Intel ITANIUM ARCHITECTURE - SOFTWARE DEVELOPERS MANUAL VOLUME 1 REV 2.3 Manual page 1712

Hide thumbs Also See for ITANIUM ARCHITECTURE - SOFTWARE DEVELOPERS MANUAL VOLUME 1 REV 2.3:
Table of Contents

Advertisement

PADDB/PADDW/PADDD—Packed Add
Opcode
0F FC /r
0F FD /r
0F FE /r
Description
Adds the individual data elements (bytes, words, or doublewords) of the source
operand (second operand) to the individual data elements of the destination operand
(first operand). (See
range for the specified data type (overflows), the result is wrapped around, meaning
that the result is truncated so that only the lower (least significant) bits of the result are
returned (that is, the carry is ignored).
The destination operand must be an MMX technology register; the source operand can
be either an MMX technology register or a quadword memory location.
Figure 3-5.
mm
mm/m64
mm
The PADDB instruction adds the bytes of the source operand to the bytes of the
destination operand and stores the results to the destination operand. When an
individual result is too large to be represented in 8 bits, the lower 8 bits of the result
are written to the destination operand and therefore the result wraps around.
The PADDW instruction adds the words of the source operand to the words of the
destination operand and stores the results to the destination operand. When an
individual result is too large to be represented in 16 bits, the lower 16 bits of the result
are written to the destination operand and therefore the result wraps around.
The PADDD instruction adds the doublewords of the source operand to the doublewords
of the destination operand and stores the results to the destination operand. When an
individual result is too large to be represented in 32 bits, the lower 32 bits of the result
are written to the destination operand and therefore the result wraps around.
4:410
Instruction
PADDB mm, mm/m64
PADDW mm, mm/m64
PADDD mm, mm/m64
Figure
3-5.) If the result of an individual addition exceeds the
Operation of the PADDW Instruction
PADDW mm, mm/m64
+
Description
Add packed bytes from mm/m64 to packed bytes in mm .
Add packed words from mm/m64 to packed words in mm .
Add packed doublewords from mm/m64 to packed
doublewords in mm .
1000000000000000
+
+
1111111111111111
0111111111111111
®
Volume 4: IA-32 Intel
MMX™ Technology Instruction Reference
0111111100111000
+
0001011100000111
1001011000111111
3006015

Advertisement

Table of Contents
loading

This manual is also suitable for:

Itanium architecture 2.3

Table of Contents