This changes the behavior of constructing MLIRContext to no longer load globally
registered dialects on construction. Instead Dialects are only loaded explicitly
on demand:
- the Parser is lazily loading Dialects in the context as it encounters them
during parsing. This is the only purpose for registering dialects and not load
them in the context.
- Passes are expected to declare the dialects they will create entity from
(Operations, Attributes, or Types), and the PassManager is loading Dialects into
the Context when starting a pipeline.
This changes simplifies the configuration of the registration: a compiler only
need to load the dialect for the IR it will emit, and the optimizer is
self-contained and load the required Dialects. For example in the Toy tutorial,
the compiler only needs to load the Toy dialect in the Context, all the others
(linalg, affine, std, LLVM, ...) are automatically loaded depending on the
optimization pipeline enabled.
To adjust to this change, stop using the existing dialect registration: the
global registry will be removed soon.
1) For passes, you need to override the method:
virtual void getDependentDialects(DialectRegistry ®istry) const {}
and registery on the provided registry any dialect that this pass can produce.
Passes defined in TableGen can provide this list in the dependentDialects list
field.
2) For dialects, on construction you can register dependent dialects using the
provided MLIRContext: `context.getOrLoadDialect<DialectName>()`
This is useful if a dialect may canonicalize or have interfaces involving
another dialect.
3) For loading IR, dialect that can be in the input file must be explicitly
registered with the context. `MlirOptMain()` is taking an explicit registry for
this purpose. See how the standalone-opt.cpp example is setup:
mlir::DialectRegistry registry;
registry.insert<mlir::standalone::StandaloneDialect>();
registry.insert<mlir::StandardOpsDialect>();
Only operations from these two dialects can be in the input file. To include all
of the dialects in MLIR Core, you can populate the registry this way:
mlir::registerAllDialects(registry);
4) For `mlir-translate` callback, as well as frontend, Dialects can be loaded in
the context before emitting the IR: context.getOrLoadDialect<ToyDialect>()
Differential Revision: https://reviews.llvm.org/D85622
This changes the behavior of constructing MLIRContext to no longer load globally
registered dialects on construction. Instead Dialects are only loaded explicitly
on demand:
- the Parser is lazily loading Dialects in the context as it encounters them
during parsing. This is the only purpose for registering dialects and not load
them in the context.
- Passes are expected to declare the dialects they will create entity from
(Operations, Attributes, or Types), and the PassManager is loading Dialects into
the Context when starting a pipeline.
This changes simplifies the configuration of the registration: a compiler only
need to load the dialect for the IR it will emit, and the optimizer is
self-contained and load the required Dialects. For example in the Toy tutorial,
the compiler only needs to load the Toy dialect in the Context, all the others
(linalg, affine, std, LLVM, ...) are automatically loaded depending on the
optimization pipeline enabled.
To adjust to this change, stop using the existing dialect registration: the
global registry will be removed soon.
1) For passes, you need to override the method:
virtual void getDependentDialects(DialectRegistry ®istry) const {}
and registery on the provided registry any dialect that this pass can produce.
Passes defined in TableGen can provide this list in the dependentDialects list
field.
2) For dialects, on construction you can register dependent dialects using the
provided MLIRContext: `context.getOrLoadDialect<DialectName>()`
This is useful if a dialect may canonicalize or have interfaces involving
another dialect.
3) For loading IR, dialect that can be in the input file must be explicitly
registered with the context. `MlirOptMain()` is taking an explicit registry for
this purpose. See how the standalone-opt.cpp example is setup:
mlir::DialectRegistry registry;
mlir::registerDialect<mlir::standalone::StandaloneDialect>();
mlir::registerDialect<mlir::StandardOpsDialect>();
Only operations from these two dialects can be in the input file. To include all
of the dialects in MLIR Core, you can populate the registry this way:
mlir::registerAllDialects(registry);
4) For `mlir-translate` callback, as well as frontend, Dialects can be loaded in
the context before emitting the IR: context.getOrLoadDialect<ToyDialect>()
This changes the behavior of constructing MLIRContext to no longer load globally registered dialects on construction. Instead Dialects are only loaded explicitly on demand:
- the Parser is lazily loading Dialects in the context as it encounters them during parsing. This is the only purpose for registering dialects and not load them in the context.
- Passes are expected to declare the dialects they will create entity from (Operations, Attributes, or Types), and the PassManager is loading Dialects into the Context when starting a pipeline.
This changes simplifies the configuration of the registration: a compiler only need to load the dialect for the IR it will emit, and the optimizer is self-contained and load the required Dialects. For example in the Toy tutorial, the compiler only needs to load the Toy dialect in the Context, all the others (linalg, affine, std, LLVM, ...) are automatically loaded depending on the optimization pipeline enabled.
Differential Revision: https://reviews.llvm.org/D85622
This changes the behavior of constructing MLIRContext to no longer load globally registered dialects on construction. Instead Dialects are only loaded explicitly on demand:
- the Parser is lazily loading Dialects in the context as it encounters them during parsing. This is the only purpose for registering dialects and not load them in the context.
- Passes are expected to declare the dialects they will create entity from (Operations, Attributes, or Types), and the PassManager is loading Dialects into the Context when starting a pipeline.
This changes simplifies the configuration of the registration: a compiler only need to load the dialect for the IR it will emit, and the optimizer is self-contained and load the required Dialects. For example in the Toy tutorial, the compiler only needs to load the Toy dialect in the Context, all the others (linalg, affine, std, LLVM, ...) are automatically loaded depending on the optimization pipeline enabled.
-- This commit handles the returnOp in memref map layout normalization.
-- An initial filter is applied on FuncOps which helps us know which functions can be
a suitable candidate for memref normalization which doesn't lead to invalid IR.
-- Handles memref map normalization for external function assuming the external function
is normalizable.
Differential Revision: https://reviews.llvm.org/D85226
This diff attempts to resolve the TODO in `getOpIndexSet` (formerly
known as `getInstIndexSet`), which states "Add support to handle IfInsts
surronding `op`".
Major changes in this diff:
1. Overload `getIndexSet`. The overloaded version considers both
`AffineForOp` and `AffineIfOp`.
2. The `getInstIndexSet` is updated accordingly: its name is changed to
`getOpIndexSet` and its implementation is based on a new API `getIVs`
instead of `getLoopIVs`.
3. Add `addAffineIfOpDomain` to `FlatAffineConstraints`, which extracts
new constraints from the integer set of `AffineIfOp` and merges it to
the current constraint system.
4. Update how a `Value` is determined as dim or symbol for
`ValuePositionMap` in `buildDimAndSymbolPositionMaps`.
Differential Revision: https://reviews.llvm.org/D84698
Always define a remapping for the memref replacement (`indexRemap`)
with the proper number of inputs, including all the `outerIVs`, so that
the number of inputs and the operands provided for the map don't mismatch.
Reviewed By: bondhugula, andydavis1
Differential Revision: https://reviews.llvm.org/D85177
Remove use of iterator::difference_type to know where to insert a
moved or erased block during undo actions.
Differential Revision: https://reviews.llvm.org/D85066
-- Introduces a pass that normalizes the affine layout maps to the identity layout map both within and across functions by rewriting function arguments and call operands where necessary.
-- Memref normalization is now implemented entirely in the module pass '-normalize-memrefs' and the limited intra-procedural version has been removed from '-simplify-affine-structures'.
-- Run using -normalize-memrefs.
-- Return ops are not handled and would be handled in the subsequent revisions.
Signed-off-by: Abhishek Varma <abhishek.varma@polymagelabs.com>
Differential Revision: https://reviews.llvm.org/D84490
- Add getArgumentTypes() to Region (missed from before)
- Adopt Region argument API in `hasMultiplyAddBody`
- Fix 2 typos in comments
Differential Revision: https://reviews.llvm.org/D84807
The MemRefDataFlow pass does store to load forwarding
only for affine store/loads. This patch updates the pass
to use affine read/write interface which enables vector
forwarding.
Reviewed By: dcaballe, bondhugula, ftynse
Differential Revision: https://reviews.llvm.org/D84302
This revision adds support for much deeper type conversion integration into the conversion process, and enables auto-generating cast operations when necessary. Type conversions are now largely automatically managed by the conversion infra when using a ConversionPattern with a provided TypeConverter. This removes the need for patterns to do type cast wrapping themselves and moves the burden to the infra. This makes it much easier to perform partial lowerings when type conversions are involved, as any lingering type conversions will be automatically resolved/legalized by the conversion infra.
To support this new integration, a few changes have been made to the type materialization API on TypeConverter. Materialization has been split into three separate categories:
* Argument Materialization: This type of materialization is used when converting the type of block arguments when calling `convertRegionTypes`. This is useful for contextually inserting additional conversion operations when converting a block argument type, such as when converting the types of a function signature.
* Source Materialization: This type of materialization is used to convert a legal type of the converter into a non-legal type, generally a source type. This may be called when uses of a non-legal type persist after the conversion process has finished.
* Target Materialization: This type of materialization is used to convert a non-legal, or source, type into a legal, or target, type. This type of materialization is used when applying a pattern on an operation, but the types of the operands have not yet been converted.
Differential Revision: https://reviews.llvm.org/D82831
AllocOp is updated in normalizeMemref(AllocOp allocOp), but, when the
AllocOp has `alignment` attribute, it was ignored and updated AllocOp
does not have `alignment` attribute. This patch fixes it.
Differential Revision: https://reviews.llvm.org/D83656
Some dialects have semantics which is not well represented by common
SSA structures with dominance constraints. This patch allows
operations to declare the 'kind' of their contained regions.
