tvm.relay.analysis

The Relay IR namespace containing the analysis passes.

Classes:

AnnotatedRegionSet(expr, region_begin_op, ...)	Class to represent a relay expression split into regions.
CallGraph(module)	Class to represent a call graph.
Feature(value[, names, module, qualname, ...])	The features a program might contain.

Functions:

all_dtypes(expr)	Collect set of all data types used in expr.
all_type_vars(expr[, mod])	Get all type variables from expression/type e
all_vars(expr)	Get all vars from expression expr in post-DFS order.
bound_type_vars(expr[, mod])	Get bound type variables from expression/type e
bound_vars(expr)	Get bound vars from expression expr in post-DFS order.
check_basic_block_normal_form(expr)	Check whether an expression is in the basic block form
check_constant(expr)	Check whether an expression is constant
check_kind(t[, mod])	Check that the type is well kinded and return the kind.
count_layers(expr, valid_ops)	Determine the number of layers of specified ops in a graph.
cpu([dev_id])	Construct a CPU device
detect_feature(a[, b])	Detect the feature used in a relay program.
extract_fused_functions(mod)	Pass to extract IRModule of only fused primitive functions.
extract_intermdeiate_expr(mod, expr_id)	Extract Relay Expr by its expression ID
free_type_vars(expr[, mod])	Get free type variables from expression/type e
free_vars(expr)	Get free Vars from expression expr in Post DFS order.
get_calibration_data(mod, data)	Get the calibration data of a given relay graph
get_total_mac_number(expr)	Count the number of MACs (multiply-accumulate) of a model
list_fake_quantized_op_freqs(mod)	Pass to extract fake quantized op names and the frequency that they appear in fake quantized regions of an IRModule.
list_op_freqs(mod)	Pass to extract unique operator names and how frequently they appear in an IRModule.
post_order_visit(expr, fvisit)	Recursively visit the ir in post DFS order node, apply fvisit.
search_fc_transpose(expr)	Search fc weight name in the patten: y = nn.dense(x, transpose(w, [1, 0]))
unmatched_cases(match[, mod])	Finds cases that the match expression does not catch, if any.
well_formed(expr)	Check that each Var is only bound once (well formed).

class tvm.relay.analysis.AnnotatedRegionSet(expr, region_begin_op, region_end_op)

Class to represent a relay expression split into regions.

Methods:

get_region(expr)

Get the region an expression belongs to.

get_region(expr)

Get the region an expression belongs to.

参数:

expr (tvm.relay.Expr) -- The expression.

返回:

The region containing the expression. None if not found.

返回类型:

region

class tvm.relay.analysis.CallGraph(module)

Class to represent a call graph.

Methods:

global_call_count(var)	Return the number of global function calls from a given global var.
is_recursive(var)	Return if the function corresponding to a var is a recursive function.
print_var(var)	Print a call graph of a global function by name or by variable.
ref_count(var)	Return the number of references to the global var

Attributes:

module

Return the contained Relay IR module.

global_call_count(var)

Return the number of global function calls from a given global var.

参数:

var (Union[String, tvm.relay.GlobalVar])

返回:

ret -- The number of global function calls from the given var.

返回类型:

int

is_recursive(var)

Return if the function corresponding to a var is a recursive function.

参数:

var (Union[String, tvm.relay.GlobalVar])

返回:

ret -- If the function corresponding to var is recurisve.

返回类型:

Boolean

property module

Return the contained Relay IR module.

参数:

None

返回:

ret -- The contained IRModule

返回类型:

tvm.ir.IRModule

print_var(var)

Print a call graph of a global function by name or by variable.

参数:

var (Union[String, tvm.relay.GlobalVar]) -- The name or global variable.

返回:

ret -- The call graph represented in string.

返回类型:

String

ref_count(var)

Return the number of references to the global var

参数:

var (Union[String, tvm.relay.GlobalVar])

返回:

ret -- The number reference to the global var

返回类型:

int

class tvm.relay.analysis.Feature(value, names=<not given>, *values, module=None, qualname=None, type=None, start=1, boundary=None)

The features a program might contain.

Attributes:

fGraph	Whether there is local fixpoint in the program.
fMatch	Whether any non-atom fragment of the program is shared, making the program a graph.

fGraph = 15

Whether there is local fixpoint in the program.

fMatch = 14

Whether any non-atom fragment of the program is shared, making the program a graph.

tvm.relay.analysis.all_dtypes(expr)

Collect set of all data types used in expr.

