AMD Typewriter x86 사용자 설명서

Replace Branches with Computation in 3DNow!™ Code

AMD Athlon™ Processor x86 Code Optimization

22007E/0—November 1999

Example 2:

C code:

float x,z;
z = abs(x);
if (z >= 1) {

z = 1/z;

}

3DNow! code:

;in: MM0 = x
;out: MM0 = z
MOVQ

MM5, mabs ;0x7fffffff

PAND

MM0, MM5 ;z=abs(x)

PFRCP

MM2, MM0 ;1/z approx

MOVQ

MM1, MM0 ;save z

PFRCPIT1 MM0, MM2 ;1/z step
PFRCPIT2 MM0, MM2 ;1/z final
PFMIN

MM0, MM1 ;z = z < 1 ? z : 1/z

Example 3:

C code:

float x,z,r,res;
z = fabs(x)
if (z < 0.575) {
res = r;
}
else {
res = PI/2 - 2*r;
}

3DNow! code:

;in: MM0 = x
;

MM1 = r

;out: MM0 = res
MOVQ MM7, mabs ;mask for absolute value
PAND MM0, MM7 ;z = abs(x)
MOVQ MM2, bnd ;0.575
PCMPGTD MM2, MM0 ;z < 0.575 ? 0xffffffff : 0
MOVQ MM3, pio2 ;pi/2
MOVQ MM0, MM1 ;save r
PFADD MM1, MM1 ;2*r
PFSUBR MM1, MM3 ;pi/2 - 2*r
PAND MM0, MM2 ;z < 0.575 ? r : 0
PANDN MM2, MM1 ;z < 0.575 ? 0 : pi/2 - 2*r
POR MM0, MM2 ;z < 0.575 ? r : pi/2 - 2 * r