Enum RmwOp 

pub enum RmwOp {
    Add,
    Sub,
    Mul,
    And,
    Or,
    Xor,
    AddF,
    SubF,
    MulF,
}

The operation of a fused read-modify-write MicroOp::ArrRMW: buf[idx-1] = buf[idx-1] <op> operand. The INT ops (Add/Sub/Mul wrap as the kernel’s i64 arithmetic; And/Or/Xor bitwise) treat the element and operand as raw i64; the FLOAT ops (AddF/SubF/MulF) reinterpret both as f64 (the nbody velocity/position-update idiom). Sub/SubF are the only non-commutative members — the peephole fuses them only when the loaded element is the LEFT operand.

Variants

Add

Wrapping addition.

Sub

Wrapping subtraction (buf[i] - operand).

Mul

Wrapping multiplication.

And

Bitwise AND.

Or

Bitwise OR.

Xor

Bitwise XOR.

AddF

IEEE addition (operands reinterpreted as f64).

SubF

IEEE subtraction (buf[i] - operand, as f64).

MulF

IEEE multiplication (as f64).

Implementations

impl RmwOp

pub fn is_float(self) -> bool

Whether the op reinterprets its operands as f64.

pub fn eval(self, a: i64, b: i64) -> i64

Apply over the raw i64 bits of the element and operand — the bit-exact spec every stencil must match. Float ops reinterpret the bits as f64, compute, and re-encode (copy-and-patch never reassociates, so ordering is exact).

Trait Implementations

impl Clone for RmwOp

fn clone(&self) -> RmwOp

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for RmwOp

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for RmwOp

fn eq(&self, other: &RmwOp) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for RmwOp

impl Eq for RmwOp

impl StructuralPartialEq for RmwOp