armV8 gcc compiler auto-vectorization faster than Neon Intrinsics
Superman0307 opened this issue · comments
I am confused,why gcc auto-vectorization is faster than neon instrinsics.
I test open source code like NCNN .
C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX for x86/x64, VMX(Altivec) and VSX(Power7) for PowerPC, NEON for ARM.
Superman0307 opened this issue · comments
I am confused,why gcc auto-vectorization is faster than neon instrinsics.
I test open source code like NCNN .