Struct melior::dialect::ods::vector::TransferWriteOperation

pub struct TransferWriteOperation<'c> { /* private fields */ }

A transfer_write operation. The vector.transfer_write op writes a supervector to memory..

The vector.transfer_write op performs a write from a vector, supplied as its first operand, into a slice within a MemRef or a Ranked Tensor of the same base elemental type, supplied as its second operand.

A vector memref/tensor operand must have its vector element type match a suffix (shape and element type) of the vector (e.g. memref<3x2x6x4x3xf32>, vector<1x1x4x3xf32>). If the operand is a tensor, the operation returns a new tensor of the same type.

The slice is further defined by a full-rank index within the MemRef/Tensor, supplied as the operands [2 .. 2 + rank(memref/tensor)) that defines the starting point of the transfer (e.g. %A[%i0, %i1, %i2, %i3]).

The permutation_map attribute is an affine-map which specifies the transposition on the slice to match the vector shape. The permutation map may be implicit and omitted from parsing and printing if it is the canonical minor identity map (i.e. if it does not permute any dimension). In contrast to transfer_read, write ops cannot have broadcast dimensions.

The size of the slice is specified by the size of the vector.

An optional SSA value mask may be specified to mask out elements written to the MemRef/Tensor. The mask type is an i1 vector with a shape that matches how elements are written into the MemRef/Tensor, after applying any permutation. Elements whose corresponding mask element is 0 are masked out.

An optional SSA value mask of the same shape as the vector type may be specified to mask out elements. Elements whose corresponding mask element is 0 are masked out.

An optional boolean array attribute in_bounds specifies for every vector dimension if the transfer is guaranteed to be within the source bounds. While the starting point of the transfer has to be in-bounds, accesses may run out-of-bounds as indices increase. If specified, the in_bounds array length has to be equal to the vector rank. In absence of the attribute, accesses along all dimensions may run out-of-bounds. A vector.transfer_write can be lowered to a simple store if all dimensions are specified to be within bounds and no mask was specified.

This operation is called ‘write’ by opposition to ‘store’ because the super-vector granularity is generally not representable with a single hardware register. A vector.transfer_write is thus a mid-level abstraction that supports super-vectorization with non-effecting padding for full-tile-only code. It is the responsibility of vector.transfer_write’s implementation to ensure the memory writes are valid. Different lowerings may be pertinent depending on the hardware support.

Example:

// write vector<16x32x64xf32> into the slice
//   `%A[%i0, %i1:%i1+32, %i2:%i2+64, %i3:%i3+16]`:
for %i0 = 0 to %0 {
  affine.for %i1 = 0 to %1 step 32 {
    affine.for %i2 = 0 to %2 step 64 {
      affine.for %i3 = 0 to %3 step 16 {
        %val = `ssa-value` : vector<16x32x64xf32>
        vector.transfer_write %val, %A[%i0, %i1, %i2, %i3]
          {permutation_map: (d0, d1, d2, d3) -> (d3, d1, d2)} :
          vector<16x32x64xf32>, memref<?x?x?x?xf32>
}}}}

// or equivalently (rewrite with vector.transpose)
for %i0 = 0 to %0 {
  affine.for %i1 = 0 to %1 step 32 {
    affine.for %i2 = 0 to %2 step 64 {
      affine.for %i3 = 0 to %3 step 16 {
        %val = `ssa-value` : vector<16x32x64xf32>
        %valt = vector.transpose %val, [1, 2, 0] :
              vector<16x32x64xf32> -> vector<32x64x16xf32>
        vector.transfer_write %valt, %A[%i0, %i1, %i2, %i3]
          {permutation_map: (d0, d1, d2, d3) -> (d1, d2, d3)} :
          vector<32x64x16xf32>, memref<?x?x?x?xf32>
}}}}

// write to a memref with vector element type.
vector.transfer_write %4, %arg1[%c3, %c3]
  {permutation_map = (d0, d1)->(d0, d1)}
    : vector<1x1x4x3xf32>, memref<?x?xvector<4x3xf32>>

// return a tensor where the vector is inserted into the source tensor.
%5 = vector.transfer_write %4, %arg1[%c3, %c3]
  {permutation_map = (d0, d1)->(d0, d1)}
    : vector<1x1x4x3xf32>, tensor<?x?xvector<4x3xf32>>

// Special encoding for 0-d transfer with 0-d tensor/memref, vector shape
// {1} and permutation_map () -> (0).
%1 = vector.transfer_write %0, %arg0[] {permutation_map = affine_map<()->(0)>} :
  vector<1xf32>, tensor<f32>

Implementations

impl<'c> TransferWriteOperation<'c>

pub fn name() -> &'static str

Returns a name.

pub fn as_operation(&self) -> &Operation<'c>

Returns a generic operation.

pub fn builder( context: &'c Context, location: Location<'c> ) -> TransferWriteOperationBuilder<'c, Unset, Unset, Unset, Unset>

Creates a builder.

pub fn result(&self) -> Result<OperationResult<'c, '_>, Error>

pub fn vector(&self) -> Result<Value<'c, '_>, Error>

pub fn source(&self) -> Result<Value<'c, '_>, Error>

pub fn indices(&self) -> Result<impl Iterator<Item = Value<'c, '_>>, Error>

pub fn mask(&self) -> Result<Value<'c, '_>, Error>

pub fn permutation_map(&self) -> Result<Attribute<'c>, Error>

pub fn set_permutation_map(&mut self, value: Attribute<'c>)

pub fn in_bounds(&self) -> Result<ArrayAttribute<'c>, Error>

pub fn set_in_bounds(&mut self, value: ArrayAttribute<'c>)

pub fn remove_in_bounds(&mut self) -> Result<(), Error>

Trait Implementations

impl<'c> From<TransferWriteOperation<'c>> for Operation<'c>

fn from(operation: TransferWriteOperation<'c>) -> Self

Converts to this type from the input type.

impl<'c> TryFrom<Operation<'c>> for TransferWriteOperation<'c>

type Error = Error

The type returned in the event of a conversion error.

fn try_from(operation: Operation<'c>) -> Result<Self, Self::Error>

Performs the conversion.