msubpt

Multiply Subtract Checked Pointer

MSUBPT <Xd>, <Xn>, <Xm>, <Xa>

Calculates Ptr - (A * B) with tag check.

Pseudocode Operation

No pseudocode available.

Encoding

Binary Layout
1
31
00
30:29
11011
28:24
011
23:21
Rm
20:16
1
15
Ra
14:10
Rn
9:5
Rd
4:0
 
Format Data Processing
Opcode 0x9B608000
Extension FEAT_CPA (v9.5)

Operands

  • Xd
    Dest
  • Xn
    A
  • Xm
    B
  • Xa
    Ptr

Related

More in FEAT_CPA (v9.5)

Reference

View in Arm A64 ISA Reference ↗ Arm A64 ISA

Instruction Forms

Encoding Instruction ISA Bit pattern
0x9B608000 MSUBPT <Xd>, <Xn>, <Xm>, <Xa> A64 1 | 00 | 11011 | 011 | Rm | 1 | Ra | Rn | Rd

Description

Multiply-Subtract checked pointer multiplies two register values, subtracts the product from a third register value, and writes the result to the destination register. The intermediate product is treated as the offset. If the operation would have generated a result where the most significant 8 bits of the result register differ from the most significant 8 bits of the base register, then the result is modified such that it is likely to be non-canonical when used as an address. If the intermediate product cannot be correctly represented as a 64-bit two's complement value, then the result is modified such that it is likely to be non-canonical when used as an address.

Operation

bits(64) operand1 = X[n, 64];
bits(64) operand2 = X[m, 64];
bits(64) operand3 = X[a, 64];

bits(64) result;

integer product = SInt(operand1) * SInt(operand2);

// Signed and unsigned twos complement arithmetic are equivalent if only a
// fixed number of bits are considered.
result = operand3 - product<63:0>;
boolean overflow = (product != SInt(product<63:0>));
result = PointerMultiplyAddCheck(result, operand3, overflow);

X[d, 64] = result;