sm3partw2
SM3 Part Word 2 (A32)
SM3PARTW2.32 <Qd>, <Qn>, <Qm>
SM3 schedule update part 2.
Details
SM3 Part Word 2 performs the second part of SM3 message schedule update, completing the computation of new message schedule words from previous values. This instruction operates on three 128-bit registers and does not affect condition flags. The instruction is A32-only and requires the Crypto SM3 extension; it generates an Undefined Instruction exception if executed without the extension enabled.
Pseudocode Operation
Qd ← SM3_PARTW2(Qn, Qm)
Example
SM3PARTW2.32 q0, q1, q2
Encoding
Binary Layout
11001110011
Rm
1
1
00
01
Rn
Rd
Operands
-
Qd
Destination 128-bit SIMD register -
Qn
First source 128-bit SIMD register -
Qm
Second source 128-bit SIMD register
Reference (Arm A64 ISA)
Instruction Forms
| Encoding | Instruction | ISA | Bit pattern | ||
|---|---|---|---|---|---|
| 0xCE60C400 | SM3PARTW2 <Vd>.4S, <Vn>.4S, <Vm>.4S | A64 | 11001110011 | Rm | 1 | 1 | 00 | 01 | Rn | Rd |
Description
SM3PARTW2 takes three 128-bit vectors from three source SIMD&FP registers and returns a 128-bit result in the destination SIMD&FP register. The result is obtained by a three-way exclusive-OR of the elements within the input vectors with some fixed rotations, see the Operation pseudocode for more information.
This instruction is implemented only when FEAT_SM3 is implemented.
Operation
AArch64.CheckFPAdvSIMDEnabled(); bits(128) Vm = V[m, 128]; bits(128) Vn = V[n, 128]; bits(128) Vd = V[d, 128]; bits(128) result; bits(128) tmp; bits(32) tmp2; tmp<127:0> = Vn EOR (ROL(Vm<127:96>, 7):ROL(Vm<95:64>, 7):ROL(Vm<63:32>, 7):ROL(Vm<31:0>, 7)); result<127:0> = Vd<127:0> EOR tmp<127:0>; tmp2 = ROL(tmp<31:0>, 15); tmp2 = tmp2 EOR ROL(tmp2, 15) EOR ROL(tmp2, 23); result<127:96> = result<127:96> EOR tmp2; V[d, 128] = result;