Struct melior::dialect::ods::gpu::SubgroupMmaComputeOperation

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

A subgroup_mma_compute operation. GPU warp synchronous matrix multiply accumulate.

The gpu.subgroup_mma_compute operation performs a matrix-multiply accumulate (mma) operation using all the threads in a subgroup.

This operation takes three !gpu.mma_matrixs as arguments: these hold A, B and Coperands for the mma operation. The operation performed is represented as C += A * B. The op returns a !gpu.mma_matrix which contains the result of the operation held by all threads in a subgroup. a_transpose or b_transpose if present, signify that the respective operand was loaded in a transposed manner. The transpose operands are required to map to correct underlying intrisics but they currently do not seem to affect correctness even if they are absent given that the operands were loaded correctly using the transpose attribute in gpu.subgroup_mma_load_matrix op.

For integer types, the A and B matrices carry their signedness with their types. The accumulator type is expected to be signless and imply a signed integer with a greater width than the other two operands.

This op is meant to be used along with gpu.subgroup_mma_store_matrix and gpu.subgroup_mma_load_matrix ops.

Example:

%D = gpu.subgroup_mma_compute_matrix %A, %B, %C :
  !gpu.mma_matrix<16x16xf16, "AOp">, !gpu.mma_matrix<16x16xf16, "BOp">>
  -> !gpu.mma_matrix<16x16xf16, "COp">

Implementations

impl<'c> SubgroupMmaComputeOperation<'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> ) -> SubgroupMmaComputeOperationBuilder<'c, Unset, Unset, Unset, Unset>

Creates a builder.

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

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

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

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

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

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

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

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

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

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

Trait Implementations

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

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

Converts to this type from the input type.

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