kaddb
Add Masks Byte
KADDB k1, k2, k3
Adds two 8-bit mask registers.
Details
Adds two 8-bit mask registers and stores the result in a third 8-bit mask register, with write-mask control applied. The addition is performed on the full 8-bit width of each mask operand; no carry is defined beyond bit 7. No EFLAGS are modified. This instruction requires AVX-512DQ and operates only in 64-bit mode.
Pseudocode Operation
k1 ← (k2 + k3)[7:0]
Example
KADDB k1, k2, k3
Encoding
Binary Layout
EVEX
+0
0F
+4
4A
+5
Operands
-
dest
k-reg -
src1
k-reg -
src2
k-reg
Reference (Intel® SDM)
Instruction Forms
| Opcode | Instruction | Op/En | 64/32-bit Mode | CPUID | Description |
|---|---|---|---|---|---|
| VEX.L1.0F.W0 4A /r | KADDW k1, k2, k3 | V/V | RVR AVX512DQ OR AVX10.1 | Add 16 bits masks in k2 and k3 and place result in k1. | |
| VEX.L1.66.0F.W0 4A /r | KADDB k1, k2, k3 | V/V | RVR AVX512DQ OR AVX10.1 | Add 8 bits masks in k2 and k3 and place result in k1. | |
| VEX.L1.0F.W1 4A /r | KADDQ k1, k2, k3 | V/V | RVR AVX512BW OR AVX10.1 | Add 64 bits masks in k2 and k3 and place result in k1. | |
| VEX.L1.66.0F.W1 4A /r | KADDD k1, k2, k3 | V/V | RVR AVX512BW OR AVX10.1 | Add 32 bits masks in k2 and k3 and place result in k1. |
Description
Adds the vector mask k2 and the vector mask k3, and writes the result into vector mask k1.
Operation
KADDW DEST[15:0] := SRC1[15:0] + SRC2[15:0] DEST[MAX_KL-1:16] := 0 KADDB DEST[7:0] := SRC1[7:0] + SRC2[7:0] DEST[MAX_KL-1:8] := 0 KADDQ DEST[63:0] := SRC1[63:0] + SRC2[63:0] DEST[MAX_KL-1:64] := 0 KADDD DEST[31:0] := SRC1[31:0] + SRC2[31:0] DEST[MAX_KL-1:32] := 0
Intel C/C++ Compiler Intrinsic Equivalent
KADDW __mmask16 _kadd_mask16 (__mmask16 a, __mmask16 b); KADDB __mmask8 _kadd_mask8 (__mmask8 a, __mmask8 b); KADDQ __mmask64 _kadd_mask64 (__mmask64 a, __mmask64 b); KADDD __mmask32 _kadd_mask32 (__mmask32 a, __mmask32 b);
Flags Affected
None.
Exceptions
SIMD Floating-Point Exceptions
None.
KADDW/KADDB/KADDQ/KADDD—ADD Two Masks Vol. 2A 3-513
Other Exceptions
See Table 2-65, “TYPE K20 Exception Definition (VEX-Encoded OpMask Instructions w/o Memory Arg).”
KADDW/KADDB/KADDQ/KADDD—ADD Two Masks Vol. 2A 3-514