Browse the source code of
pytorch
/
pytorch
/
third_party
/
nvfuser
/
csrc/
online
../
arith.cpp
arith.h
WelfordResult
codegen.cpp
codegen.h
compute_at.cpp
ComputeAtSelector
compute_at.h
ComputeAt
compute_at_map.cpp
compute_at_map.h
ComputeAtMap
IterDomainGraph
contiguity.cpp
contiguity.h
ContigIDs
NonDivisibleSplitDependencies
OrderedIdInformation
disjoint_set.h
DisjointSets
VectorOfUniqueEntries
dispatch.cpp
dispatch.h
OptInConstDispatch
OptInDispatch
OptOutConstDispatch
OptOutDispatch
OptOutMutator
dynamic_type.h
IntOrDouble
evaluator_common.cpp
PrecomputedValuesBase
evaluator_common.h
FusionIRContext
FusionPrecomputedValues
KernelIRContext
KernelPrecomputedValues
NaiveValueMachine
PrecomputedValuesBase
executor.cpp
executor.h
CompileOptions
FusionExecutor
executor_kernel_arg.cpp
executor_kernel_arg.h
ArgAbstract
ArgType
BoolArg
ComplexDoubleArg
CpuScalarTensorArg
CpuScalarTensorCodegen
DoubleArg
KernelArgumentHolder
LongArg
PhiloxCudaStateArg
TensorArg
TensorArgAbstract
TensorArgCodegen
executor_launch_params.cpp
executor_launch_params.h
LaunchParams
executor_utils.cpp
CompileTimeInfo
ExecutorCompileTimeEntry
executor_utils.h
NvrtcFunction
CompileTimeEntryType
CompileTimeInfoBase
ExecutorCompileTimeEntry
ExecutorCompileTimeInfoCache
InputAliasIndices
OutputAliasIndices
ParallelBindingIterDomains
ParallelIterExtentMap
SimplifiedParallelIterExtentMap
VectorizedTensorInfo
VectorizedTensorValidation
WarpPaddedExtentsInfo
WarpPaddedParallelExtents
expr_evaluator.cpp
expr_evaluator.h
ExpressionEvaluator
fusion.cpp
fusion.h
Fusion
FusionGuard
fusion_segmenter.cpp
CombineReductions
GroupDependencyAnalysis
TranslateApplicableWelford
fusion_segmenter.h
FusionHeuristics
SegmentCandidateFinder
SegmentCandidateFinderOptions
SegmentedEdge
SegmentedFusion
SegmentedGroup
SegmenterAnalysis
graph_fuser.cpp
grouped_reduction.cpp
grouped_reduction.h
index_compute.cpp
index_compute.h
Index
IndexCompute
IndexSwizzle
RootPredicateInfo
inlining.cpp
inlining.h
MaxPosCalculator
instrumentation.cpp
instrumentation.h
Trace
TraceScope
ir_all_nodes.h
ir_base_nodes.cpp
ir_base_nodes.h
Expr
ExprPasskey
Statement
Val
ir_builder.cpp
ir_builder.h
IrBuilder
IrBuilderPasskey
SimplifyingIrBuilder
ir_cloner.cpp
ir_cloner.h
IrCloner
RecomputeTv
ir_container.cpp
ir_container.h
IrContainer
IrContainerPasskey
ir_graphviz.cpp
ir_graphviz.h
IrGraphGenerator
ir_interface_nodes.h
Bool
ComplexDouble
ComputeAtMode
Double
Int
TensorView
TensorViewBuilder
ir_internal_nodes.h
ARangeOp
BinaryOp
BroadcastOp
ExpandOp
EyeOp
FullOp
GatherOp
GroupedReductionOp
GroupedWelfordOp
IterDomain
IterDomainBuilder
LoadStoreOp
Merge
MmaOp
NamedScalar
RNGOp
ReductionOp
ShiftOp
Split
Swizzle2D
TensorDomain
TernaryOp
TransposeOp
UnaryOp
ViewAsScalar
ViewOp
WelfordOp
WelfordTriplet
ir_iostream.cpp
ir_iostream.h
IrPrinter
ir_nodes.cpp
ir_printer.h
IrMathPrinter
IrTransformPrinter
ir_utils.cpp
SubstituteInExpr
ir_utils.h
FilterIterator
FilteredView
iter_visitor.cpp
iter_visitor.h
BackwardVisitor
DependencyCheck
InputsOf
IterVisitor
StmtSort
kernel.cpp
kernel.h
Kernel
KernelInternalProxy
KernelPerformanceProfile
KernelSummary
kernel_cache.cpp
kernel_cache.h
ExecutorLog
FusionExecutorCache
FusionKernelRuntime
GraphCache
InputsIdLookup
kernel_expr_evaluator.cpp
kernel_expr_evaluator.h
ExpressionEvaluator
kernel_ir.cpp
kernel_ir.h
Allocate
AllocateFusedReduction
BlockSync
CpAsyncCommit
CpAsyncWait
ForLoop
GridBroadcast
GridReduction
GridSync
GridWelford
GroupedGridReduction
GroupedGridWelford
IfThenElse
InitMagicZero
IntPair
PairSelect
Predicate
Scope
Swizzle2DInt
TensorIndex
UpdateMagicZero
kernel_ir_dispatch.cpp
kernel_ir_dispatch.h
ConstIrVisitor
ExprMutator
IrVisitor
lower2device.cpp
lower2device.h
GpuLower
