XNNPACK
XNNPACK copied to clipboard
google
High-efficiency floating-point neural network inference operators for mobile, server, and Web
to use caching of weights and use the same ordering of the matmul as in other xnnpack benchmarks. I can't test this easily for now but once the Ruy CMakeLists.txt...
Use _mm512_movepi32_mask to extract sign mask in AVX512 microkernels
![copybara-service[bot] avatar](https://avatars.githubusercontent.com/in/44061?v=4 "copybara-service[bot] avatar"){kind=avatar}
Leverage experimental i64x2.widen_(low/high)_i32x4_s WAsm SIMD instructions
Leverage experimental Sign Select WAsm SIMD instructions
Leverage experimental Extended Multiplication WAsm SIMD instructions
Leverage experimental Load-Lane WAsm SIMD instructions
Removing dependency on cpuinfo for Fuchsia builds.
Leverage experimental Load-Zero WAsm SIMD instructions
Removing dependency on cpuinfo for Fuchsia builds.
Removing dependency on cpuinfo for Fuchsia builds.