参数:

expr (tvm.relay.Expr) -- The input expression

返回:

ret -- Set of data types used in the expression (e.g., {'int8', 'int32'})

返回类型:

Set[String]

tvm.relay.analysis.all_type_vars(expr, mod=None)

Get all type variables from expression/type e

参数:

• expr (Union[tvm.relay.Expr,tvm.relay.Type]) -- The input expression/type

• mod (Optional[tvm.IRModule]) -- The global module

返回:

free -- The list of all type variables in post-DFS order

返回类型:

List[tvm.relay.TypeVar]

tvm.relay.analysis.all_vars(expr)

Get all vars from expression expr in post-DFS order.

参数:

expr (tvm.relay.Expr) -- The input expression

返回:

free -- The list of all variables in post-DFS order.

返回类型:

List[tvm.relay.Var]

tvm.relay.analysis.bound_type_vars(expr, mod=None)

Get bound type variables from expression/type e

参数:

• expr (Union[tvm.relay.Expr,tvm.relay.Type]) -- The input expression/type

• mod (Optional[tvm.IRModule]) -- The global module

返回:

free -- The list of bound type variables in post-DFS order

返回类型:

List[tvm.relay.TypeVar]

tvm.relay.analysis.bound_vars(expr)

Get bound vars from expression expr in post-DFS order.

参数:

expr (tvm.relay.Expr) -- The input expression

返回:

free -- The list of bound variables in post-DFS order.

返回类型:

List[tvm.relay.Var]

tvm.relay.analysis.check_basic_block_normal_form(expr)

Check whether an expression is in the basic block form

参数:

expr (tvm.relay.Expr) -- The input expression

返回:

result -- Whether the expression is in the basic block form.

返回类型:

bool

tvm.relay.analysis.check_constant(expr)

Check whether an expression is constant

参数:

expr (tvm.relay.Expr) -- The input expression

返回:

result -- Whether the expression is constant.

返回类型:

bool

tvm.relay.analysis.check_kind(t, mod=None)

Check that the type is well kinded and return the kind. For example, this mean type cannot has tensor of tensor, or is a tuple type of 2 shapes.

参数:

• t (tvm.relay.Type) -- The type to check

• mod (Optional[tvm.IRModule]) -- The global module.

返回:

kind -- the kind of t

返回类型:

Kind

示例

assert check_kind(relay.TupleType([relay.TypeParam('tp1', relay.Kind.Shape)])) == Shape
assert check_kind(relay.TupleType([relay.TypeParam('tp1', relay.Kind.Type)])) == Type

tvm.relay.analysis.count_layers(expr, valid_ops)

Determine the number of layers of specified ops in a graph. This pass computes only the deepest chain of ops rather than the total number of ops in a graph. Thus, if there are two parallel convolutions (for example), they would be considered a single layer.

参数:

• expr (tvm.relay.Expr, tvm.relay.Function, or tvm.ir.IRModule.) -- The input expression.

• valid_ops (List[str]) -- A list of the operations that should be included in the count.

返回:

layer_count -- The number of layers of the specified operations found in the graph.

返回类型:

int

tvm.relay.analysis.cpu(dev_id=0)

Construct a CPU device

参数:

dev_id (int, optional) -- The integer device id

返回:

dev -- The created device

返回类型:

Device

tvm.relay.analysis.detect_feature(a, b=None)

Detect the feature used in a relay program.

参数:

• a (Union[tvm.relay.Expr, tvm.IRModule]) -- The input expression or module.

• b (Optional[Union[tvm.relay.Expr, tvm.IRModule]]) -- The input expression or module. The two arguments cannot both be expression or module.

返回:

features -- Features used in the program.

返回类型:

Set[Feature]

tvm.relay.analysis.extract_fused_functions(mod)

Pass to extract IRModule of only fused primitive functions.

The ExtractFusedFunctions pass invokes SimplifyInference, FuseOps(3), and ExtractFusedFunctions in that order

参数:

mod (tvm.IRModule)

返回:

ret -- A module containing only fused primitive functions

返回类型:

Dict[int, tvm.relay.function.Function]

tvm.relay.analysis.extract_intermdeiate_expr(mod, expr_id)

Extract Relay Expr by its expression ID

This function is used for extracting Relay Expr by its expression ID of the main function that we can see in print(mod["main"]).

