_mm_broadcastss_ps, _mm256_broadcastss_ps
Take the low packed single-precision floating-point data element from the source operand and broadcast to all elements of the result vector. The corresponding Intel® AVX2 instruction is VBROADCASTSS
_mm256_broadcastsd_pd
Takes the low packed double-precision floating-point data element from the source operand and broadcast to all elements of the result vector. The corresponding Intel® AVX2 instruction is VBROADCASTSD
_mm_broadcastb_epi8, _mm256_broadcastb_epi8
Take byte elements from the source operand and broadcast to all elements of the result vector. The corresponding Intel® AVX2 instruction is VPBROADCASTB
_mm_broadcastw_epi16, _mm256_broadcastw_epi16
Take word elements from the source operand and broadcast to all elements of the result vector. The corresponding Intel® AVX2 instruction is VPBROADCASTW
_mm_broadcastd_epi32, _mm256_broadcastd_epi32
Take doublewords from the source operand and broadcast to all elements of the result vector. The corresponding Intel® AVX2 instruction is VPBROADCASTD
_mm_broadcastq_epi64, _mm256_broadcastq_epi64
Take qwords from the source operand and broadcast to all elements of the result vector. The corresponding Intel® AVX2 instruction is VPBROADCASTQ
_mm256_broadcastsi128_si256
Takes 128-bit data from the source operand and broadcasts it to all 128-bit elements of the result 256-bit vector. The corresponding Intel® AVX2 instructions are VBROADCASTI128 and VPERM2I128.