amoxor.h

Atomic fetch-and-xor halfword

This instruction is defined by:

Encoding

svg

Synopsis

Atomically:

  • Load the halfword at address xs1

  • Write the sign-extended value into xd

  • XOR the least-significant halfword of register xs2 to the loaded value

  • Write the result to the address in xs1

Access

M HS U VS VU

Always

Always

Always

Always

Always

Decode Variables

Bits<5> xs2 = $encoding[24:20];
Bits<5> xs1 = $encoding[19:15];
Bits<5> xd = $encoding[11:7];

Execution

  • Pruned, XLEN == 64

  • Original

XReg virtual_address = X[xs1];
X[xd] = sext(amo(16, virtual_address, X[xs2][15:0], AmoOperation::Xor, 1'b0, 1'b0, $encoding), 16);
XReg virtual_address = X[xs1];
X[xd] = sext(amo(16, virtual_address, X[xs2][15:0], AmoOperation::Xor, 1'b0, 1'b0, $encoding), 16);

Exceptions

This instruction may result in the following synchronous exceptions:

  • LoadAccessFault

  • StoreAmoAccessFault

  • StoreAmoAddressMisaligned

  • StoreAmoPageFault