Enum TensorEvent 

#[repr(u8)]
pub enum TensorEvent {
    Load0 = 0,
    Load1 = 1,
    Fma = 7,
    Store = 8,
}

Tensor co-processor synchronisation events for tensor_wait.

The four-bit EVENT field in the TensorWait xs register selects which outstanding operation the hart waits for before the instruction retires.

Variants

Load0 = 0

Completion of all TensorLoad operations issued with ID = 0.

Load1 = 1

Completion of all TensorLoad operations issued with ID = 1.

Fma = 7

Completion of all preceding TensorFMA operations; the FP register file holds the final accumulated C tile and may be read or stored.

Store = 8

Completion of all preceding TensorStore DMA transfers (PRM Table 9-2, event code 8). Drains only the tensor store DMA, allowing the compiler more freedom to reorder non-tensor memory accesses around it. Prefer this over a full fence rw, rw when only tensor-store ordering is required (e.g. confirming one tile is written before reusing FP registers for the next tile in a pipelined loop).

Trait Implementations

impl Clone for TensorEvent

fn clone(&self) -> TensorEvent

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for TensorEvent

impl Debug for TensorEvent

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

Formats the value using the given formatter.

impl Eq for TensorEvent

impl PartialEq for TensorEvent

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for TensorEvent