Struct melior::dialect::ods::vector::FlatTransposeOperation

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

A flat_transpose operation. Vector matrix transposition on flattened 1-D MLIR vectors.

This is the counterpart of llvm.matrix.transpose in MLIR. It serves the purposes of more progressive lowering and localized type conversion. Higher levels typically lower matrix tranpositions into ‘vector.transpose’ operations. Subsequent rewriting rule progressively lower these operations into ‘vector.flat_transpose’ operations to bring the operations closer to the hardware ISA.

The vector.flat_transpose op treats the 1-D input matrix as a 2-D matrix with rows and columns, and returns the transposed matrix in flattened form in ‘res’.

Also see:

http://llvm.org/docs/LangRef.html#llvm-matrix-transpose-intrinsic

Example:

%1 = vector.flat_transpose %0 {columns = 4 : i32, rows = 4 : i32}
   : vector<16xf32> -> vector<16xf32>

Implementations

impl<'c> FlatTransposeOperation<'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> ) -> FlatTransposeOperationBuilder<'c, Unset, Unset, Unset, Unset>

Creates a builder.

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

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

pub fn rows(&self) -> Result<IntegerAttribute<'c>, Error>

pub fn set_rows(&mut self, value: IntegerAttribute<'c>)

pub fn columns(&self) -> Result<IntegerAttribute<'c>, Error>

pub fn set_columns(&mut self, value: IntegerAttribute<'c>)

Trait Implementations

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

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

Converts to this type from the input type.

impl<'c> TryFrom<Operation<'c>> for FlatTransposeOperation<'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.