inline size_t BMat16::nr_rows() const noexcept {
[...]
//// Vectorized version which doesn't work due to the absence of popcnt in
/// simde
// xpu16 tmp = _data, zero = simde_mm256_setzero_si256();
// xpu16 x = (tmp != zero);
// return simde_mm256_popcnt_epi16(x);
}
As soon as popcnt is implemented in simde