Cooperative matrix

[alan-baker]

All major platform APIs have now released a similar extensions for cooperative matrix:

• Metal introduced simdgroup_matrix in MSL 3.1
• HLSL has support in SM6.8 (currently experimental release)
• SPIR-V/Vulkan released SPV_KHR_cooperative_matrix

This feature is very useful for accelerating ML operations by performing matrix calculations across multiple threads.

[PWhiddy]

Would a wgpu extension providing an interface for this make it feasible?

[dneto0]

Update on Google's thinking:

• This is important, with clear use cases
• Platform support is uneven so far. HLSL's SM 6.8 is still experimental.
• We think the portability issues for subgroups also affect coopartive matrix multiplies. So we'd like to resolve subgroup portability first.