Currently, two kinds are allowed: "SSACFG" and "Graph". The only
difference between them at the moment is that SSACFG regions are
required to have dominance, while Graph regions are not required to
have dominance. The intention is that this Interface would be
generated by ODS for existing operations, although this has not yet
been implemented. Presumably, if someone were interested in code
generation, we might also have a "CFG" dialect, which defines control
flow, but does not require SSA.
The new behavior is mostly identical to the previous behavior, since
registered operations without a RegionKindInterface are assumed to
contain SSACFG regions. However, the behavior has changed for
unregistered operations. Previously, these were checked for
dominance, however the new behavior allows dominance violations, in
order to allow the processing of unregistered dialects with Graph
regions. One implication of this is that regions in unregistered
operations with more than one op are no longer CSE'd (since it
requires dominance info).
I've also reorganized the LangRef documentation to remove assertions
about "sequential execution", "SSA Values", and "Dominance". Instead,
the core IR is simply "ordered" (i.e. totally ordered) and consists of
"Values". I've also clarified some things about how control flow
passes between blocks in an SSACFG region. Control Flow must enter a
region at the entry block and follow terminator operation successors
or be returned to the containing op. Graph regions do not define a
notion of control flow.
see discussion here:
https://llvm.discourse.group/t/rfc-allowing-dialects-to-relax-the-ssa-dominance-condition/833/53
Differential Revision: https://reviews.llvm.org/D80358
Up until now, there has been an implicit agreement that when an operation is marked as
"erased" all uses of that operation's results are guaranteed to be removed during conversion. How this works in practice is that there is either an assert/crash/asan failure/etc. This revision adds support for properly detecting when an erased operation has dangling users, emits and error and fails the conversion.
Differential Revision: https://reviews.llvm.org/D82830
- Arguments of the first block of a region are considered region arguments.
- Add API on Region class to deal with these arguments directly instead of
using the front() block.
- Changed several instances of existing code that can use this API
- Fixes https://bugs.llvm.org/show_bug.cgi?id=46535
Differential Revision: https://reviews.llvm.org/D83599
Summary:
Almost all uses of these iterators, including implicit ones, really
only need the const variant (as it should be). The only exception is
in NewGVN, which changes the order of dominator tree child nodes.
Change-Id: I4b5bd71e32d71b0c67b03d4927d93fe9413726d4
Reviewers: arsenm, RKSimon, mehdi_amini, courbet, rriddle, aartbik
Subscribers: wdng, Prazek, hiraditya, kuhar, rogfer01, rriddle, jpienaar, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, stephenneuendorffer, Joonsoo, grosul1, vkmr, Kayjukh, jurahul, msifontes, cfe-commits, llvm-commits
Tags: #clang, #mlir, #llvm
Differential Revision: https://reviews.llvm.org/D83087
ViewLikeOpInterfaces introduce new aliases that need to be added to the alias
list. This is necessary to place deallocs in the right positions.
Differential Revision: https://reviews.llvm.org/D83044
This pass removes redundant dialect-independent Copy operations in different
situations like the following:
%from = ...
%to = ...
... (no user/alias for %to)
copy(%from, %to)
... (no user/alias for %from)
dealloc %from
use(%to)
Differential Revision: https://reviews.llvm.org/D82757
Summary: The current BufferPlacement implementation does not support
nested region control flow. This CL adds support for nested regions via
the RegionBranchOpInterface and the detection of branch-like
(ReturnLike) terminators inside nested regions.
Differential Revision: https://reviews.llvm.org/D81926
Summary: The patch fixes an off by one error in the method collapseParallelLoops. It ensures the same normalized bound is used for the computation of the division and the remainder.
Reviewers: herhut
Reviewed By: herhut
Subscribers: mehdi_amini, rriddle, jpienaar, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, stephenneuendorffer, Joonsoo, grosul1, Kayjukh, jurahul, msifontes
Tags: #mlir
Differential Revision: https://reviews.llvm.org/D82634
When there is a mix of affine load/store and non-affine operations (e.g. std.load, std.store),
affine-loop-fusion ignores the present of non-affine ops, thus changing the program semantics.
E.g. we have a program of three affine loops operating on the same memref in which one of them uses std.load and std.store, as follows.
```
affine.for
affine.store %1
affine.for
std.load %1
std.store %1
affine.for
affine.load %1
affine.store %1
```
affine-loop-fusion will produce the following result which changed the program semantics:
```
affine.for
std.load %1
std.store %1
affine.for
affine.store %1
affine.load %1
affine.store %1
```
This patch is to fix the above problem by checking non-affine users of the memref that are between the source and destination nodes of interest.
Differential Revision: https://reviews.llvm.org/D82158
This revision removes the TypeConverter parameter passed to the apply* methods, and instead moves the responsibility of region type conversion to patterns. The types of a region can be converted using the 'convertRegionTypes' method, which acts similarly to the existing 'applySignatureConversion'. This method ensures that all blocks within, and including those moved into, a region will have the block argument types converted using the provided converter.
This has the benefit of making more of the legalization logic controlled by patterns, instead of being handled explicitly by the driver. It also opens up the possibility to support multiple type conversions at some point in the future.
This revision also adds a new utility class `FailureOr<T>` that provides a LogicalResult friendly facility for returning a failure or a valid result value.
Differential Revision: https://reviews.llvm.org/D81681
Traditionally patterns have always had the root operation kind hardcoded to a specific operation name. This has worked well for quite some time, but it has certain limitations that make it undesirable. For example, some lowering have the same implementation for many different operations types with a few lowering entire dialects using the same pattern implementation. This problem has led to several "solutions":
a) Provide a template implementation to the user so that they can instantiate it for each operation combination, generally requiring the inclusion of the auto-generated operation definition file.
b) Use a non-templated pattern that allows for providing the name of the operation to match
- No one ever does this, because enumerating operation names can be cumbersome and so this quickly devolves into solution a.
This revision removes the restriction that patterns have a hardcoded root type, and allows for a class patterns that could match "any" operation type. The major downside of root-agnostic patterns is that they make certain pattern analyses more difficult, so it is still very highly encouraged that an operation specific pattern be used whenever possible.
Differential Revision: https://reviews.llvm.org/D82066
This class enables for abstracting more of the details for the rewrite process, and will allow for clients to apply specific cost models to the pattern list. This allows for DialectConversion and the GreedyPatternRewriter to share the same underlying matcher implementation. This also simplifies the plumbing necessary to support dynamic patterns.
Differential Revision: https://reviews.llvm.org/D81985
We previously weren't properly updating the SCC iterator when nodes were removed, leading to asan failures in certain situations. This commit adds a CallGraphSCC class and defers operation deletion until inlining has finished.
Differential Revision: https://reviews.llvm.org/D81984
Similarly to `scf::ForOp`, introduce additional `function_ref` arguments to
`::build` functions of SCF `ParallelOp` and `ReduceOp`. The provided functions
will be called to construct the body of the respective operations while
constructing the operation itself. Exercise them in LoopUtils.
Differential Revision: https://reviews.llvm.org/D81872
It is quite common for the same type to be converted many types throughout the conversion process, and there isn't any good reason why we aren't caching that result. Especially given that we currently use identity conversion to signify legality. This revision also adds a few additional helpers to TypeConverter.
Differential Revision: https://reviews.llvm.org/D81679
allocations cannot be moved freely and can remain in divergent control flow.
The current BufferPlacement pass does not support allocation nodes that carry
additional dependencies (like in the case of dynamic shaped types). These
allocations can often not be moved freely and in turn might remain in divergent
control-flow branches. This requires a different strategy with respect to block
arguments and aliases. This CL adds additinal functionality to support
allocation nodes in divergent control flow while avoiding memory leaks.
Differential Revision: https://reviews.llvm.org/D79850
This patch changes the fusion algorithm so that after fusing two loop nests
we revisit previously visited nodes so that they are considered again for
fusion in the context of the new fused loop nest.
Reviewed By: bondhugula
Differential Revision: https://reviews.llvm.org/D81609
This parameter gives the developers the freedom to choose their desired function
signature conversion for preparing their functions for buffer placement. It is
introduced for BufferAssignmentFuncOpConverter, and also for
BufferAssignmentReturnOpConverter, and BufferAssignmentCallOpConverter to adapt
the return and call operations with the selected function signature conversion.
If the parameter is set, buffer placement won't also deallocate the returned
buffers.
Differential Revision: https://reviews.llvm.org/D81137
This revision adds a helper function to hoist vector.transfer_read /
vector.transfer_write pairs out of immediately enclosing scf::ForOp
iteratively, if the following conditions are true:
1. The 2 ops access the same memref with the same indices.
2. All operands are invariant under the enclosing scf::ForOp.
3. No uses of the memref either dominate the transfer_read or are
dominated by the transfer_write (i.e. no aliasing between the write and
the read across the loop)
To improve hoisting opportunities, call the `moveLoopInvariantCode` helper
function on the candidate loop above which to hoist. Hoisting the transfers
results in scf::ForOp yielding the value that originally transited through
memory.
This revision additionally exposes `moveLoopInvariantCode` as a helper in
LoopUtils.h and updates SliceAnalysis to support return scf::For values and
allow hoisting across multiple scf::ForOps.
Differential Revision: https://reviews.llvm.org/D81199
This patch enables affine loop fusion for loops with affine vector loads
and stores. For that, we only had to use affine memory op interfaces in
LoopFusionUtils.cpp and Utils.cpp so that vector loads and stores are
also taken into account.
Reviewed By: andydavis1, ftynse
Differential Revision: https://reviews.llvm.org/D80971
Dialect conversion infrastructure supports 1->N type conversions by requiring
individual conversions to provide facilities to generate operations
retrofitting N values into 1 of the original type when N > 1. This
functionality can also be used to materialize explicit "cast"-like operations,
but it did not support 1->1 type conversions until now. Modify TypeConverter to
support materialization of cast operations for 1-1 conversions.
