Allows the use of 64-bit atomic minimum and maximum operations on `atomic<vec2u>` in WGSL. This provides WebGPU shader authors with a way to implement certain algorithms that use 64-bit atomics without requiring full support for 64-bit integers.
This provides WebGPU shader authors with a way to implement certain algorithms that use 64-bit atomics without requiring full support for 64-bit integers. Not every device that supports 64-bit atomics can support every atomic operation on these types, so this feature is scoped to the min and max operations to deliver broadest reach.
Explainers: https://github.com/gpuweb/gpuweb/issues/5071