matrix_product.hpp File Reference

Tensor-level matrix product update and overwrite operations. More...

#include <uni20/common/trace.hpp>
#include <uni20/linalg/matrix_product_shape.hpp>
#include <uni20/linalg/ops/gemm.hpp>
#include <uni20/mdspan/mdspan.hpp>
#include <uni20/tensor/output.hpp>
#include <concepts>
#include <memory>
#include <type_traits>
#include <utility>

Include dependency graph for ops/matrix_product.hpp:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Namespaces
namespace	uni20
namespace	uni20::linalg

Functions
template<MutableRankedTensorView< 2 > Output, RankedTensorView< 2 > A, RankedTensorView< 2 > B, class Alpha > requires detail::CompatibleMatrixProductTensors<Output, A, B> && OperationScalar<Alpha, tensor_element_t<Output>>
void	uni20::linalg::add_product (Output &&output, A const &a, B const &b, Alpha const &alpha, std::optional< Precision > p={})
	Apply add_product using the storage-selected backend.
template<MutableRankedTensorView< 2 > Output, RankedTensorView< 2 > A, RankedTensorView< 2 > B> requires detail::CompatibleMatrixProductTensors<Output, A, B>
void	uni20::linalg::add_product (Output &&output, A const &a, B const &b, std::optional< Precision > p={})
	Apply unit-coefficient add_product using storage-selected backends.
template<KernelBackendSelector Selector, MutableRankedTensorView< 2 > Output, RankedTensorView< 2 > A, RankedTensorView< 2 > B, class Alpha > requires detail::CompatibleMatrixProductTensors<Output, A, B> && OperationScalar<Alpha, tensor_element_t<Output>>
void	uni20::linalg::add_product (Selector &&selector, Output &&output, A const &a, B const &b, Alpha const &alpha, std::optional< Precision > requested={})
	Accumulate alpha * a * b into an existing fixed-shape output.
template<KernelBackendSelector Selector, MutableRankedTensorView< 2 > Output, RankedTensorView< 2 > A, RankedTensorView< 2 > B> requires detail::CompatibleMatrixProductTensors<Output, A, B>
void	uni20::linalg::add_product (Selector &&selector, Output &&output, A const &a, B const &b, std::optional< Precision > p={})
	Apply add_product with an exact unit coefficient and optional precision.
template<MutableRankedTensorView< 2 > Output, RankedTensorView< 2 > A, RankedTensorView< 2 > B, class Alpha > requires detail::CompatibleMatrixProductTensors<Output, A, B> && OperationScalar<Alpha, tensor_element_t<Output>>
void	uni20::linalg::assign_product (Output &&output, A const &a, B const &b, Alpha const &alpha, std::optional< Precision > p={})
	Apply assign_product using the storage-selected backend.
template<MutableRankedTensorView< 2 > Output, RankedTensorView< 2 > A, RankedTensorView< 2 > B> requires detail::CompatibleMatrixProductTensors<Output, A, B>
void	uni20::linalg::assign_product (Output &&output, A const &a, B const &b, std::optional< Precision > p={})
	Apply unit-coefficient assign_product using storage-selected backends.
template<KernelBackendSelector Selector, MutableRankedTensorView< 2 > Output, RankedTensorView< 2 > A, RankedTensorView< 2 > B, class Alpha > requires detail::CompatibleMatrixProductTensors<Output, A, B> && OperationScalar<Alpha, tensor_element_t<Output>>
void	uni20::linalg::assign_product (Selector &&selector, Output &&output, A const &a, B const &b, Alpha const &alpha, std::optional< Precision > requested={})
	Overwrite a resizable or already-compatible output with alpha * a * b.
template<KernelBackendSelector Selector, MutableRankedTensorView< 2 > Output, RankedTensorView< 2 > A, RankedTensorView< 2 > B> requires detail::CompatibleMatrixProductTensors<Output, A, B>
void	uni20::linalg::assign_product (Selector &&selector, Output &&output, A const &a, B const &b, std::optional< Precision > p={})
	Apply assign_product with an exact unit coefficient and optional precision.

Detailed Description

Tensor-level matrix product update and overwrite operations.