This also makes materialization specification more extensible following the
same pattern as type conversions. Instead of overloading a virtual function,
users or subclasses of TypeConversion can now register type-specific
materialization callbacks that will be called in order for the given type.
Differential Revision: https://reviews.llvm.org/D79729
Add BufferAssignmentCallOpConverter as a pattern rewriter for Buffer
Placement. It matches the signature of the caller operation with the callee
after rewriting the callee with FunctionAndBlockSignatureConverter.
Differential Revision: https://reviews.llvm.org/D80785
Buffer placement can now operates on functions that return buffers. These
buffers escape from the deallocation phase of buffer placement.
Differential Revision: https://reviews.llvm.org/D80696
PatternRewriter has support for erasing a Block from its parent region, but
this feature has not been implemented for ConversionPatternRewriter that needs
to keep track of and be able to undo block actions. Introduce support for
undoing block erasure in the ConversionPatternRewriter by marking all the ops
it contains for erasure and by detaching the block from its parent region. The
detached block is stored in the action description and is not actually deleted
until the rewrites are applied.
Differential Revision: https://reviews.llvm.org/D80135
Dialect conversion infrastructure may roll back op creation by erasing the
operations in the reverse order of their creation. While this guarantees uses
of values will be deleted before their definitions, this does not guarantee
that a parent operation will not be deleted before its child. (This may happen
in case of block inlining or if child operations, such as terminators, are
created in the parent's `build` function before the parent itself.) Handle the
parent/child relationship between ops by removing all child ops from the blocks
before erasing the parent. The child ops remain live, detached from a block,
and will be safely destroyed in their turn, which may come later than that of
the parent.
Differential Revision: https://reviews.llvm.org/D80134
This patch introduces interfaces for read and write ops with affine
restrictions. I used `read`/`write` intead of `load`/`store` for the
interfaces so that they can also be implemented by dma ops.
For now, they are only implemented by affine.load, affine.store,
affine.vector_load and affine.vector_store.
For testing purposes, this patch also migrates affine loop fusion and
required analysis to use the new interfaces. No other changes are made
beyond that.
Co-authored-by: Alex Zinenko <zinenko@google.com>
Reviewed By: bondhugula, ftynse
Differential Revision: https://reviews.llvm.org/D79829
Making these two converters more generic. FunctionAndBlockSignatureConverter now
moves only memref results (after type conversion) to the function argument and
keeps other legal function results unchanged. NonVoidToVoidReturnOpConverter is
renamed to NoBufferOperandsReturnOpConverter. It removes only the buffer
operands from the operands of the converted ReturnOp and inserts CopyOps to copy
each buffer to the target function argument.
Differential Revision: https://reviews.llvm.org/D79329
Summary:
This makes a common pattern of
`dyn_cast_or_null<OpTy>(v.getDefiningOp())` more concise.
Differential Revision: https://reviews.llvm.org/D79681
This dialect contains various structured control flow operaitons, not only
loops, reflect this in the name. Drop the Ops suffix for consistency with other
dialects.
Note that this only moves the files and changes the C++ namespace from 'loop'
to 'scf'. The visible IR prefix remains the same and will be updated
separately. The conversions will also be updated separately.
Differential Revision: https://reviews.llvm.org/D79578
The list of destination load ops while evaluating producer-consumer
fusion wasn't being maintained as a set, and as such, duplicate load ops
were being added to it. Although this is harmless correctness-wise, it's
a killer efficiency-wise and it prevents interesting/useful fusions
(including for eg. reshapes into a matmul). The reason the latter
fusions would be missed is that a slice union would be unnecessarily
needed due to the duplicate load ops on a memref added to the 'dst
loads' list. Since slice union is unimplemented for the local var case,
a single destination load op that leads to local vars (like a floordiv /
mod producing fusion), a common case, would not get fused due to an
unnecessary union being tried with itself. (The union would actually be
the same thing but we would bail out.)
Besides the above, this would also significantly speed up fusion as all
the unnecessary slice computations / unions, checks, etc. due to the
duplicates go away.
Differential Revision: https://reviews.llvm.org/D79547
Essentially takes the lld/Common/Threads.h wrappers and moves them to
the llvm/Support/Paralle.h algorithm header.
The changes are:
- Remove policy parameter, since all clients use `par`.
- Rename the methods to `parallelSort` etc to match LLVM style, since
they are no longer C++17 pstl compatible.
- Move algorithms from llvm::parallel:: to llvm::, since they have
"parallel" in the name and are no longer overloads of the regular
algorithms.
- Add range overloads
- Use the sequential algorithm directly when 1 thread is requested
(skips task grouping)
- Fix the index type of parallelForEachN to size_t. Nobody in LLVM was
using any other parameter, and it made overload resolution hard for
for_each_n(par, 0, foo.size(), ...) because 0 is int, not size_t.
Remove Threads.h and update LLD for that.
This is a prerequisite for parallel public symbol processing in the PDB
library, which is in LLVM.
Reviewed By: MaskRay, aganea
Differential Revision: https://reviews.llvm.org/D79390
Summary:
Adds the loop unroll transformation for loop::ForOp.
Adds support for promoting the body of single-iteration loop::ForOps into its containing block.
Adds check tests for loop::ForOps with dynamic and static lower/upper bounds and step.
Care was taken to share code (where possible) with the AffineForOp unroll transformation to ease maintenance and potential future transition to a LoopLike construct on which loop transformations for different loop types can implemented.
Reviewers: ftynse, nicolasvasilache
Reviewed By: ftynse
Subscribers: bondhugula, mgorny, zzheng, mehdi_amini, rriddle, jpienaar, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, Joonsoo, grosul1, frgossen, Kayjukh, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D79184
This revision adds support for merging identical blocks, or those with the same operations that branch to the same successors. Operands that mismatch between the different blocks are replaced with new block arguments added to the merged block.
Differential Revision: https://reviews.llvm.org/D79134
This allows for walking the operations nested directly within a region, without traversing nested regions.
Differential Revision: https://reviews.llvm.org/D79056
- Exports MLIR targets to be used out-of-tree.
- mimicks `add_clang_library` and `add_flang_library`.
- Fixes libMLIR.so
After https://reviews.llvm.org/D77515 libMLIR.so was no longer containing
any object files. We originally had a cludge there that made it work with
the static initalizers and when switchting away from that to the way the
clang shlib does it, I noticed that MLIR doesn't create a `obj.{name}` target,
and doesn't export it's targets to `lib/cmake/mlir`.
This is due to MLIR using `add_llvm_library` under the hood, which adds
the target to `llvmexports`.
Differential Revision: https://reviews.llvm.org/D78773
[MLIR] Fix libMLIR.so and LLVM_LINK_LLVM_DYLIB
Primarily, this patch moves all mlir references to LLVM libraries into
either LLVM_LINK_COMPONENTS or LINK_COMPONENTS. This enables magic in
the llvm cmake files to automatically replace reference to LLVM components
with references to libLLVM.so when necessary. Among other things, this
completes fixing libMLIR.so, which has been broken for some configurations
since D77515.
Unlike previously, the pattern is now that mlir libraries should almost
always use add_mlir_library. Previously, some libraries still used
add_llvm_library. However, this confuses the export of targets for use
out of tree because libraries specified with add_llvm_library are exported
by LLVM. Instead users which don't need/can't be linked into libMLIR.so
can specify EXCLUDE_FROM_LIBMLIR
A common error mode is linking with LLVM libraries outside of LINK_COMPONENTS.
This almost always results in symbol confusion or multiply defined options
in LLVM when the same object file is included as a static library and
as part of libLLVM.so. To catch these errors more directly, there's now
mlir_check_all_link_libraries.
To simplify usage of add_mlir_library, we assume that all mlir
libraries depend on LLVMSupport, so it's not necessary to separately specify
it.
tested with:
BUILD_SHARED_LIBS=on,
BUILD_SHARED_LIBS=off + LLVM_BUILD_LLVM_DYLIB,
BUILD_SHARED_LIBS=off + LLVM_BUILD_LLVM_DYLIB + LLVM_LINK_LLVM_DYLIB.
By: Stephen Neuendorffer <stephen.neuendorffer@xilinx.com>
Differential Revision: https://reviews.llvm.org/D79067
[MLIR] Move from using target_link_libraries to LINK_LIBS
This allows us to correctly generate dependencies for derived targets,
such as targets which are created for object libraries.
By: Stephen Neuendorffer <stephen.neuendorffer@xilinx.com>
Differential Revision: https://reviews.llvm.org/D79243
Three commits have been squashed to avoid intermediate build breakage.
The current BufferPlacement implementation tries to find Alloc and Dealloc
operations in order to move them. However, this is a tight coupling to
standard-dialect ops which has been removed in this CL.
Differential Revision: https://reviews.llvm.org/D78993
This is useful for several reasons:
* In some situations the user can guarantee that thread-safety isn't necessary and don't want to pay the cost of synchronization, e.g., when parsing a very large module.
* For things like logging threading is not desirable as the output is not guaranteed to be in stable order.
This flag also subsumes the pass manager flag for multi-threading.
Differential Revision: https://reviews.llvm.org/D79266
These libraries are distinct from other things in Analysis in that they
operate only on core IR concepts. This also simplifies dependencies
so that Dialect -> Analysis -> Parser -> IR. Previously, the parser depended
on portions of the the Analysis directory as well, which sometimes
caused issues with the way the cmake makefile generator discovers
dependencies on generated files during compilation.
