AMD 250 manual 232, XMM3

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

imul	ecx, 2	; ECX = # quadwords of vertices to rotate
add	edi, edx	; EDI = -> end				of	"v"
add	eax, edx	; EAX	=	->	end	of	"rotv"
neg	ecx	; ECX	=	-#	quadwords of vertices to rotate

;==============================================================================

;THE 4 ASM LINES BELOW LOAD THE TRANSPOSED ROTATION MATRIX "R" INTO XMM0-XMM3

;IN THE FOLLOWING MANNER:

;xmm0 = column 0 of "R" or row 0 of "R" transpose

;xmm1 = column 1 of "R" or row 1 of "R" transpose

;xmm2 = column 2 of "R" or row 2 of "R" transpose

;xmm3 = column 3 of "R" or row 3 of "R" transpose ;==============================================================================

movaps xmm0, [esi]			; XMM0 = [R30,R20,R10,R00]
movaps xmm1, [esi+16]			; XMM1 = [R31,R21,R11,R01]
movaps	xmm2,	[esi+32]	;	XMM2	=	[R32,R22,R12,R02]
movaps	xmm3,	[esi+48]	;	XMM3	=	[R33,R23,R13,R03]

;==============================================================================

;THIS LOOP ROTATES "num_vertices_to_rotate" VERTICES BY THE TRANSPOSED

;ROTATION MATRIX "R" PASSED INTO THE ROUTINE AND STORES THE ROTATED

;VERTICES TO "rotv". ;==============================================================================

ALIGN 16		; Align address of loop to a 16-byte boundary.
rotate_vertices_loop:
movlps	xmm4, [edi+8*ecx]	; XMM4=[,,v1,v0]
movlps	xmm6, [edi+8*ecx+8]	; XMM6=[,,v3,v2]
unpcklps	xmm4, xmm4	; XMM4=[v1,v1,v0,v0]
unpcklps	xmm6, xmm6	; XMM6=[v3,v3,v2,v2]
movhlps	xmm5, xmm4	; XMM5=[,,v1,v1]
movhlps	xmm7, xmm6	; XMM7=[,,v3,v3]
movlhps	xmm4, xmm4	; XMM4=[v0,v0,v0,v0]
mulps	xmm4, xmm0	; XMM4=[R30*v0,R20*v0,R10*v0,R00*v0]
movlhps	xmm5, xmm5	; XMM5=[v1,v1,v1,v1]
mulps	xmm5, xmm1	; XMM5=[R31*v1,R21*v1,R11*v1,R01*v1]
movlhps	xmm6, xmm6	; XMM6=[v2,v2,v2,v2]
mulps	xmm6, xmm2	; XMM6=[R32*v2,R22*v2,R12*v2,R02*v2]
addps	xmm4, xmm5	; XMM4=[R30*v0+R31*v1,R20*v0+R21*v1,
		;	R10*v0+R11*v1,R00*v0+R01*v1]
movlhps	xmm7, xmm7	; XMM7=[v3,v3,v3,v3]
mulps	xmm7, xmm3	; XMM6=[R33*v3,R23*v3,R13*v3,R03*v3]
addps	xmm6, xmm7	; XMM6=[R32*v2+R33*v3,R22*v2+R23*v3,
		;	R12*v2+R13*v3,R02*v2+R03*v3]
addps	xmm4, xmm6	; XMM4=New rotated vertex
movntps	[eax+8*ecx], xmm4	; Store rotated vertex to rotv.
add	ecx, 2	; Decrement the # of QWORDs to rotate by 2.
jnz	rotate_vertices_loop
sfence		; Finish all memory writes.

;==============================================================================

;INSTRUCTIONS BELOW RESTORE THE REGISTER STATE WITH WHICH THIS ROUTINE

;WAS ENTERED

232 Optimizing with SIMD Instructions Chapter 9