gemv_batched_strided.h File Reference

#include "cutlass/cutlass.h"
#include "cutlass/aligned_buffer.h"
#include "cutlass/array.h"
#include "cutlass/numeric_types.h"
#include "cutlass/matrix_shape.h"
#include "cutlass/gemm/gemm.h"

Include dependency graph for gemv_batched_strided.h:

Go to the source code of this file.

Classes
struct	cutlass::gemm::kernel::detail::GemvBatchedStridedEpilogueScaling< ElementAlphaBeta, BetaIsZero >

Namespaces
	cutlass
	cutlass::gemm
	cutlass::gemm::kernel
	cutlass::gemm::kernel::detail

Functions
template<typename GemvKernel , typename ElementAlphaBeta , bool BetaIsZero = false>
CUTLASS_DEVICE void	cutlass::gemm::kernel::GemvBatchedStridedDevice (cutlass::gemm::BatchedGemmCoord problem_size, ElementAlphaBeta alpha, ElementAlphaBeta beta, typename GemvKernel::IteratorA::TensorRef ref_A, typename GemvKernel::IteratorA::TensorRef::LongIndex lda, typename GemvKernel::IteratorB::TensorRef ref_B, typename GemvKernel::IteratorB::TensorRef::LongIndex ldb, typename GemvKernel::IteratorCD::TensorRef ref_C, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldc, typename GemvKernel::IteratorCD::TensorRef ref_D, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldd)
template<typename GemvKernel , typename ElementAlphaBeta , bool BetaIsZero>
__global__ void	cutlass::gemm::kernel::GemvBatchedStrided (cutlass::gemm::BatchedGemmCoord problem_size, ElementAlphaBeta alpha, ElementAlphaBeta beta, typename GemvKernel::IteratorA::TensorRef ref_A, typename GemvKernel::IteratorA::TensorRef::LongIndex lda, typename GemvKernel::IteratorB::TensorRef ref_B, typename GemvKernel::IteratorB::TensorRef::LongIndex ldb, typename GemvKernel::IteratorCD::TensorRef ref_C, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldc, typename GemvKernel::IteratorCD::TensorRef ref_D, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldd)
template<typename GemvKernel , typename ElementAlphaBeta >
__global__ void	cutlass::gemm::kernel::GemvBatchedStrided (cutlass::gemm::BatchedGemmCoord problem_size, ElementAlphaBeta alpha, typename GemvKernel::IteratorA::TensorRef ref_A, typename GemvKernel::IteratorA::TensorRef::LongIndex lda, typename GemvKernel::IteratorB::TensorRef ref_B, typename GemvKernel::IteratorB::TensorRef::LongIndex ldb, typename GemvKernel::IteratorCD::TensorRef ref_D, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldd)
template<typename GemvKernel >
__global__ void	cutlass::gemm::kernel::GemvBatchedStrided (cutlass::gemm::BatchedGemmCoord problem_size, typename GemvKernel::IteratorA::TensorRef ref_A, typename GemvKernel::IteratorA::TensorRef::LongIndex lda, typename GemvKernel::IteratorB::TensorRef ref_B, typename GemvKernel::IteratorB::TensorRef::LongIndex ldb, typename GemvKernel::IteratorCD::TensorRef ref_D, typename GemvKernel::IteratorCD::TensorRef::LongIndex ldd)