Differential Revision: https://reviews.llvm.org/D79240
The current OpBuilder has a set of virtual functions required by the fact that the PatternRewriter inherits from it for convenience. The PatternRewriter is required to know about IR mutations for correctness. This revision changes the relationship to be explicit by having users register a listener with the builder instead of using inheritance/vtables. This still requires that users properly transfer the listener when creating new builders, but has several benefits:
* More than one builder can be created during pattern rewrites(assuming that the listener is properly forwarded)
* OpBuilder no longer requires a vtable, and thus does not incur the cost when a listener isn't present.
Differential Revision: https://reviews.llvm.org/D79206
There are three op conversion modes: Partial, Full, and Analysis. This change modifies the Partial mode to optionally take a set of non-legalizable ops. If this parameter is specified, all ops that are not legalizable (i.e. would cause full conversion to fail) are tracked throughout the partial legalization.
Differential Revision: https://reviews.llvm.org/D78788
This range allows for performing many different operations on successor operands, including erasing/adding/setting. This removes the need for the explicit canEraseSuccessorOperand and eraseSuccessorOperand methods.
Differential Revision: https://reviews.llvm.org/D79077
This provides a general hash and comparison for checking if two operations are equivalent. This revision also optimizes the handling of result types to take advantage of how result types are stored on the operation.
Differential Revision: https://reviews.llvm.org/D79029
Makes the relationship and function clearer. Accordingly rename getAttrList to getMutableAttrDict.
Differential Revision: https://reviews.llvm.org/D79125
We have provided a generic buffer assignment transformation ported from
TensorFlow. This generic transformation pass automatically analyzes the values
and their aliases (also in other blocks) and returns the valid positions for
Alloc and Dealloc operations. To find these positions, the algorithm uses the
block Dominator and Post-Dominator analyses. In our proposed algorithm, we have
considered aliasing, liveness, nested regions, branches, conditional branches,
critical edges, and independency to custom block terminators. This
implementation doesn't support block loops. However, we have considered this in
our design. For this purpose, it is only required to have a loop analysis to
insert Alloc and Dealloc operations outside of these loops in some special
cases.
Differential Revision: https://reviews.llvm.org/D78484
This revision adds support for propagating constants across symbol-based callgraph edges. It uses the existing Call/CallableOpInterfaces to detect the dataflow edges, and propagates constants through arguments and out of returns.
Differential Revision: https://reviews.llvm.org/D78592
This provides a much cleaner interface into Symbols, and allows for users to start injecting op-specific information. For example, derived op can now inject when a symbol can be discarded if use_empty. This would let us drop unused external functions, which generally have public visibility.
This revision also adds a new `extraTraitClassDeclaration` field to ODS OpInterface to allow for injecting declarations into the trait class that gets attached to the operations.
Differential Revision: https://reviews.llvm.org/D78522
Many ops with this trait have `getBody()` and `getBodyBuilder()` methods defined in `extraClassDeclaration` in tablegen. `getBody()` implementation is the same accross all these ops, but `getBodyBuilder()` can return builders with varying insertion points set. In this PR, `getBody()` is moved into `SingleImplicitBlockTerminator` struct and `getBodyBuilder()` is replaced with `OpBuilder::atBlock(End|Terminator)(op.getBody);`.
Differential Revision: https://reviews.llvm.org/D78864
This revision refactors the structure of the operand storage such that there is no additional memory cost for resizable operand lists until it is required. This is done by using two different internal representations for the operand storage:
* One using trailing operands
* One using a dynamically allocated std::vector<OpOperand>
This allows for removing the resizable operand list bit, and will free up APIs from needing to workaround non-resizable operand lists.
Differential Revision: https://reviews.llvm.org/D78875
The current implementation of this method performs the replacement directly, and thus doesn't support proper back tracking.
Differential Revision: https://reviews.llvm.org/D78790
This is possible by adding two new ControlFlowInterface additions:
- A new interface, RegionBranchOpInterface
This interface allows for region holding operations to describe how control flows between regions. This interface initially contains two methods:
* getSuccessorEntryOperands
Returns the operands of this operation used as the entry arguments when entering the region at `index`, which was specified as a successor by `getSuccessorRegions`. when entering. These operands should correspond 1-1 with the successor inputs specified in `getSuccessorRegions`, and may be a subset of the entry arguments for that region.
* getSuccessorRegions
Returns the viable successors of a region, or the possible successor when branching from the parent op. This allows for describing which regions may be executed when entering an operation, and which regions are executed after having executed another region of the parent op. For example, a structured loop operation may always enter into the loop body region. The loop body region may branch back to itself, or exit to the operation.
- A trait, ReturnLike
This trait signals that a terminator exits a region and forwards all of its operands as "exiting" values.
These additions allow for performing more general dataflow analysis in the presence of region holding operations.
Differential Revision: https://reviews.llvm.org/D78447
This revision adds the initial pass for performing SCCP generically in MLIR. SCCP is an algorithm for propagating constants across control flow, and optimistically assumes all values to be constant unless proven otherwise. It currently supports branching control, with support for regions and inter-procedural propagation being added in followups.
Differential Revision: https://reviews.llvm.org/D78397
The previous code result a mismatch between block argument types and
predecessor successor args when a type conversion was needed in a
multiblock case. It was assuming the replaced result types matched the
region result types.
Also, slighly improve the debug output from the inliner.
Differential Revision: https://reviews.llvm.org/D78415
Rename mlir::tileCodeGen -> mlir::tilePerfectlyNested to be consistent.
NFC clean up tiling utility code, drop dead code, better comments.
Expose isPerfectlyNested and reuse.
Differential Revision: https://reviews.llvm.org/D78423
There were some unused CMakeFiles for Affine/IR and Affine/EDSC.
This change builds separate MLIRAffineOps and MLIRAffineEDSC libraries
using those CMakeFiles. This combination replaces the old MLIRAffine
library.
Differential Revision: https://reviews.llvm.org/D78317
This avoids asan failures as more calls may be added during inlining, invalidating the reference.
Differential Revision: https://reviews.llvm.org/D78258
Summary:
Modified AffineMap::get to remove support for the overload which allowed
an ArrayRef of AffineExpr but no context (and gathered the context from a
presumed first entry, resulting in bugs when there were 0 results).
Instead, we support only a ArrayRef and a context, and a version which
takes a single AffineExpr.
Additionally, removed some now needless case logic which previously
special cased which call to AffineMap::get to use.
Reviewers: flaub, bondhugula, rriddle!, nicolasvasilache, ftynse, ulysseB, mravishankar, antiagainst, aartbik
Subscribers: mehdi_amini, jpienaar, burmako, shauheen, antiagainst, arpith-jacob, mgester, lucyrfox, liufengdb, Joonsoo, bader, grosul1, frgossen, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D78226
Introduce mlir::applyOpPatternsAndFold which applies patterns as well as
any folding only on a specified op (in contrast to
applyPatternsAndFoldGreedily which applies patterns only on the regions
of an op isolated from above). The caller is made aware of the op being
folded away or erased.
Depends on D77485.
Differential Revision: https://reviews.llvm.org/D77487
This class implements a switch-like dispatch statement for a value of 'T' using dyn_cast functionality. Each `Case<T>` takes a callable to be invoked if the root value isa<T>, the callable is invoked with the result of dyn_cast<T>() as a parameter.
Differential Revision: https://reviews.llvm.org/D78070
These have proved incredibly useful for interleaving values between a range w.r.t to streams. After this revision, the mlir/Support/STLExtras.h is empty. A followup revision will remove it from the tree.
Differential Revision: https://reviews.llvm.org/D78067
This revision moves the various range utilities present in MLIR to LLVM to enable greater reuse. This revision moves the following utilities:
* indexed_accessor_*
This is set of utility iterator/range base classes that allow for building a range class where the iterators are represented by an object+index pair.
* make_second_range
Given a range of pairs, returns a range iterating over the `second` elements.
* hasSingleElement
Returns if the given range has 1 element. size() == 1 checks end up being very common, but size() is not always O(1) (e.g., ilist). This method provides O(1) checks for those cases.
Differential Revision: https://reviews.llvm.org/D78064
This makes no impact on the test cases because affine-data-copy-generate
runs whole function canonicalization at its end; however, the latter
will be removed in a pending revision. It is thus useful to clean up
these affine.applys right here, and eventually, not even generate
these (when the right API to compose by construction is in place).
Differential Revision: https://reviews.llvm.org/D78055
OperatioFolder::tryToFold performs both true folding and in a few
instances in-place updates through op rewrites. In the latter case, we
should still be applying the supplied pattern rewrites in the same
iteration; however this wasn't the case since tryToFold returned
success() for both true folding and in-place updates, and the patterns
for the in-place updated ops were being applied only in the next
iteration of the driver's outer loop. This fix would make it converge
faster.
Differential Revision: https://reviews.llvm.org/D77485
Rename mlir::applyPatternsGreedily -> applyPatternsAndFoldGreedily. The
new name is a more accurate description of the method - it performs
both, application of the specified patterns and folding of all ops in
the op's region irrespective of whether any patterns have been supplied.
Differential Revision: https://reviews.llvm.org/D77478
Summary: Some pattern rewriters, like dialect conversion, prohibit the unbounded recursion(or reapplication) of patterns on generated IR. Most patterns are not written with recursive application in mind, so will generally explode the stack if uncaught. This revision adds a hook to RewritePattern, `hasBoundedRewriteRecursion`, to signal that the pattern can safely be applied to the generated IR of a previous application of the same pattern. This allows for establishing a contract between the pattern and rewriter that the pattern knows and can handle the potential recursive application.
Differential Revision: https://reviews.llvm.org/D77782
Summary: Pass options are a better choice for various reasons and avoid the need for static constructors.
Differential Revision: https://reviews.llvm.org/D77707
Summary:
This is much cleaner, and fits the same structure as many other tablegen backends. This was not done originally as the CRTP in the pass classes made it overly verbose/complex.
