Arun Etm

> 32 bit [u]intfloat conversions are indeed common. Unfortunately, I doubt many developers are aware that signed is cheaper than unsigned on x86. If they were, signed would be sufficient...

Thanks, @abrown for the numbers. Quick question, Is vp9 using i16x8.shl in the IA version of their kernel and i8x16.shl on ARM?

Agree that we have a great case for keeping byte shifts if these are useful and const shifts make the common case. @zeux do you know of any workload that...

Loads and stores are provided as v128 vector sizes by this proposal. Agree that there could be a need for float16 operations in future for these application categories. These needs...

Floating point vector rounding instructions are considered here: https://github.com/WebAssembly/simd/issues/7 Efficient implementations across platforms is a concern in exposing these.

Thanks for proposing this. FMAs are super useful, especially in AI/ML apps. This proposal can also pave way for a new class of Scalar & SIMD instructions, ie expanding to...

The details of failed CI tests appears to to inaccessible. How to view the logs?

@taste1981 please review. The update moves implementation to use AudioWorklets as discussed. The issue with mismatched sample buffer size between Audioworklet (128) and Rnnoise (>512) is resolved using a new...

Thanks for the review. I will edit the source to meet the copyright requirements and update this PR.

I suggest fingerprinting concerns should not prevent useful feature inclusion here. Being a performance extension of a performance feature, it helps if relaxed simd can prioritize perf benefits while doing...