AMD 250 manual Text Segment

Software Optimization Guide for AMD64 Processors 25112 Rev. 3.06 September 2005

To improve performance and substantially reduce code size, the following procedure performs the same 64-bit integer multiplication using 64-bit instead of 32-bit operations:

;64bitalu_64x64(int *a, int *b, int *c);

;TO ASSEMBLE INTO *.obj DO THE FOLLOWING:

;ml64.exe -c 64bitalu_64x64.asm

;

_TEXT SEGMENT

64bitalu_64x64 PROC NEAR ;==============================================================================

;Parameters passed into routine:

;rcx = ->a

;rdx = ->b

;r8 = ->c ;==============================================================================

mov rax, [rcx]		; RAX =		[a0]
mul [rdx]		; Multiply			[a0]	by [b0]	such that
		;	RDX:RAX		= [c1]:[c0].
mov	[r8], rax	;	Store	128-bit		product	of a and b.
mov	[r8+8], rdx

;============================================================================== ret

64bitalu_64x64 ENDP END

66 General 64-Bit Optimizations Chapter 3