cutlass::gemm::threadblock Namespace Reference

Namespaces
	detail

Classes
struct	DefaultGemvCore
struct	DefaultMma
struct	DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::ColumnMajorInterleaved< InterleavedK >, OperatorClass, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, true >
	Specialization for column-major-interleaved output. More...
struct	DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, false >
	Specialization for row-major output (OperatorClass Simt) More...
struct	DefaultMma< ElementA, LayoutA, kAlignmentA, ElementB, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassTensorOp, ArchTag, ThreadblockShape, WarpShape, InstructionShape, 2, Operator, false >
	Specialization for row-major output (OperatorClass Simt) More...
struct	DefaultMma< int8_t, LayoutA, kAlignmentA, int8_t, LayoutB, kAlignmentB, ElementAccumulator, layout::RowMajor, arch::OpClassSimt, ArchTag, ThreadblockShape, WarpShape, GemmShape< 1, 1, 4 >, 2, Operator, false >
struct	DefaultMmaCore
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_, >
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 1 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >
	Partial specialization: More...
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::ColumnMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >
	Partial specialization: More...
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 1, 1, 4 >, int8_t, layout::RowMajor, int8_t, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassSimt, 2, Operator_ >
	Partial specialization: More...
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, GemmShape< 8, 8, 4 >, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::ColumnMajorInterleaved< InterleavedK >, ElementB_, layout::RowMajorInterleaved< InterleavedK >, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_, AccumulatorsInRowMajor >
struct	DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::ColumnMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	DefaultMmaCore< Shape_, WarpShape_, InstructionShape_, ElementA_, layout::RowMajor, ElementB_, layout::RowMajor, ElementC_, LayoutC_, arch::OpClassTensorOp, 2, Operator_ >
struct	GemmBatchedIdentityThreadblockSwizzle
	Threadblock swizzling function for batched GEMMs. More...
struct	GemmHorizontalThreadblockSwizzle
	Threadblock swizzling function for GEMMs. More...
struct	GemmIdentityThreadblockSwizzle
	Threadblock swizzling function for GEMMs. More...
struct	GemmSplitKHorizontalThreadblockSwizzle
	Threadblock swizzling function for split-K GEMMs. More...
struct	GemmSplitKIdentityThreadblockSwizzle
	Threadblock swizzling function for split-K GEMMs. More...
class	Gemv
	Structure to compute the matrix-vector product using SIMT math instructions. More...
struct	GemvBatchedStridedThreadblockDefaultSwizzle
	Threadblock swizzling function for batched GEMVs. More...
class	MmaBase
class	MmaPipelined
	Structure to compute the matrix product targeting CUDA cores and SIMT math instructions. More...
struct	MmaPolicy
	Policy object describing MmaTensorOp. More...
class	MmaSingleStage
	Structure to compute the matrix product targeting CUDA cores and SIMT math instructions. More...

Functions
CUTLASS_DEVICE int	RematerializeThreadIdxX ()
	Helper to rematerialize block Idx. Reduces register liveness. More...
CUTLASS_DEVICE int	RematerializeThreadIdxY ()
	Helper to rematerialize block Idx. Reduces register liveness. More...
CUTLASS_DEVICE int	RematerializeThreadIdxZ ()
	Helper to rematerialize block Idx. Reduces register liveness. More...
CUTLASS_DEVICE int	RematerializeBlockIdxX ()
	Helper to rematerialize block Idx. Reduces register liveness. More...
CUTLASS_DEVICE int	RematerializeBlockIdxY ()
	Helper to rematerialize block Idx. Reduces register liveness. More...
CUTLASS_DEVICE int	RematerializeBlockIdxZ ()
	Helper to rematerialize block Idx. Reduces register liveness. More...
CUTLASS_DEVICE int	RematerializeBlockDimX ()
	Helper to rematerialize block Dim. Reduces register liveness. More...
CUTLASS_DEVICE int	RematerializeBlockDimY ()
	Helper to rematerialize block Dim. Reduces register liveness. More...
CUTLASS_DEVICE int	RematerializeBlockDimZ ()
	Helper to rematerialize block Dim. Reduces register liveness. More...

Function Documentation

CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockDimX

(

)

CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockDimY

(

)

CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockDimZ

(

)

CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockIdxX

(

)

CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockIdxY

(

)

CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeBlockIdxZ

(

)

CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeThreadIdxX

(

)

CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeThreadIdxY

(

)

CUTLASS_DEVICE int cutlass::gemm::threadblock::RematerializeThreadIdxZ

(

)