Err, maybe I'm missing something, but if developers writing for wasm have to think about whether the target has SSEx (specifically) or Neon (specifically) we're doing things terribly wrong. The only target they should need to check for is whether the *wasm* engine supports wasm-simd128, and target that; if developers need to detect for underlying implementation details, that should be a huuuuuge red flag. (I'd argue that even being *able* to detect the underlying SIMD architecture from wasm-land is a bad idea, lest people try to game their current compiler to squeak out marginal performance improvements based on that.)
> Developers want to be able to write page_sse.wasm and > page_neon.wasm files and feature check to run the appropriate one > depending on the target. (and they also want to be able to write > page_simd.wasm that simultaneously targets both sse and neon) But > there is some hope to introduce proper SSE* instruction sets in a > future revision of the WebAssembly SIMD v2 or similar. > -- You received this message because you are subscribed to the Google Groups "emscripten-discuss" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/emscripten-discuss/CAM%3DdnvfH2cGQzMLzrRZUPH7xGBA-hddbuceZ%3DRp4BTxA0U8LzQ%40mail.gmail.com.
