Minimum number of copies from Uint8Array to wgpu::Buffer

[FL33TW00D]

Currently in wgpu, there is no way to create a wgpu::Buffer directly from Uint8Array.

This means that our tensor data does something like this:

IndexedDB -> Uint8Array -> Vec<u8> ~~> Uint8Array -> WebGPU

Judging by this: https://developer.mozilla.org/en-US/docs/Web/API/GPUBuffer

I think the optimal is:

IndexedDB -> Uint8Array -> WebGPU

Reference: https://github.com/gfx-rs/wgpu/blob/trunk/wgpu/src/backend/webgpu.rs#L1821

[sigma-andex]

If we store the webgpu aligned Uint8Array, can't we just pass it through when loading?

[FL33TW00D]

@sigma-andex There is just no way to provide a Uint8Array to wgpu as of now, we need to add it

[ikorin24]

Hi, I am also interested in this issue.

I found a method wgpu::BufferSlice::get_mapped_range_as_array_buffer.
It seems to be available only in the webgpu feature. Would this be of any help to you?

[FL33TW00D]

wgpu::BufferSlice::get_mapped_range_as_array_buffer

@ikorin24 It looks like that method was added in this PR: gfx-rs/wgpu#4042

It seems to help only in the other direction (i.e getting data from WebGPU land -> JS land with less copies). We need the other direction to be added!