store_10x16_avx2.cpp

// Store 10-bit pieces from 16-bit lanes of the AVX2 vector, with truncation.
// The function writes 20 bytes to the pointer.
inline void store_10x16_avx2( __m256i v, uint8_t* rdi )
{
	__m256i low, high;
	// Pack pairs of 10 bits into 20
	low = _mm256_slli_epi16( v, 6 );
	v = _mm256_blend_epi16( v, low, 0b01010101 );

	// Now the vector contains 32-bit lanes with 20 payload bits / each in the middle of them
	low = _mm256_slli_epi32( v, 6 );
	high = _mm256_srli_epi32( v, 6 );
	v = _mm256_blend_epi32( high, low, 0b01010101 );
	// Now the vector contains 64-bit lanes with 40 payload bits / each in the middle of them
	// One last shift to move to lower positions.
	v = _mm256_srli_epi64( v, 12 );

	// Now the vector contains 64-bit lanes with 40 payload bits / each
	// 40 bits = 5 bytes, store initial 4 bytes of the result
	_mm_storeu_si32( rdi, _mm256_castsi256_si128( v ) );

	// Shuffle the remaining 16 bytes of payload into correct positions.
	const __m256i shuffleIndices = _mm256_setr_epi8(
		// Lower half
		4, 8, 9, 10, 11, 12,
		-1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
		// Higher half
		-1, -1, -1, -1, -1, -1,
		0, 1, 2, 3, 4,
		8, 9, 10, 11, 12
	);
	v = _mm256_shuffle_epi8( v, shuffleIndices );

	// Combine and store the final 16 bytes of payload
	const __m128i low16 = _mm256_castsi256_si128( v );
	const __m128i high16 = _mm256_extracti128_si256( v, 1 );
	const __m128i result = _mm_or_si128( low16, high16 );
	_mm_storeu_si128( ( __m128i* )( rdi + 4 ), result );
}