Agam Brahma
This is the second post in a series on Driftwood, a runtime for stateful Wasm actors with hardware-accelerated inference on Apple Silicon. The first post covered the zero-copy GPU path: that a Wasm actor's linear memory can be shared with the GPU without copying. This one covers a different...
Agam Brahma
tl;dr: on Apple Silicon, a WebAssembly module's linear memory can be shared directly with the GPU: no copies, no serialization, no intermediate buffers. The CPU and GPU read and write the same physical bytes. End-to-end, it works: a Wasm guest fills a matrix in its linear memory, the GPU reads it,...
M.G. Siegler
Reading between the lines of the ‘Scary Fast’ event…A flurry of Apple news, reports, and rumors hit in the past week — so much so that it’s hard to keep up. But you do have to wonder if many of them are related, hence the timing. If so, it likely all centers around the just-announced “Scary Fast”...