Reviewed By: rriddle Differential Revision: https://reviews.llvm.org/D92416
21 KiB
Dialect Conversion
This document describes a framework in MLIR in which to perform operation conversions between, and within dialects. This framework allows for transforming illegal operations to those supported by a provided conversion target, via a set of pattern-based operation rewriting patterns.
[TOC]
The dialect conversion framework consists of the following components:
- A Conversion Target
- A set of Rewrite Patterns
- A Type Converter (Optional)
Modes of Conversion
When applying a conversion to a set of operations, there are several different conversion modes that may be selected from:
-
Partial Conversion
- A partial conversion will legalize as many operations to the target as possible, but will allow pre-existing operations that were not explicitly marked as "illegal" to remain unconverted. This allows for partially lowering parts of the input in the presence of unknown operations.
- A partial conversion can be applied via
applyPartialConversion
.
-
Full Conversion
- A full conversion legalizes all input operations, and is only successful if all operations are properly legalized to the given conversion target. This ensures that only known operations will exist after the conversion process.
- A full conversion can be applied via
applyFullConversion
.
-
Analysis Conversion
- An analysis conversion will analyze which operations are legalizable to the given conversion target if a conversion were to be applied. This is done by performing a 'partial' conversion and recording which operations would have been successfully converted if successful. Note that no rewrites, or transformations, are actually applied to the input operations.
- An analysis conversion can be applied via
applyAnalysisConversion
.
Conversion Target
The conversion target is a formal definition of what is considered to be legal
during the conversion process. The final operations generated by the conversion
framework must be marked as legal on the ConversionTarget
for the rewrite to
be a success. Depending on the conversion mode, existing operations need not
always be legal. Operations and dialects may be marked with any of the provided
legality actions below:
-
Legal
- This action signals that every instance of a given operation is legal, i.e. any combination of attributes, operands, types, etc. are valid.
-
Dynamic
- This action signals that only some instances of a given operation are
legal. This allows for defining fine-tune constraints, e.g. saying that
addi
is only legal when operating on 32-bit integers. - If a specific handler is not provided when setting the action, the
target must override the
isDynamicallyLegal
hook provided byConversionTarget
.
- This action signals that only some instances of a given operation are
legal. This allows for defining fine-tune constraints, e.g. saying that
-
Illegal
- This action signals that no instance of a given operation is legal. Operations marked as "illegal" must always be converted for the conversion to be successful. This action also allows for selectively marking specific operations as illegal in an otherwise legal dialect.
An example conversion target is shown below:
struct MyTarget : public ConversionTarget {
MyTarget(MLIRContext &ctx) : ConversionTarget(ctx) {
//--------------------------------------------------------------------------
// Marking an operation as Legal:
/// Mark all operations within the LLVM dialect are legal.
addLegalDialect<LLVMDialect>();
/// Mark `std.constant` op is always legal on this target.
addLegalOp<ConstantOp>();
//--------------------------------------------------------------------------
// Marking an operation as dynamically legal.
/// Mark all operations within Affine dialect have dynamic legality
/// constraints.
addDynamicallyLegalDialect<AffineDialect>();
/// Mark `std.return` as dynamically legal.
addDynamicallyLegalOp<ReturnOp>();
/// Mark `std.return` as dynamically legal, but provide a specific legality
/// callback.
addDynamicallyLegalOp<ReturnOp>([](ReturnOp op) { ... });
/// Treat unknown operations, i.e. those without a legalization action
/// directly set, as dynamically legal.
markUnknownOpDynamicallyLegal();
markUnknownOpDynamicallyLegal([](Operation *op) { ... });
//--------------------------------------------------------------------------
// Marking an operation as illegal.