Differential Revision: https://reviews.llvm.org/D77367
This revision removes all of the CRTP from the pass hierarchy in preparation for using the tablegen backend instead. This creates a much cleaner interface in the C++ code, and naturally fits with the rest of the infrastructure. A new utility class, PassWrapper, is added to replicate the existing behavior for passes not suitable for using the tablegen backend.
Differential Revision: https://reviews.llvm.org/D77350
ModulePass doesn't provide any special utilities and thus doesn't give enough benefit to warrant a special pass class. This revision replaces all usages with the more general OperationPass.
Differential Revision: https://reviews.llvm.org/D77339
Fix point-wise copy generation to work with bounds that have max/min.
Change structure of copy loop nest to use absolute loop indices and
subtracting base from the indexes of the fast buffers. Update supporting
utilities: Fix FlatAffineConstraints::getLowerAndUpperBound to look at
equalities as well and for a missing division. Update unionBoundingBox
to not discard common constraints (leads to a tighter system). Update
MemRefRegion::getConstantBoundingSizeAndShape to add memref dimension
constraints. Run removeTrivialRedundancy at the end of
MemRefRegion::compute. Run single iteration loop promotion and
load/store canonicalization after affine data copy (in its test pass as
well).
Differential Revision: https://reviews.llvm.org/D77320
Add a pattern rewriter utility to erase blocks (while notifying the
pattern rewriting driver of the erased ops). Use this to remove trivial
else blocks in affine.if ops.
Differential Revision: https://reviews.llvm.org/D77083
Removing dead ops should make the outer loop of the pattern rewriting
driver run again. Although its operands are added to the worklist, if no
changes happenned to them or remaining ops in the worklist, the driver
wouldn't run once again - but it should be.
Differential Revision: https://reviews.llvm.org/D77483
PatternRewriter and derived classes provide a set of virtual methods to
manipulate blocks, which ConversionPatternRewriter overrides to keep track of
the manipulations and undo them in case the conversion fails. However, one can
currently create a block only by splitting another block into two. This not
only makes the API inconsistent (`splitBlock` is allowed in conversion
patterns, but `createBlock` is not), but it also make it impossible for one to
create blocks with argument lists different from those of already existing
blocks since in-place block updates are not supported either. Such
functionality precludes dialect conversion infrastructure from being used more
extensively on region-containing ops, for example, for value-returning "if"
operations. At the same time, ConversionPatternRewriter already allows one to
undo block creation as block creation is one of the primitive operations in
already supported region inlining.
Support block creation in conversion patterns by hooking `createBlock` on the
block action undo mechanism. This requires to make `Builder::createBlock`
virtual, similarly to Op insertion. This is a minimal change to the Builder
infrastructure that will later help support additional use cases such as block
signature changes. `createBlock` now additionally takes the types of the block
arguments that are added immediately so as to avoid in-place argument list
manipulation that would be illegal in conversion patterns.
Add a method that given an affine map returns another with just its unique
results. Use this to drop redundant bounds in max/min for affine.for. Update
affine.for's canonicalization pattern and createCanonicalizedForOp to use
this.
Differential Revision: https://reviews.llvm.org/D77237
Modernize/cleanup code in loop transforms utils - a lot of this code was
written prior to the currently available IR support / code style. This
patch also does some variable renames including inst -> op, comment
updates, turns getCleanupLoopLowerBound into a local function.
Differential Revision: https://reviews.llvm.org/D77175
This revision adds support for generating utilities for passes such as options/statistics/etc. that can be inferred from the tablegen definition. This removes additional boilerplate from the pass, and also makes it easier to remove the reliance on the pass registry to provide certain things(e.g. the pass argument).
Differential Revision: https://reviews.llvm.org/D76659
This will greatly simplify a number of things related to passes:
* Enables generation of pass registration
* Enables generation of boiler plate pass utilities
* Enables generation of pass documentation
This revision focuses on adding the basic structure and adds support for generating the registration for passes in the Transforms/ directory. Future revisions will add more support and move more passes over.
Differential Revision: https://reviews.llvm.org/D76656
Rewrite mlir::permuteLoops (affine loop permutation utility) to fix
incorrect approach. Avoiding using sinkLoops entirely - use single move
approach. Add test pass.
This fixes https://bugs.llvm.org/show_bug.cgi?id=45328
Depends on D77003.
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Differential Revision: https://reviews.llvm.org/D77004
Add missing assert checks for input to mlir::interchangeLoops utility.
Rename interchangeLoops -> permuteLoops; update doc comments to clarify
inputs / return val. Other than the assert checks, this is NFC.
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Differential Revision: https://reviews.llvm.org/D77003
This patch introduces a utility to separate full tiles from partial
tiles when tiling affine loop nests where trip counts are unknown or
where tile sizes don't divide trip counts. A conditional guard is
generated to separate out the full tile (with constant trip count loops)
into the then block of an 'affine.if' and the partial tile to the else
block. The separation allows the 'then' block (which has constant trip
count loops) to be optimized better subsequently: for eg. for
unroll-and-jam, register tiling, vectorization without leading to
cleanup code, or to offload to accelerators. Among techniques from the
literature, the if/else based separation leads to the most compact
cleanup code for multi-dimensional cases (because a single version is
used to model all partial tiles).
INPUT
affine.for %i0 = 0 to %M {
affine.for %i1 = 0 to %N {
"foo"() : () -> ()
}
}
OUTPUT AFTER TILING W/O SEPARATION
map0 = affine_map<(d0) -> (d0)>
map1 = affine_map<(d0)[s0] -> (d0 + 32, s0)>
affine.for %arg2 = 0 to %M step 32 {
affine.for %arg3 = 0 to %N step 32 {
affine.for %arg4 = #map0(%arg2) to min #map1(%arg2)[%M] {
affine.for %arg5 = #map0(%arg3) to min #map1(%arg3)[%N] {
"foo"() : () -> ()
}
}
}
}
OUTPUT AFTER TILING WITH SEPARATION
map0 = affine_map<(d0) -> (d0)>
map1 = affine_map<(d0) -> (d0 + 32)>
map2 = affine_map<(d0)[s0] -> (d0 + 32, s0)>
#set0 = affine_set<(d0, d1)[s0, s1] : (-d0 + s0 - 32 >= 0, -d1 + s1 - 32 >= 0)>
affine.for %arg2 = 0 to %M step 32 {
affine.for %arg3 = 0 to %N step 32 {
affine.if #set0(%arg2, %arg3)[%M, %N] {
// Full tile.
affine.for %arg4 = #map0(%arg2) to #map1(%arg2) {
affine.for %arg5 = #map0(%arg3) to #map1(%arg3) {
"foo"() : () -> ()
}
}
} else {
// Partial tile.
affine.for %arg4 = #map0(%arg2) to min #map2(%arg2)[%M] {
affine.for %arg5 = #map0(%arg3) to min #map2(%arg3)[%N] {
"foo"() : () -> ()
}
}
}
}
}
The separation is tested via a cmd line flag on the loop tiling pass.
The utility itself allows one to pass in any band of contiguously nested
loops, and can be used by other transforms/utilities. The current
implementation works for hyperrectangular loop nests.
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Differential Revision: https://reviews.llvm.org/D76700
This allows conversion of a ParallelLoop from N induction variables to
some nuber of induction variables less than N.
The first intended use of this is for the GPUDialect to convert
ParallelLoops to iterate over 3 dimensions so they can be launched as
GPU Kernels.
To implement this:
- Normalize each iteration space of the ParallelLoop
- Use the same induction variable in a new ParallelLoop for multiple
original iterations.
- Split the new induction variable back into the original set of values
inside the body of the ParallelLoop.
Subscribers: mgorny, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, Joonsoo, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D76363
The declarations for these were already part of transforms utils, but
the definitions were left in affine transforms. Move definitions to loop
transforms utils.
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Differential Revision: https://reviews.llvm.org/D76633
When trying to fold an operation during operation creation check that
the operation folding succeeds before inserting the op.
Differential Revision: https://reviews.llvm.org/D76415
Move some of the affine transforms and their test cases to their
respective dialect directory. This patch does not complete the move, but
takes care of a good part.
Renames: prefix 'affine' to affine loop tiling cl options,
vectorize -> super-vectorize
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Differential Revision: https://reviews.llvm.org/D76565
Summary:
Change AffineOps Dialect structure to better group both IR and Tranforms. This included extracting transforms directly related to AffineOps. Also move AffineOps to Affine.
Differential Revision: https://reviews.llvm.org/D76161
OperationFolder::tryToFold was running the pre-replacement
action even when there was no constant folding, i.e., when the operation
was just being updated in place but was not going to be replaced. This
led to nested ops being unnecessarily removed from the worklist and only
being processed in the next outer iteration of the greedy pattern
rewriter, which is also why this didn't affect the final output IR but
only the convergence rate. It also led to an op's results' users to be
unnecessarily added to the worklist.
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Differential Revision: https://reviews.llvm.org/D76268
Summary: This is somewhat complex(annoying) as it involves directly tracking the uses within each of the callgraph nodes, and updating them as needed during inlining. The benefit of this is that we can have a more exact cost model, enable inlining some otherwise non-inlinable cases, and also ensure that newly dead callables are properly disposed of.
Differential Revision: https://reviews.llvm.org/D75476
Summary:
This revision adds a new hook, `notifyMatchFailure`, that allows for notifying the rewriter that a match failure is coming with the provided reason. This hook takes as a parameter a callback that fills a `Diagnostic` instance with the reason why the match failed. This allows for the rewriter to decide how this information can be displayed to the end-user, and may completely ignore it if desired(opt mode). For now, DialectConversion is updated to include this information in the debug output.
