Intel ARCHITECTURE IA-32 - Manual (Page 235)

Optimizing for SIMD Integer Applications
4
4-15
If all of the operands in a register are being replaced by a series of
pinsrw instructions, it can be useful to clear the content and break the
dependence chain by either using the pxor instruction or loading the
register. See the “Clearing Registers” section in Chapter 2.
Figure 4-6 pinsrw Instruction
Example 4-8 pinsrw Instruction Code
; Input:
; edx pointer to source value
; Output:
; mm0 register with new 16-bit value inserted
;
mov eax, [edx]
pinsrw mm0, eax, 1
O M15164
Y2
M M
R32
31 0
31 0 63
X4 X3 Y1 X1
Y1