/// All operations within the GPU dialect are illegal.
addIllegalDialect<GPUDialect>();
/// Mark `std.br` and `std.cond_br` as illegal.
addIllegalOp<BranchOp, CondBranchOp>();
}
/// Implement the default legalization handler to handle operations marked as
/// dynamically legal that were not provided with an explicit handler.
bool isDynamicallyLegal(Operation *op) override { ... }
};
Recursive Legality
In some cases, it may be desirable to mark entire regions as legal. This
provides an additional granularity of context to the concept of "legal". If an
operation is marked recursively legal, either statically or dynamically, then
all of the operations nested within are also considered legal even if they would
otherwise be considered "illegal". An operation can be marked via
markOpRecursivelyLegal<>
:
ConversionTarget &target = ...;
/// The operation must first be marked as `Legal` or `Dynamic`.
target.addLegalOp<MyOp>(...);
target.addDynamicallyLegalOp<MySecondOp>(...);
/// Mark the operation as always recursively legal.
target.markOpRecursivelyLegal<MyOp>();
/// Mark optionally with a callback to allow selective marking.
target.markOpRecursivelyLegal<MyOp, MySecondOp>([](Operation *op) { ... });
/// Mark optionally with a callback to allow selective marking.
target.markOpRecursivelyLegal<MyOp>([](MyOp op) { ... });
Rewrite Pattern Specification
After the conversion target has been defined, a set of legalization patterns must be provided to transform illegal operations into legal ones. The patterns supplied here have the same structure and restrictions as those described in the main Pattern documentation. The patterns provided do not need to generate operations that are directly legal on the target. The framework will automatically build a graph of conversions to convert non-legal operations into a set of legal ones.
As an example, say you define a target that supports one operation: foo.add
.
When providing the following patterns: [bar.add
-> baz.add
, baz.add
->
foo.add
], the framework will automatically detect that it can legalize
bar.add
-> foo.add
even though a direct conversion does not exist. This
means that you don’t have to define a direct legalization pattern for bar.add
-> foo.add
.
Conversion Patterns
Along with the general RewritePattern
classes, the conversion framework
provides a special type of rewrite pattern that can be used when a pattern
relies on interacting with constructs specific to the conversion process, the
ConversionPattern
. For example, the conversion process does not necessarily
update operations in-place and instead creates a mapping of events such as
replacements and erasures, and only applies them when the entire conversion
process is successful. Certain classes of patterns rely on using the
updated/remapped operands of an operation, such as when the types of results
defined by an operation have changed. The general Rewrite Patterns can no longer
be used in these situations, as the types of the operands of the operation being
matched will not correspond with those expected by the user. This pattern
provides, as an additional argument to the matchAndRewrite
and rewrite
methods, the list of operands that the operation should use after conversion. If
an operand was the result of a non-converted operation, for example if it was
already legal, the original operand is used. This means that the operands
provided always have a 1-1 non-null correspondence with the operands on the
operation. The original operands of the operation are still intact and may be
inspected as normal. These patterns also utilize a special PatternRewriter
,
ConversionPatternRewriter
, that provides special hooks for use with the
conversion infrastructure.
struct MyConversionPattern : public ConversionPattern {
/// The `matchAndRewrite` hooks on ConversionPatterns take an additional
/// `operands` parameter, containing the remapped operands of the original
/// operation.
virtual LogicalResult
matchAndRewrite(Operation *op, ArrayRef<Value> operands,
ConversionPatternRewriter &rewriter) const;
};
Type Safety
The types of the remapped operands provided to a conversion pattern must be of a
type expected by the pattern. The expected types of a pattern are determined by
a provided TypeConverter. If no type converter is provided,
the types of the remapped operands are expected to match the types of the
original operands. If a type converter is provided, the types of the remapped
operands are expected to be legal as determined by the converter. If the
remapped operand types are not of an expected type, and a materialization to the
expected type could not be performed, the pattern fails application before the
matchAndRewrite
hook is invoked. This ensures that patterns do not have to
explicitly ensure type safety, or sanitize the types of the incoming remapped
operands. More information on type conversion is detailed in the
dedicated section below.
Type Conversion
It is sometimes necessary as part of a conversion to convert the set types of
being operated on. In these cases, a TypeConverter
object may be defined that
details how types should be converted when interfacing with a pattern. A
TypeConverter
may be used to convert the signatures of block arguments and
regions, to define the expected inputs types of the pattern, and to reconcile
type differences in general.
Type Converter
The TypeConverter
contains several hooks for detailing how to convert types,
and how to materialize conversions between types in various situations. The two
main aspects of the TypeConverter
are conversion and materialization.
