Yolanda-Chen

v8,tools: expose experimental wasm revectorize feature

7

The wasm simd256 revectorization feature is enabled by default when v8_enable_webassembly is true on x64 target in V8. At runtime it will be enabled through flag --experimental-wasm-revectorize. This PR adds...

Support qs8 5x8c8 wasmdot microkernels

1

Add 5x8c8 wasmdot kernels, as it performs better than the default configuration. Especially it will get better speedup after AVX-256 revectorization (see [chromium bug](https://issues.chromium.org/issues/42202660)) at runtime. --------------------------------------------------------------------------------------------------- |   |   --...

Add qs8 c4 microkernels for wasmsdot

1

Add qs8 c4 wasmsdot templates which can perform better than the default configuration. The new template helps generate more effecient AVX-256 revectorized code with very few inserts at run time....