2164f6b1eb
Welcome to better optimised op calls! Currently opSync is called with parameters of every type and count. This most definitely makes the call megamorphic. Additionally, it seems that spread params leads to V8 not being able to optimise the calls quite as well (apparently Fast Calls cannot be used with spread params). Monomorphising op calls should lead to some improved performance. Now that unwrapping of sync ops results is done on Rust side, this is pretty simple: ``` opSync("op_foo", param1, param2); // -> turns to ops.op_foo(param1, param2); ``` This means sync op calls are now just directly calling the native binding function. When V8 Fast API Calls are enabled, this will enable those to be called on the optimised path. Monomorphising async ops likely requires using callbacks and is left as an exercise to the reader. |
||
---|---|---|
.. | ||
src | ||
Cargo.toml | ||
LICENSE.md | ||
README.md | ||
webgpu.idl |
deno_webgpu
This op crate implements the WebGPU API as defined in https://gpuweb.github.io/gpuweb/ in Deno. The implementation targets the spec draft as of February 22, 2021. The spec is still very much in flux. This op crate tries to stay up to date with the spec, but is constrained by the features implemented in our GPU backend library wgpu.
The spec is still very bare bones, and is still missing many details. As the spec becomes more concrete, we will implement to follow the spec more closely.
In addition, setting the DENO_WEBGPU_TRACE
environmental variable will output
a
wgpu trace
to the specified directory.
For testing this op crate will make use of the WebGPU conformance tests suite, running through our WPT runner. This will be used to validate implementation conformance.
GitHub CI doesn't run with GPUs, so testing relies on software like DX WARP & Vulkan lavapipe. Currently only using DX WARP works, so tests are only run on Windows.
Links
Specification: https://gpuweb.github.io/gpuweb/
Design documents: https://github.com/gpuweb/gpuweb/tree/main/design
Conformance tests suite: https://github.com/gpuweb/cts
WebGPU examples for Deno: https://github.com/crowlKats/webgpu-examples
wgpu-users matrix channel: https://matrix.to/#/#wgpu-users:matrix.org