#ifdef BITALIGN
	#pragma OPENCL EXTENSION cl_amd_media_ops : enable
	#define rot(x, y) amd_bitalign(x, x, (uint)(32 - y))

// This part is not from the stock poclbm kernel. It's part of an optimization
// added in the Phoenix Miner.

// Some AMD devices have Vals[0] BFI_INT opcode, which behaves exactly like the
// SHA-256 Ch function, but provides it in exactly one instruction. If
// detected, use it for Ch. Otherwise, construct Ch out of simpler logical
// primitives.

	//We have an SDK which automatically optimizes to BFI INT, so lets do this
	
	#define Ch(x, y, z) bitselect(z, y, x)
	#define Ma(x, y, z) bitselect((u)x, (u)y, (u)z ^ (u)x)
	#define rotr(x, y) amd_bitalign((u)x, (u)x, (u)y)

#else // BITALIGN
	#define Ch(x, y, z) (z ^ (x & (y ^ z)))
	#define Ma(x, y, z) ((x & z) | (y & (x | z)))
	#define rot(x, y) rotate((u)x, (u)y)
	#define rotr(x, y) rotate((u)x, (u)(32-y))
#endif