A conversion
describes how a given illegal source Type
should be converted
to N target types. If the source type is already "legal", it should convert to
itself. Type conversions are specified via the addConversion
method described
below.
A materialization
describes how a set of values should be converted to a
single value of a desired type. An important distinction with a conversion
is
that a materialization
can produce IR, whereas a conversion
cannot. These
materializations are used by the conversion framework to ensure type safety
during the conversion process. There are several types of materializations
depending on the situation.
-
Argument Materialization
- An argument materialization is used when converting the type of a block argument during a signature conversion.
-
Source Materialization
- A source materialization converts from a value with a "legal" target type, back to a specific source type. This is used when an operation is "legal" during the conversion process, but contains a use of an illegal type. This may happen during a conversion where some operations are converted to those with different resultant types, but still retain users of the original type system.
- This materialization is used in the following situations:
- When a block argument has been converted to a different type, but the original argument still has users that will remain live after the conversion process has finished.
- When the result type of an operation has been converted to a different type, but the original result still has users that will remain live after the conversion process is finished.
-
Target Materialization
- A target materialization converts from a value with an "illegal" source type, to a value of a "legal" type. This is used when a pattern expects the remapped operands to be of a certain set of types, but the original input operands have not been converted. This may happen during a conversion where some operations are converted to those with different resultant types, but still retain uses of the original type system.
- This materialization is used in the following situations:
- When the remapped operands of a conversion pattern are not legal for the type conversion provided by the pattern.
If a converted value is used by an operation that isn't converted, it needs a
conversion back to the source
type, hence source materialization; if an
unconverted value is used by an operation that is being converted, it needs
conversion to the target
type, hence target materialization.
As noted above, the conversion process guarantees that the type contract of the IR is preserved during the conversion. This means that the types of value uses will not implicitly change during the conversion process. When the type of a value definition, either block argument or operation result, is being changed, the users of that definition must also be updated during the conversion process. If they aren't, a type conversion must be materialized to ensure that a value of the expected type is still present within the IR. If a target materialization is required, but cannot be performed, the pattern application fails. If a source materialization is required, but cannot be performed, the entire conversion process fails.
Several of the available hooks are detailed below:
class TypeConverter {
public:
/// Register a conversion function. A conversion function defines how a given
/// source type should be converted. A conversion function must be convertible
/// to any of the following forms(where `T` is a class derived from `Type`:
/// * Optional<Type>(T)
/// - This form represents a 1-1 type conversion. It should return nullptr
/// or `llvm::None` to signify failure. If `llvm::None` is returned, the
/// converter is allowed to try another conversion function to perform
/// the conversion.
/// * Optional<LogicalResult>(T, SmallVectorImpl<Type> &)
/// - This form represents a 1-N type conversion. It should return
/// `failure` or `llvm::None` to signify a failed conversion. If the new
/// set of types is empty, the type is removed and any usages of the
/// existing value are expected to be removed during conversion. If
/// `llvm::None` is returned, the converter is allowed to try another
/// conversion function to perform the conversion.
/// Note: When attempting to convert a type, e.g. via 'convertType', the
/// mostly recently added conversions will be invoked first.
template <typename FnT,
typename T = typename llvm::function_traits<FnT>::template arg_t<0>>
void addConversion(FnT &&callback) {
registerConversion(wrapCallback<T>(std::forward<FnT>(callback)));
}
/// Register a materialization function, which must be convertible to the
/// following form:
/// `Optional<Value> (OpBuilder &, T, ValueRange, Location)`,
/// where `T` is any subclass of `Type`.
/// This function is responsible for creating an operation, using the
/// OpBuilder and Location provided, that "converts" a range of values into a
/// single value of the given type `T`. It must return a Value of the
/// converted type on success, an `llvm::None` if it failed but other
/// materialization can be attempted, and `nullptr` on unrecoverable failure.
/// It will only be called for (sub)types of `T`.