Differential Revision: https://reviews.llvm.org/D76203
Summary: PatternState was a mechanism to pass state between the match and rewrite calls of a RewritePattern. With the rise of matchAndRewrite, this class is unused and unnecessary. This revision removes PatternState and simplifies PatternMatchResult to just be a LogicalResult. A future revision will replace all usages of PatternMatchResult/matchSuccess/matchFailure with LogicalResult equivalents.
Differential Revision: https://reviews.llvm.org/D76202
- rename vars that had inst suffixes (due to ops earlier being
known as insts); other renames for better readability
- drop unnecessary matches in test cases
- iterate without block terminator
- comment/doc updates
- instBodySkew -> affineForOpBodySkew
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Differential Revision: https://reviews.llvm.org/D76214
Summary:
- remove stale declarations on flat affine constraints
- avoid allocating small vectors where possible
- clean up code comments, rename some variables
Differential Revision: https://reviews.llvm.org/D76117
Summary: A number of transform import StandardOps despite not being dependent on it. Cleaned it up to better understand what dialects each of these transforms depend on.
Differential Revision: https://reviews.llvm.org/D76112
HasNoSideEffect can now be implemented using the MemoryEffectInterface, removing the need to check multiple things for the same information. This also removes an easy foot-gun for users as 'Operation::hasNoSideEffect' would ignore operations that dynamically, or recursively, have no side effects. This also leads to an immediate improvement in some of the existing users, such as DCE, now that they have access to more information.
Differential Revision: https://reviews.llvm.org/D76036
The current mechanism for identifying is a bit hacky and extremely adhoc, i.e. we explicit check 1-result, 0-operand, no side-effect, and always foldable and then assume that this is a constant. Adding a trait adds structure to this, and makes checking for a constant much more efficient as we can guarantee that all of these things have already been verified.
Differential Revision: https://reviews.llvm.org/D76020
These terminator operations don't really have any side effects, and this allows for more accurate side-effect analysis for region operations. For example, currently we can't detect like a loop.for or affine.for are dead because the affine.terminator is "side effecting".
Note: Marking as NoSideEffect doesn't mean that these operations can be opaquely erased.
Differential Revision: https://reviews.llvm.org/D75888
Summary:
affineDataCopyGenerate is a monolithinc function that
combines several steps for good reasons, but it makes customizing
the behaivor even harder. The major two steps by affineDataCopyGenerate are:
a) Identify interesting memrefs and collect their uses.
b) Create new buffers to forward these uses.
Step (a) actually has requires tremendous customization options. One could see
that from the recently added filterMemRef parameter.
This patch adds a function that only does (b), in the hope that (a)
can be directly implemented by the callers. In fact, (a) is quite
simple if the caller has only one buffer to consider, or even one use.
Differential Revision: https://reviews.llvm.org/D75965
Summary:
Interfaces/ is the designated directory for these types of interfaces, and also removes the need for including them directly in IR/.
Differential Revision: https://reviews.llvm.org/D75886
The interfaces themselves aren't really analyses, they may be used by analyses though. Having them in Analysis can also create cyclic dependencies if an analysis depends on a specific dialect, that also provides one of the interfaces.
Differential Revision: https://reviews.llvm.org/D75867
Summary:
The old interface was a temporary stopgap to allow for implementing simple LICM that took side effects of region operations into account. Now that MLIR has proper support for specifying memory effects, this interface can be deleted.
Differential Revision: https://reviews.llvm.org/D74441
add convenience method for affine data copy generation for a loop body
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Differential Revision: https://reviews.llvm.org/D75822
Putting this up mainly for discussion on
how this should be done. I am interested in MLIR from
the Julia side and we currently have a strong preference
to dynamically linking against the LLVM shared library,
and would like to have a MLIR shared library.
This patch adds a new cmake function add_mlir_library()
which accumulates a list of targets to be compiled into
libMLIR.so. Note that not all libraries make sense to
be compiled into libMLIR.so. In particular, we want
to avoid libraries which primarily exist to support
certain tools (such as mlir-opt and mlir-cpu-runner).
Note that the resulting libMLIR.so depends on LLVM, but
does not contain any LLVM components. As a result, it
is necessary to link with libLLVM.so to avoid linkage
errors. So, libMLIR.so requires LLVM_BUILD_LLVM_DYLIB=on
FYI, Currently it appears that LLVM_LINK_LLVM_DYLIB is broken
because mlir-tblgen is linked against libLLVM.so and
and independent LLVM components.
Previous version of this patch broke depencies on TableGen
targets. This appears to be because it compiled all
libraries to OBJECT libraries (probably because cmake
is generating different target names). Avoiding object
libraries results in correct dependencies.
(updated by Stephen Neuendorffer)
Differential Revision: https://reviews.llvm.org/D73130
add_llvm_library and add_llvm_executable may need to create new targets with
appropriate dependencies. As a result, it is not sufficient in some
configurations (namely LLVM_BUILD_LLVM_DYLIB=on) to only call
add_dependencies(). Instead, the explicit TableGen dependencies must
be passed to add_llvm_library() or add_llvm_executable() using the DEPENDS
keyword.
Differential Revision: https://reviews.llvm.org/D74930
CMake allows calling target_link_libraries() without a keyword,
but this usage is not preferred when also called with a keyword,
and has surprising behavior. This patch explicitly specifies a
keyword when using target_link_libraries().
Differential Revision: https://reviews.llvm.org/D75725
Summary:
This revision removes all of the functionality related to successor operands on the core Operation class. This greatly simplifies a lot of handling of operands, as well as successors. For example, DialectConversion no longer needs a special "matchAndRewrite" for branching terminator operations.(Note, the existing method was also broken for operations with variadic successors!!)
This also enables terminator operations to define their own relationships with successor arguments, instead of the hardcoded "pass-through" behavior that exists today.
Differential Revision: https://reviews.llvm.org/D75318
The existing API for successor operands on operations is in the process of being removed. This revision simplifies a later one that completely removes the existing API.
Differential Revision: https://reviews.llvm.org/D75316
Summary:
Make computeConversionSet bubble up errors from nested regions. Note
that this doesn't change top-level behavior - since the nested region
calls emitError, the error was visible before, just not surfaced as
quickly.
Differential Revision: https://reviews.llvm.org/D75369
Summary: For example, DenseElementsAttr currently does not properly round-trip unsigned integer values.
Differential Revision: https://reviews.llvm.org/D75374
Putting this up mainly for discussion on
how this should be done. I am interested in MLIR from
the Julia side and we currently have a strong preference
to dynamically linking against the LLVM shared library,
and would like to have a MLIR shared library.
This patch adds a new cmake function add_mlir_library()
which accumulates a list of targets to be compiled into
libMLIR.so. Note that not all libraries make sense to
be compiled into libMLIR.so. In particular, we want
to avoid libraries which primarily exist to support
certain tools (such as mlir-opt and mlir-cpu-runner).
Note that the resulting libMLIR.so depends on LLVM, but
does not contain any LLVM components. As a result, it
is necessary to link with libLLVM.so to avoid linkage
errors. So, libMLIR.so requires LLVM_BUILD_LLVM_DYLIB=on
FYI, Currently it appears that LLVM_LINK_LLVM_DYLIB is broken
because mlir-tblgen is linked against libLLVM.so and
and independent LLVM components.
Previous version of this patch broke depencies on TableGen
targets. This appears to be because it compiled all
libraries to OBJECT libraries (probably because cmake
is generating different target names). Avoiding object
libraries results in correct dependencies.
(updated by Stephen Neuendorffer)
Differential Revision: https://reviews.llvm.org/D73130
add_llvm_library and add_llvm_executable may need to create new targets with
appropriate dependencies. As a result, it is not sufficient in some
configurations (namely LLVM_BUILD_LLVM_DYLIB=on) to only call
add_dependencies(). Instead, the explicit TableGen dependencies must
be passed to add_llvm_library() or add_llvm_executable() using the DEPENDS
keyword.
Differential Revision: https://reviews.llvm.org/D74930
When compiling libLLVM.so, add_llvm_library() manipulates the link libraries
being used. This means that when using add_llvm_library(), we need to pass
the list of libraries to be linked (using the LINK_LIBS keyword) instead of
using the standard target_link_libraries call. This is preparation for
properly dealing with creating libMLIR.so as well.
Differential Revision: https://reviews.llvm.org/D74864
Putting this up mainly for discussion on
how this should be done. I am interested in MLIR from
the Julia side and we currently have a strong preference
to dynamically linking against the LLVM shared library,
and would like to have a MLIR shared library.
This patch adds a new cmake function add_mlir_library()
which accumulates a list of targets to be compiled into
libMLIR.so. Note that not all libraries make sense to
be compiled into libMLIR.so. In particular, we want
to avoid libraries which primarily exist to support
certain tools (such as mlir-opt and mlir-cpu-runner).
Note that the resulting libMLIR.so depends on LLVM, but
does not contain any LLVM components. As a result, it
is necessary to link with libLLVM.so to avoid linkage
errors. So, libMLIR.so requires LLVM_BUILD_LLVM_DYLIB=on
FYI, Currently it appears that LLVM_LINK_LLVM_DYLIB is broken
because mlir-tblgen is linked against libLLVM.so and
and independent LLVM components
(updated by Stephen Neuendorffer)
Differential Revision: https://reviews.llvm.org/D73130
add_llvm_library and add_llvm_executable may need to create new targets with
appropriate dependencies. As a result, it is not sufficient in some
configurations (namely LLVM_BUILD_LLVM_DYLIB=on) to only call
add_dependencies(). Instead, the explicit TableGen dependencies must
be passed to add_llvm_library() or add_llvm_executable() using the DEPENDS
keyword.