lower_alias_memory.cpp
lower_alias_memory.h
lower_allocation.cpp
lower_allocation.h
LocalAllocationInfo
lower_bank_conflict.cpp
lower_bank_conflict.h
lower_divisible_split.cpp
lower_divisible_split.h
lower_double_buffer.cpp
lower_double_buffer.h
DoubleBufferInfo
DoubleBufferPass
lower_expr_sort.cpp
lower_expr_sort.h
lower_fused_reduction.cpp
lower_fused_reduction.h
FusedReductionInfo
lower_fusion_simplifier.cpp
lower_fusion_simplifier.h
lower_index.cpp
lower_index.h
IndexLowering
lower_index_compute.cpp
LoopIndexingAnalysis
lower_index_compute.h
IndexFromIdGraph
LoopIndexing
lower_index_hoist.cpp
lower_index_hoist.h
CommonIndexKey
CommonIndexKeyHash
CommonIndexMap
lower_insert_syncs.cpp
lower_insert_syncs.h
lower_instrument.cpp
lower_instrument.h
lower_loops.cpp
lower_loops.h
LoopNestGenerator
lower_magic_zero.cpp
lower_magic_zero.h
IndexMagicZeroInfo
lower_misaligned_vectorization.cpp
lower_misaligned_vectorization.h
lower_predicate.cpp
lower_predicate.h
lower_predicate_elimination.cpp
lower_predicate_elimination.h
PredicateElimination
lower_replace_size.cpp
lower_replace_size.h
lower_shift.cpp
lower_shift.h
AxisHaloInfo
HaloInfo
ShiftPredicateInserter
lower_sync_information.cpp
lower_sync_information.h
SyncMap
lower_thread_predicate.cpp
lower_thread_predicate.h
ThreadPredicateMap
lower_trivial_broadcast.cpp
lower_trivial_broadcast.h
ConcretizedBroadcastDomains
lower_trivial_reductions.cpp
lower_trivial_reductions.h
TrivialReductionInfo
lower_unroll.cpp
lower_unroll.h
UnrollPass
lower_utils.cpp
lower_utils.h
IterDomainDependencySorter
TVDomainGuard
BasicAllocInfo
lower_validation.cpp
lower_validation.h
lower_warp_reduce.cpp
lower_warp_reduce.h
WarpPaddedParallelInfo
manager.cpp
manager.h
maxinfo_propagator.cpp
maxinfo_propagator.h
MaxInfoSpanningTree
MaxRootDomainInfoSpanningTree
SetSelector
SpanningTreePrinter
mma_type.cpp
mma_type.h
GemmTile
MatMulTileOptions
MmaBuilder
MmaOptions
mutator.cpp
mutator.h
non_divisible_split.cpp
non_divisible_split.h
NonDivisibleSplitInfo
[+]
ops/
parallel_dimension_map.cpp
parallel_dimension_map.h
ParallelDimensionMap
parallel_type_bitmap.cpp
parallel_type_bitmap.h
ParallelTypeBitmap
ParallelTypeMap
parser.cpp
parser.h
partial_split_map.cpp
partial_split_map.h
PartialSplitMap
partition.cpp
partition.h
predicate_compute.cpp
predicate_compute.h
ParallelizedDomainPredicate
PredicateCompute
UnswitchPredicate
UnswitchPredicateKey
UnswitchPredicateKeyHash
[+]
python_frontend/
register_interface.cpp
register_interface.h
NVFuserPassManager
root_domain_map.cpp
root_domain_map.h
ComputeAtRootDomainMap
ComputeAtRootDomainMapBuilder
DomainKey
DomainKeyHash
ExactRootDomainMap
PairwiseRootDomainMap
RootDomainMap
UnmappableReductionDomains
[+]
scheduler/
tensor_view.cpp
transform_iter.cpp
transform_iter.h
torch::jit::fuser::cuda::(anonymous namespace)::id_int_lt
BestEffortReplay
ReplayTransformations
transform_replay.cpp
transform_replay.h
MostInlinedTransformPropagator
TransformPropagator
TransformReplay
transform_rfactor.cpp
transform_rfactor.h
TransformRFactor
transform_view.cpp
Transform
ViewTransform
transform_view.h
AnalyzeViewConstraint
AnalyzeViewResult
type.cpp
type.h
BinaryOpType
DataType
DoubleBufferLoopStage
ExprType
IdMappingMode
IterType
KernelIndexMode
LaunchConfigType
LoadStoreOpType
MemoryType
ParallelType
PredicateType
RNGOpType
Swizzle2DType
SwizzleMode
SwizzleType
TernaryOpType
TypeHash
UnaryOpType
ValType
type_inference.cpp
type_inference.h
type_promotion.cpp
type_promotion.h
TypePromotionConfig
utils.cpp
utils.h
DebugDumpOption
DisableOption
EnableOption
NonCopyable
PolymorphicBase
vectorization_info.h
VectorizedSetInfo
Generated on
2023-Feb-12
Powered by
Code Browser
2.1
Generator usage only permitted with license