takahiroharada / oclradixsort Goto Github PK

void sort4Bits1(u32 sortData[4], int startBit, int lIdx, __local u32* ldsSortData)
{
	for(uint ibit=0; ibit<BITS_PER_PASS; ibit+=2)
	{
		uint4 b = make_uint4((sortData[0]>>(startBit+ibit)) & 0x3, 
			(sortData[1]>>(startBit+ibit)) & 0x3, 
			(sortData[2]>>(startBit+ibit)) & 0x3, 
			(sortData[3]>>(startBit+ibit)) & 0x3);

		u32 key4;
		u32 sKeyPacked[4] = { 0, 0, 0, 0 };
		{
			sKeyPacked[0] |= 1<<(8*b.x);
			sKeyPacked[1] |= 1<<(8*b.y);
			sKeyPacked[2] |= 1<<(8*b.z);
			sKeyPacked[3] |= 1<<(8*b.w);

			key4 = sKeyPacked[0] + sKeyPacked[1] + sKeyPacked[2] + sKeyPacked[3];
		}

		u32 rankPacked;
		u32 sumPacked;
		{
			rankPacked = localPrefixSum( key4, lIdx, &sumPacked, ldsSortData, WG_SIZE );
		}

		GROUP_LDS_BARRIER;

		u32 newOffset[4] = { 0,0,0,0 };
		{
			u32 sumScanned = bit8Scan( sumPacked );