Differential Revision: https://reviews.llvm.org/D74930
When compiling libLLVM.so, add_llvm_library() manipulates the link libraries
being used. This means that when using add_llvm_library(), we need to pass
the list of libraries to be linked (using the LINK_LIBS keyword) instead of
using the standard target_link_libraries call. This is preparation for
properly dealing with creating libMLIR.so as well.
Differential Revision: https://reviews.llvm.org/D74864
Summary:
NFC - Moved StandardOps/Ops.h to a StandardOps/IR dir to better match surrounding
directories. This is to match other dialects, and prepare for moving StandardOps
related transforms in out for Transforms and into StandardOps/Transforms.
Differential Revision: https://reviews.llvm.org/D74940
Thus far IntegerType has been signless: a value of IntegerType does
not have a sign intrinsically and it's up to the specific operation
to decide how to interpret those bits. For example, std.addi does
two's complement arithmetic, and std.divis/std.diviu treats the first
bit as a sign.
This design choice was made some time ago when we did't have lots
of dialects and dialects were more rigid. Today we have much more
extensible infrastructure and different dialect may want different
modelling over integer signedness. So while we can say we want
signless integers in the standard dialect, we cannot dictate for
others. Requiring each dialect to model the signedness semantics
with another set of custom types is duplicating the functionality
everywhere, considering the fundamental role integer types play.
This CL extends the IntegerType with a signedness semantics bit.
This gives each dialect an option to opt in signedness semantics
if that's what they want and helps code sharing. The parser is
modified to recognize `si[1-9][0-9]*` and `ui[1-9][0-9]*` as
signed and unsigned integer types, respectively, leaving the
original `i[1-9][0-9]*` to continue to mean no indication over
signedness semantics. All existing dialects are not affected (yet)
as this is a feature to opt in.
More discussions can be found at:
https://groups.google.com/a/tensorflow.org/d/msg/mlir/XmkV8HOPWpo/7O4X0Nb_AQAJ
Differential Revision: https://reviews.llvm.org/D72533
It replaces DenseMap output with a SmallVector and it
removes empty loop levels from the output.
Reviewed By: andydavis1, mehdi_amini
Differential Revision: https://reviews.llvm.org/D74658
Summary:
This revision refactors the TypeConverter class to not use inheritance to add type conversions. It instead moves to a registration based system, where conversion callbacks are added to the converter with `addConversion`. This method takes a conversion callback, which must be convertible to any of the following forms(where `T` is a class derived from `Type`:
* Optional<Type> (T type)
- 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 type, SmallVectorImpl<Type> &results)
- 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.
When attempting to convert a type, the TypeConverter walks each of the registered converters starting with the one registered most recently.
Differential Revision: https://reviews.llvm.org/D74584
This patch extends affine data copy optimization utility with an
optional memref filter argument. When the memref filter is used, data
copy optimization will only generate copies for such a memref.
Note: this patch is just porting the memref filter feature from Uday's
'hop' branch: https://github.com/bondhugula/llvm-project/tree/hop.
Reviewed By: bondhugula
Differential Revision: https://reviews.llvm.org/D74342
In the previous state, we were relying on forcing the linker to include
all libraries in the final binary and the global initializer to self-register
every piece of the system. This change help moving away from this model, and
allow users to compose pieces more freely. The current change is only "fixing"
the dialect registration and avoiding relying on "whole link" for the passes.
The translation is still relying on the global registry, and some refactoring
is needed to make this all more convenient.
Differential Revision: https://reviews.llvm.org/D74461
Summary:
Adds affine loop fusion transformation function to LoopFusionUtils.
Updates TestLoopFusion utility to run loop fusion transformation until a fixed point is reached.
Adds unit tests to test the transformation.
Includes ASAN bug fix for D73190.
Reviewers: bondhugula, dcaballe
Reviewed By: bondhugula, dcaballe
Subscribers: mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, Joonsoo, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D74330
The existing (default) calling convention for memrefs in standard-to-LLVM
conversion was motivated by interfacing with LLVM IR produced from C sources.
In particular, it passes a pointer to the memref descriptor structure when
calling the function. Therefore, the descriptor is allocated on stack before
the call. This convention leads to several problems. PR44644 indicates a
problem with stack exhaustion when calling functions with memref-typed
arguments in a loop. Allocating outside of the loop may lead to concurrent
access problems in case the loop is parallel. When targeting GPUs, the contents
of the stack-allocated memory for the descriptor (passed by pointer) needs to
be explicitly copied to the device. Using an aggregate type makes it impossible
to attach pointer-specific argument attributes pertaining to alignment and
aliasing in the LLVM dialect.
Change the default calling convention for memrefs in standard-to-LLVM
conversion to transform a memref into a list of arguments, each of primitive
type, that are comprised in the memref descriptor. This avoids stack allocation
for ranked memrefs (and thus stack exhaustion and potential concurrent access
problems) and simplifies the device function invocation on GPUs.
Provide an option in the standard-to-LLVM conversion to generate auxiliary
wrapper function with the same interface as the previous calling convention,
compatible with LLVM IR porduced from C sources. These auxiliary functions
pack the individual values into a descriptor structure or unpack it. They also
handle descriptor stack allocation if necessary, serving as an allocation
scope: the memory reserved by `alloca` will be freed on exiting the auxiliary
function.
The effect of this change on MLIR-generated only LLVM IR is minimal. When
interfacing MLIR-generated LLVM IR with C-generated LLVM IR, the integration
only needs to require auxiliary functions and change the function name to call
the wrapper function instead of the original function.
This also opens the door to forwarding aliasing and alignment information from
memrefs to LLVM IR pointers in the standrd-to-LLVM conversion.
Summary:
This revision adds a utility to generate debug locations from the IR during compilation, by snapshotting to a output stream and using the locations that operations were dumped in that stream. The new locations may either;
* Replace the original location of the operation.
old:
loc("original_source.cpp":1:1)
new:
loc("snapshot_source.mlir":10:10)
* Fuse with the original locations as NamedLocs with a specific tag.
old:
loc("original_source.cpp":1:1)
new:
loc(fused["original_source.cpp":1:1, "snapshot"("snapshot_source.mlir":10:10)])
This feature may be used by a debugger to display the code at various different levels of the IR. It would also be able to show the different levels of IR attached to a specific source line in the original source file.
This feature may also be used to generate locations for operations generated during compilation, that don't necessarily have a user source location to attach to.
This requires changes in the printer to track the locations of operations emitted in the stream. Moving forward we need to properly(and efficiently) track the number of newlines emitted to the stream during printing.
Differential Revision: https://reviews.llvm.org/D74019
Summary: This is the most common operation performed on a CallOpInterface. This just moves the existing functionality from the CallGraph so that other users can access it.
Differential Revision: https://reviews.llvm.org/D74250
This reverts commit 64871f778d.
ASAN indicates a use-after-free in in mlir::canFuseLoops(mlir::AffineForOp, mlir::AffineForOp, unsigned int, mlir::ComputationSliceState*) lib/Transforms/Utils/LoopFusionUtils.cpp:202:41
Summary:
This revision adds basic support for emitting line table information when exporting to LLVMIR. We don't yet have a story for supporting all of the LLVM debug metadata, so this revision stubs some features(like subprograms) to enable emitting line tables.
Differential Revision: https://reviews.llvm.org/D73934
Summary:
Adds affine loop fusion transformation function to LoopFusionUtils.
Updates TestLoopFusion utility to run loop fusion transformation until a fixed point is reached.
Adds unit tests to test the transformation.
Reviewers: bondhugula, dcaballe, nicolasvasilache
Reviewed By: bondhugula, dcaballe
Subscribers: Joonsoo, merge_guards_bot, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D73190
Summary:
MLIRAnalysis depended on MLIRVectorOps
MLIRVectorOps depended on MLIRAnalysis for Loop information.
Both of these can be solved by factoring out libraries related to loop
analysis into their own library. The new MLIRLoopAnalysis might be
better off with the Loop Dialect in the future.
Reviewers: nicolasvasilache, rriddle!, mehdi_amini
Reviewed By: mehdi_amini
Subscribers: Joonsoo, vchuravy, merge_guards_bot, mgorny, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D73655
Summary:
This breaks a cyclic library dependency where MLIRPass used the verifier
in MLIRAnalysis, but MLIRAnalysis also contained passes used for testing.
The presence of the test passes here is archaeology, predating
test/lib/Transform.
Reviewers: rriddle
Reviewed By: rriddle
Subscribers: merge_guards_bot, mgorny, mehdi_amini, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, liufengdb, Joonsoo, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D74067
This is fixing a build error:
error: non-constant-expression cannot be narrowed from type 'unsigned int' to 'Region::iterator::difference_type' (aka 'int') in initializer list
Fix pr44767
Seen on gcc 8, in release mode & assertions off warnings about logger,
made all statements referencing logger inside LLVM_DEBUG blocks and
ifdef a few variables only used in debug.
This is mechanical fix to get CI green.
Summary:
This revision beefs up the debug logging within dialect conversion. Given the nature of multi-level legalization, and legalization in general, it is one of the harder pieces of infrastructure to debug. This revision adds nice formatting to make the output log easier to parse:
```
Legalizing operation : 'std.constant'(0x608000002420) {
* Fold {
} -> FAILURE : unable to fold
* Pattern : 'std.constant -> ()' {
} -> FAILURE : pattern failed to match
* Pattern : 'std.constant -> ()' {
} -> FAILURE : pattern failed to match
* Pattern : 'std.constant -> (spv.constant)' {
** Insert : 'spv.constant'(0x608000002c20)
** Replace : 'std.constant'(0x608000002420)
//===-------------------------------------------===//
Legalizing operation : 'spv.constant'(0x608000002c20) {
} -> SUCCESS : operation marked legal by the target
//===-------------------------------------------===//
} -> SUCCESS : pattern applied successfully
} -> SUCCESS
```
Differential Revision: https://reviews.llvm.org/D73747
The refactored MemRefType::get() calls all intend to clone from another
memref type, with some modifications. In fact, some calls dropped memory space
during the cloning. Migrate them to the cloning API so that nothing gets
dropped if they are not explicitly listed.