///
/// This method registers a materialization that will be called when
/// converting an illegal block argument type, to a legal type.
template <typename FnT,
typename T = typename llvm::function_traits<FnT>::template arg_t<1>>
void addArgumentMaterialization(FnT &&callback) {
argumentMaterializations.emplace_back(
wrapMaterialization<T>(std::forward<FnT>(callback)));
}
/// This method registers a materialization that will be called when
/// converting a legal type to an illegal source type. This is used when
/// conversions to an illegal type must persist beyond the main conversion.
template <typename FnT,
typename T = typename llvm::function_traits<FnT>::template arg_t<1>>
void addSourceMaterialization(FnT &&callback) {
sourceMaterializations.emplace_back(
wrapMaterialization<T>(std::forward<FnT>(callback)));
}
/// This method registers a materialization that will be called when
/// converting type from an illegal, or source, type to a legal type.
template <typename FnT,
typename T = typename llvm::function_traits<FnT>::template arg_t<1>>
void addTargetMaterialization(FnT &&callback) {
targetMaterializations.emplace_back(
wrapMaterialization<T>(std::forward<FnT>(callback)));
}
};
Region Signature Conversion
From the perspective of type conversion, the types of block arguments are a bit
special. Throughout the conversion process, blocks may move between regions of
different operations. Given this, the conversion of the types for blocks must be
done explicitly via a conversion pattern. To convert the types of block
arguments within a Region, a custom hook on the ConversionPatternRewriter
must
be invoked; convertRegionTypes
. This hook uses a provided type converter to
apply type conversions to all blocks within a given region, and all blocks that
move into that region. As noted above, the conversions performed by this method
use the argument materialization hook on the TypeConverter
. This hook also
takes an optional TypeConverter::SignatureConversion
parameter that applies a
custom conversion to the entry block of the region. The types of the entry block
arguments are often tied semantically to details on the operation, e.g. FuncOp,
AffineForOp, etc. To convert the signature of just the region entry block, and
not any other blocks within the region, the applySignatureConversion
hook may
be used instead. A signature conversion, TypeConverter::SignatureConversion
,
can be built programmatically:
class SignatureConversion {
public:
/// Remap an input of the original signature with a new set of types. The
/// new types are appended to the new signature conversion.
void addInputs(unsigned origInputNo, ArrayRef<Type> types);
/// Append new input types to the signature conversion, this should only be
/// used if the new types are not intended to remap an existing input.
void addInputs(ArrayRef<Type> types);
/// Remap an input of the original signature with a range of types in the
/// new signature.
void remapInput(unsigned origInputNo, unsigned newInputNo,
unsigned newInputCount = 1);
/// Remap an input of the original signature to another `replacement`
/// value. This drops the original argument.
void remapInput(unsigned origInputNo, Value replacement);
};
The TypeConverter
provides several default utilities for signature conversion
and legality checking:
convertSignatureArgs
/convertBlockSignature
/isLegal(Region *|Type)
.
Debugging
To debug the execution of the dialect conversion framework,
-debug-only=dialect-conversion
may be used. This command line flag activates
LLVM's debug logging infrastructure solely for the conversion framework. The
output is formatted as a tree structure, mirroring the structure of the
conversion process. This output contains all of the actions performed by the
rewriter, how generated operations get legalized, and why they fail.
Example output is shown below:
//===-------------------------------------------===//
Legalizing operation : 'std.return'(0x608000002e20) {
"std.return"() : () -> ()
* Fold {
} -> FAILURE : unable to fold
* Pattern : 'std.return -> ()' {
** Insert : 'spv.Return'(0x6070000453e0)
** Replace : 'std.return'(0x608000002e20)
//===-------------------------------------------===//
Legalizing operation : 'spv.Return'(0x6070000453e0) {
"spv.Return"() : () -> ()
} -> SUCCESS : operation marked legal by the target
//===-------------------------------------------===//
} -> SUCCESS : pattern applied successfully
} -> SUCCESS
//===-------------------------------------------===//
This output is describing the legalization of an std.return
operation. We
first try to legalize by folding the operation, but that is unsuccessful for
std.return
. From there, a pattern is applied that replaces the std.return
with a spv.Return
. The newly generated spv.Return
is then processed for
legalization, but is found to already legal as per the target.