Function core::arch::x86_64::_mm_clmulepi64_si128

pub unsafe fn _mm_clmulepi64_si128<const IMM8: i32>(
    a: __m128i, 
    b: __m128i
) -> __m128i

This is supported on x86-64 and target feature pclmulqdq only.

Performs a carry-less multiplication of two 64-bit polynomials over the finite field GF(2^k).

The immediate byte is used for determining which halves of a and b should be used. Immediate bits other than 0 and 4 are ignored.

Intel’s documentation