executor-path concerns in node-graph/libraries/wgpu-executor/src/pipeline.rs and node-graph/libraries/wgpu-executor/src/lib.rs (per-call boxing in a hot path, eager duplicate pipeline creation, and longer-than-needed lock scope) increase performance/concurrency risk but are secondary to correctness issues.
Pay close attention to node-graph/nodes/gstd/src/render_background.rs, node-graph/libraries/wgpu-executor/src/lib.rs, node-graph/libraries/wgpu-executor/src/pipeline.rs - potential blank output, panic-on-error behavior, and executor hot-path regressions.

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/pipeline.rs">

<violation number="1" location="node-graph/libraries/wgpu-executor/src/pipeline.rs:35">
P2: Pipeline dispatch now boxes every async run, adding per-call heap allocation in a hot executor path.</violation>
</file>

_{Reply with feedback, questions, or to request a fix.

Re-trigger cubic}

cubic-dev-ai · 2026-06-07T23:39:53Z

+	}
+
+	fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> PipelineFuture<'a, Self::Out> {
+		Box::pin(<P as AsyncPipeline>::run(self, executor, args))


P2: Pipeline dispatch now boxes every async run, adding per-call heap allocation in a hot executor path.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At node-graph/libraries/wgpu-executor/src/pipeline.rs, line 35: <comment>Pipeline dispatch now boxes every async run, adding per-call heap allocation in a hot executor path.</comment> <file context> @@ -0,0 +1,37 @@ + } + + fn run<'a>(&'a self, executor: &'a WgpuExecutor, args: &'a Self::Args<'_>) -> PipelineFuture<'a, Self::Out> { + Box::pin(::run(self, executor, args)) + } +} </file context>

likely blocked by

error: lifetime bound not satisfied --> node-graph/nodes/gstd/src/render_background.rs:17:1 | 17 | #[node_macro::node(category(""))] | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this is a known limitation that will be removed in the future (see issue #100013 <https://github.com/rust-lang/rust/issues/100013> for more information) = note: this error originates in the attribute macro `node_macro::node` (in Nightly builds, run with -Z macro-backtrace for more info) error: lifetime bound not satisfied --> node-graph/nodes/gstd/src/render_pixel_preview.rs:13:1 | 13 | #[node_macro::node(category(""))] | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ | = note: this is a known limitation that will be removed in the future (see issue #100013 <https://github.com/rust-lang/rust/issues/100013> for more information) = note: this error originates in the attribute macro `node_macro::node` (in Nightly builds, run with -Z macro-backtrace for more info)

Thanks for the heads-up — that looks like a blocking compiler limitation.

cubic-dev-ai

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/lib.rs">

<violation number="1" location="node-graph/libraries/wgpu-executor/src/lib.rs:103">
P2: `P::create()` now executes while the `pipelines` write lock is held, introducing avoidable lock contention during expensive pipeline construction.</violation>
</file>

_{Reply with feedback, questions, or to request a fix.

Re-trigger cubic}

cubic-dev-ai · 2026-06-08T00:08:49Z

+			.write()
+			.unwrap()
+			.entry(key)
+			.or_insert_with(|| Arc::new(P::create(&self.context)))


P2: P::create() now executes while the pipelines write lock is held, introducing avoidable lock contention during expensive pipeline construction.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At node-graph/libraries/wgpu-executor/src/lib.rs, line 103: <comment>`P::create()` now executes while the `pipelines` write lock is held, introducing avoidable lock contention during expensive pipeline construction.</comment> <file context> @@ -91,17 +91,16 @@ impl WgpuExecutor { .unwrap() .entry(key) - .or_insert(built) + .or_insert_with(|| Arc::new(P::create(&self.context))) .clone() .downcast::() </file context>

timon-schelling added 8 commits June 7, 2026 18:54

Pipeline trait

605da5e

Impl Resampler pipeline

8b8fff0

Impl BackgroundCompositor pipeline

7038200

Move Pipelines to only consumer

e350c7e

Fixup

07e3e41

Refactor pipeline trait

e941bec

Fix background offset

1cd9e74

Revert "Refactor pipeline trait"

5dd5a35

This reverts commit e941bec.

timon-schelling marked this pull request as ready for review June 7, 2026 23:33

timon-schelling requested a review from TrueDoctor June 7, 2026 23:34

gemini-code-assist Bot reviewed Jun 7, 2026

View reviewed changes

cubic-dev-ai Bot reviewed Jun 7, 2026

View reviewed changes

github-actions Bot deployed to graphite-dev (Preview) June 7, 2026 23:41 View deployment

timon-schelling changed the title ~~Implement generic pipeline caching for WgpuExecutor~~ Implement generic pipeline caching in WgpuExecutor Jun 8, 2026

Review

48bff5b

cubic-dev-ai Bot reviewed Jun 8, 2026

View reviewed changes

Review

a3efae0

github-actions Bot deployed to graphite-dev (Preview) June 8, 2026 00:15 View deployment

github-actions Bot deployed to graphite-dev (Preview) June 8, 2026 00:36 View deployment

Uh oh!

Conversation

timon-schelling commented Jun 7, 2026

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

gemini-code-assist Bot Jun 7, 2026

Choose a reason for hiding this comment

Uh oh!

timon-schelling Jun 7, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

cubic-dev-ai Bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

cubic-dev-ai Bot Jun 7, 2026

Choose a reason for hiding this comment

Uh oh!

timon-schelling Jun 8, 2026

Choose a reason for hiding this comment

Uh oh!

cubic-dev-ai Bot Jun 8, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

cubic-dev-ai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

cubic-dev-ai Bot Jun 8, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

cubic-dev-ai Bot left a comment •

edited

Loading