Tags / Equivalents
vdupq_n_bf16() on Arm 64-bit - NEON
Duplicates a scalar into every element of the destination vector.
vdupq_n_f16() on Arm 64-bit - NEON
Duplicates a scalar into every element of the destination vector.
_mm256_set1_ph() on Intel 64-bit - AVX512
Broadcast half-precision (16-bit) floating-point value "a" to all elements of "dst".
vdup_n_bf16() on Arm 64-bit - NEON
Duplicates a scalar into every element of the destination vector.
_mm512_set1_ph() on Intel 64-bit - AVX512
Broadcast half-precision (16-bit) floating-point value "a" to all elements of "dst".
_mm_set1_ph() on Intel 64-bit - AVX512
Broadcast half-precision (16-bit) floating-point value "a" to all elements of "dst".