cmpgt_epu64_ssse3.cpp

#include <emmintrin.h>
#include <tmmintrin.h>

__m128i cmpgt_epu64_ssse3( __m128i a, __m128i b )
{
	// Compare uint32_t lanes for a > b and a < b
	const __m128i signBits = _mm_set1_epi32( 0x80000000 );
	a = _mm_xor_si128( a, signBits );
	b = _mm_xor_si128( b, signBits );
	__m128i gt = _mm_cmpgt_epi32( a, b );
	__m128i lt = _mm_cmpgt_epi32( b, a );

	// Shuffle bytes making two pairs of equal uint32_t values to compare.
	// Each uint32_t combines two bytes from lower and higher parts of the vectors.
	const __m128i shuffleIndices = _mm_setr_epi8(
		0, 4, -1, -1,
		0, 4, -1, -1,
		8, 12, -1, -1,
		8, 12, -1, -1 );
	gt = _mm_shuffle_epi8( gt, shuffleIndices );
	lt = _mm_shuffle_epi8( lt, shuffleIndices );
	// Make the result
	return _mm_cmpgt_epi32( gt, lt );
}