PSUBSB          Subtract Signed with Saturation on Byte

PSUBSB destination, source                           CPU: MMX

        Logic
        mm(7..0)   <- SaturateToSignedByte (mm(7..0)   - mm/m64 (7..0) )
        mm(15..8)  <- SaturateToSignedByte (mm(15..8)  - mm/m64(15..8) )
        mm(23..16) <- SaturateToSignedByte (mm(23..16) - mm/m64(23..16))
        mm(31..24) <- SaturateToSignedByte (mm(31..24) - mm/m64(31..24))
        mm(39..32) <- SaturateToSignedByte (mm(39..32) - mm/m64(39..32))
        mm(47..40) <- SaturateToSignedByte (mm(47..40) - mm/m64(47..40))
        mm(55..48) <- SaturateToSignedByte (mm(55..48) - mm/m64(55..48))
        mm(63..56) <- SaturateToSignedByte (mm(63..56) - mm/m64(63..56))

    PSUBSB subtracts the signed bytes of the source operand from the
    signed bytes of the destination operand, and writes the results to
    the destination register.
    If the result is larger or smaller than the range of a signed byte,
    the value is saturated; in the case of an overflow - to 7Fh, and in
    the case of an underflow - to 80h.

    The destination operand is an MMX register. The source operand can
    either be an MMX register or a 64-bit memory operand. 


    Opcode      Format
    0F E8 /r    PSUBSB mm, mm/m64