参数:

• mod (tvm.IRModule)

• expr_id (the Expr ID that we want to extract)

返回:

ret

返回类型:

Extracted IRModule

示例

# Suppose our module is printed like this:
# def @main(%x: Tensor[(1, 1, 5, 1), float32], %w1, %w2) {
#   %0 = nn.conv2d(%x, %w1, padding=[1, 1, 1, 1], channels=1, kernel_size=[3, 3]);
#   %1 = nn.conv2d(%0, %w2, padding=[1, 1, 1, 1], channels=1, kernel_size=[3, 3]);
#   %2 = add(%0, %1);
#   %3 = split(%2, indices_or_sections=1);
#   %4 = %3.0;
#   add(%4, 1f)
# }
# if we want to extract `%1 = nn.conv2d`
from tvm import relay

relay.analysis.extract_intermdeiate_expr(mod, 1)

tvm.relay.analysis.free_type_vars(expr, mod=None)

Get free type variables from expression/type e

参数:

• expr (Union[tvm.relay.Expr,tvm.relay.Type]) -- The input expression/type

• mod (Optional[tvm.IRModule]) -- The global module

返回:

free -- The list of free type variables in post-DFS order

返回类型:

List[tvm.relay.TypeVar]

tvm.relay.analysis.free_vars(expr)

Get free Vars from expression expr in Post DFS order.

参数:

expr (tvm.relay.Expr) -- The input expression

返回:

free -- The list of free variables in post DFS order.

返回类型:

List[tvm.relay.Var]

备注

The fact that Vars are post-DFS ordred are useful in neural networks: usually this means weights of previous are ordered first.

tvm.relay.analysis.get_calibration_data(mod, data)

Get the calibration data of a given relay graph

This pass uses the graph executor to get the calibration data of a module, which includes the input and output values of each function. The returned data uses the GlobalVar of each function as a key. Users can further access the inputs and outputs by using inputs or outputs as the key.

Following are some limitations: 1. The input module (graph) cannot have control flows. 2. The input arguments of each function cannot be tuples (outputs can be tuples). 3. We only handle top-level functions (i.e., nested function is not handled). 4. We only handle functions with Compiler attribute being set.

参数:

• mod (tvm.IRModule) -- The input module for collecting the calibration data

• data (Dict[str, NDArray]) -- The input data for running the module

返回:

data

返回类型:

Dict[tvm.relay.GlobalVar, Dict[str, NDArray]]

tvm.relay.analysis.get_total_mac_number(expr)

Count the number of MACs (multiply-accumulate) of a model

参数:

expr (tvm.relay.Expr) -- The input expression.

返回:

result -- The number of MACs (multiply-accumulate) of a model

返回类型:

int64

tvm.relay.analysis.list_fake_quantized_op_freqs(mod)

Pass to extract fake quantized op names and the frequency that they appear in fake quantized regions of an IRModule.

参数:

mod (tvm.IRModule)

返回:

ret -- Dict of fake quantized operator names to frequency

返回类型:

Dict[str, int]

tvm.relay.analysis.list_op_freqs(mod)

Pass to extract unique operator names and how frequently they appear in an IRModule. Fused functions are traversed to count the operators that compose them.

参数:

mod (tvm.IRModule)

返回:

ret -- Dict of unique operator names to frequency

返回类型:

Dict[str, int]

tvm.relay.analysis.post_order_visit(expr, fvisit)

Recursively visit the ir in post DFS order node, apply fvisit. Each node is guaranteed to be visited only once.

参数:

• expr (tvm.relay.Expr) -- The input expression.

• fvisit (function) -- The visitor function to be applied.

tvm.relay.analysis.search_fc_transpose(expr)

Search fc weight name in the patten: y = nn.dense(x, transpose(w, [1, 0]))

This function is used in the data_dep_optimization.simplify_fc_transpose method

参数:

expr (tvm.relay.Expr)

返回:

ret -- Array of weight variable name in pattern y = nn.dense(x, transpose(w, [1, 0]))

返回类型:

Array[String]

tvm.relay.analysis.unmatched_cases(match, mod=None)

Finds cases that the match expression does not catch, if any.

参数:

• match (tvm.relay.Match) -- The match expression

• mod (Optional[tvm.IRModule]) -- The module (defaults to an empty module)

返回:

missing_patterns -- Patterns that the match expression does not catch.

返回类型:

[tvm.relay.Pattern]

tvm.relay.analysis.well_formed(expr)

Check that each Var is only bound once (well formed).

参数:

expr (tvm.relay.Expr) -- The input expression

返回:

well_form -- Whether the input expression is well formed

返回类型:

bool