|
Uni20
Asynchronous tensor and runtime library.
|
Checked provider-ready matrix wrappers over cuBLAS GEMM. More...
#include <uni20/backend/cublas/gemm.hpp>#include <uni20/common/trace.hpp>#include <uni20/linalg/blas/blas_matrix.hpp>#include <concepts>#include <limits>Go to the source code of this file.
Namespaces | |
| namespace | uni20 |
| namespace | uni20::linalg |
| namespace | uni20::linalg::cublas |
Functions | |
| template<uni20::cublas::CublasScalar Scalar, class OutputHandle , class LhsHandle , class RhsHandle > requires std::convertible_to<OutputHandle, Scalar*> && std::convertible_to<LhsHandle, Scalar const*> && std::convertible_to<RhsHandle, Scalar const*> | |
| void | uni20::linalg::cublas::gemm (uni20::cublas::ExecutionLease &execution, blas::BlasWritableMatrix< Scalar, OutputHandle > output, Scalar alpha, blas::BlasReadableMatrix< Scalar, LhsHandle > lhs, blas::BlasReadableMatrix< Scalar, RhsHandle > rhs, Scalar beta) |
| Run provider-ready column-major GEMM through cuBLAS. | |
Checked provider-ready matrix wrappers over cuBLAS GEMM.