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

// Some AMD devices have the 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.

#ifdef BFI_INT <==== kod dla AMD
// Well, slight problem... It turns out BFI_INT isn't actually exposed to
// OpenCL (or CAL IL for that matter) in any way. However, there is
// a similar instruction, BYTE_ALIGN_INT, which is exposed to OpenCL via
// amd_bytealign, takes the same inputs, and provides the same output.
// We can use that as a placeholder for BFI_INT and have the application
// patch it after compilation.

// This is the BFI_INT function
#define Ch(x, y, z) amd_bytealign(x, y, z)

// Ma can also be implemented in terms of BFI_INT...
#define Ma(x, y, z) amd_bytealign((y), (x | z), (z & x))
#else <===== kod dla NVidii
#define Ch(x, y, z) (z ^ (x & (y ^ z)))
#define Ma(x, y, z) ((x & z) | (y & (x | z)))
#endif