MCPcopy Create free account
hub / github.com/numpy/numpy / npyv_pack_b8_b16

Function npyv_pack_b8_b16

numpy/core/src/common/simd/neon/conversion.h:91–97  ·  view source on GitHub ↗

pack two 16-bit boolean into one 8-bit boolean vector

Source from the content-addressed store, hash-verified

89
90// pack two 16-bit boolean into one 8-bit boolean vector
91NPY_FINLINE npyv_b8 npyv_pack_b8_b16(npyv_b16 a, npyv_b16 b) {
92#if defined(__aarch64__)
93 return vuzp1q_u8((uint8x16_t)a, (uint8x16_t)b);
94#else
95 return vcombine_u8(vmovn_u16(a), vmovn_u16(b));
96#endif
97}
98
99// pack four 32-bit boolean vectors into one 8-bit boolean vector
100NPY_FINLINE npyv_b8

Callers 1

npyv_pack_b8_b32Function · 0.70

Calls

no outgoing calls

Tested by

no test coverage detected