It's close to NFC but not quite, as it helps with propagating memory spaces in
some places.
Differential Revision: https://reviews.llvm.org/D73296
This is how it should've been and brings it more in line with
std::string_view. There should be no functional change here.
This is mostly mechanical from a custom clang-tidy check, with a lot of
manual fixups. It uncovers a lot of minor inefficiencies.
This doesn't actually modify StringRef yet, I'll do that in a follow-up.
Summary: This pass deletes all symbols that are found to be unreachable. This is done by computing the set of operations that are known to be live, propagating that liveness to other symbols, and then deleting all symbols that are not within this live set.
Differential Revision: https://reviews.llvm.org/D72482
Summary: The new internal representation of operation results now allows for accessing the result types to be more efficient. Changing the API to ArrayRef is more efficient and removes the need to explicitly materialize vectors in several places.
Differential Revision: https://reviews.llvm.org/D73429
Summary: This allows for providing a default "catchall" legality check that is not dependent on specific operations or dialects. For example, this can be useful to check legality based on the specific types of operation operands or results.
Differential Revision: https://reviews.llvm.org/D73379
Summary:
Remove 'valuesToRemoveIfDead' from PatternRewriter API. The removal
functionality wasn't implemented and we decided [1] not to implement it in
favor of having more powerful DCE approaches.
[1] https://github.com/tensorflow/mlir/pull/212
Reviewers: rriddle, bondhugula
Reviewed By: rriddle
Subscribers: liufengdb, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D72545
Summary:
First step towards the consolidation
of a lot of vector related utilities
that are now all over the place
(or even duplicated).
Reviewers: nicolasvasilache, andydavis1
Reviewed By: nicolasvasilache, andydavis1
Subscribers: merge_guards_bot, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, arpith-jacob, mgester, lucyrfox, liufengdb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D72955
Summary:
This enables tracking calls that cross symbol table boundaries. It also simplifies some of the implementation details of CallableOpInterface, i.e. there can only be one region within the callable operation.
Depends On D72042
Reviewed By: jpienaar
Differential Revision: https://reviews.llvm.org/D72043
Summary: A new class is added, IRMultiObjectWithUseList, that allows for representing an IR use list that holds multiple sub values(used in this case for OpResults). This class provides all of the same functionality as the base IRObjectWithUseList, but for specific sub-values. This saves a word per operation result and is a necessary step in optimizing the layout of operation results. For now the use list is placed on the operation itself, so zero-result operations grow by a word. When the work for optimizing layout is finished, this can be moved back to being a trailing object based on memory/runtime benchmarking.
Reviewed By: jpienaar
Differential Revision: https://reviews.llvm.org/D71955
This means that in-place, or root, updates need to use explicit calls to `startRootUpdate`, `finalizeRootUpdate`, and `cancelRootUpdate`. The major benefit of this change is that it enables in-place updates in DialectConversion, which simplifies the FuncOp pattern for example. The major downside to this is that the cases that *may* modify an operation in-place will need an explicit cancel on the failure branches(assuming that they started an update before attempting the transformation).
PiperOrigin-RevId: 286933674
This is an initial step to refactoring the representation of OpResult as proposed in: https://groups.google.com/a/tensorflow.org/g/mlir/c/XXzzKhqqF_0/m/v6bKb08WCgAJ
This change will make it much simpler to incrementally transition all of the existing code to use value-typed semantics.
PiperOrigin-RevId: 286844725
Rename the 'shlis' operation in the standard dialect to 'shift_left'. Add tests
for this operation (these have been missing so far) and add a lowering to the
'shl' operation in the LLVM dialect.
Add also 'shift_right_signed' (lowered to LLVM's 'ashr') and 'shift_right_unsigned'
(lowered to 'lshr').
The original plan was to name these operations 'shift.left', 'shift.right.signed'
and 'shift.right.unsigned'. This works if the operations are prefixed with 'std.'
in MLIR assembly. Unfortunately during import the short form is ambigous with
operations from a hypothetical 'shift' dialect. The best solution seems to omit
dots in standard operations for now.
Closestensorflow/mlir#226
PiperOrigin-RevId: 286803388
* Fixes use of anonymous namespace for static methods.
* Uses explicit qualifiers(mlir::) instead of wrapping the definition with the namespace.
PiperOrigin-RevId: 286222654
Introduce affine.prefetch: op to prefetch using a multi-dimensional
subscript on a memref; similar to affine.load but has no effect on
semantics, but only on performance.
Provide lowering through std.prefetch, llvm.prefetch and map to llvm's
prefetch instrinsic. All attributes reflected through the lowering -
locality hint, rw, and instr/data cache.
affine.prefetch %0[%i, %j + 5], false, 3, true : memref<400x400xi32>
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closestensorflow/mlir#225
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/225 from bondhugula:prefetch 4c3b4e93bc64d9a5719504e6d6e1657818a2ead0
PiperOrigin-RevId: 286212997
This keeps the IR valid and consistent as it is expected that each block should have a valid parent region/operation. Previously, converted blocks were kept floating without a valid parent region.
PiperOrigin-RevId: 285821687
This change allows for DialectConversion to attempt folding as a mechanism to legalize illegal operations. This also expands folding support in OpBuilder::createOrFold to generate new constants when folding, and also enables it to work in the context of a PatternRewriter.
PiperOrigin-RevId: 285448440
It is sometimes useful to create operations separately from the builder before insertion as it may be easier to erase them in isolation if necessary. One example use case for this is folding, as we will only want to insert newly generated constant operations on success. This has the added benefit of fixing some silent PatternRewriter failures related to cloning, as the OpBuilder 'clone' methods don't call createOperation.
PiperOrigin-RevId: 285086242
This allows for users to provide operand_range and result_range in builder.create<> calls, instead of requiring an explicit copy into a separate data structure like SmallVector/std::vector.
PiperOrigin-RevId: 284360710
This class represents a generic abstraction over the different ways to represent a range of Values: ArrayRef<Value *>, operand_range, result_range. This class will allow for removing the many instances of explicit SmallVector<Value *, N> construction. It has the same memory cost as ArrayRef, and only suffers cost from indexing(if+elsing the different underlying representations).
This change only updates a few of the existing usages, with more to be changed in followups; e.g. 'build' API.
PiperOrigin-RevId: 284307996
Statistics are a way to keep track of what the compiler is doing and how effective various optimizations are. It is useful to see what optimizations are contributing to making a particular program run faster. Pass-instance specific statistics take this even further as you can see the effect of placing a particular pass at specific places within the pass pipeline, e.g. they could help answer questions like "what happens if I run CSE again here".
Statistics can be added to a pass by simply adding members of type 'Pass::Statistics'. This class takes as a constructor arguments: the parent pass pointer, a name, and a description. Statistics can be dumped by the pass manager in a similar manner to how pass timing information is dumped, i.e. via PassManager::enableStatistics programmatically; or -pass-statistics and -pass-statistics-display via the command line pass manager options.
Below is an example:
struct MyPass : public OperationPass<MyPass> {
Statistic testStat{this, "testStat", "A test statistic"};
void runOnOperation() {
...
++testStat;
...
}
};
$ mlir-opt -pass-pipeline='func(my-pass,my-pass)' foo.mlir -pass-statistics
Pipeline Display:
===-------------------------------------------------------------------------===
... Pass statistics report ...
===-------------------------------------------------------------------------===
'func' Pipeline
MyPass
(S) 15 testStat - A test statistic
MyPass
(S) 6 testStat - A test statistic
List Display:
===-------------------------------------------------------------------------===
... Pass statistics report ...
===-------------------------------------------------------------------------===
MyPass
(S) 21 testStat - A test statistic
PiperOrigin-RevId: 284022014
Now that we have unrolling as a declarative pattern, we can drop a full pass that has gone stale. In the future we may want to add specific unrolling patterns for VectorTransferReadOp.
PiperOrigin-RevId: 283806880
In the replaceAllUsesExcept utility function called from loop coalescing the
iteration over the use-chain is incorrect. The use list nodes (IROperands) have
next/prev links, and bluntly resetting the use would make the loop to continue
on uses of the value that was replaced instead of the original one. As a
result, it could miss the existing uses and update the wrong ones. Make sure we
increment the iterator before updating the use in the loop body.
Reported-by: Uday Bondhugula <uday@polymagelabs.com>
Closestensorflow/mlir#291.
PiperOrigin-RevId: 283754195
This CL refactors some of the MLIR vector dependencies to allow decoupling VectorOps, vector analysis, vector transformations and vector conversions from each other.
This makes the system more modular and allows extracting VectorToVector into VectorTransforms that do not depend on vector conversions.
This refactoring exhibited a bunch of cyclic library dependencies that have been cleaned up.
PiperOrigin-RevId: 283660308
tensorflow/mlir#162 introduced a bug that
incorrectly allowed fusion of producer loops with multiple outgoing
edges. This commit fixes that problem. It also introduces a new flag to
disable sibling loop fusion so that we can test producer-consumer fusion
in isolation.
Closestensorflow/mlir#259
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/259 from dcaballe:dcaballe/fix_multi_out_edge_producer_fusion 578d5661705fd5c56c555832d5e0528df88c5282
PiperOrigin-RevId: 283531105
To simplify the lowering into SPIR-V, while still respecting the ABI
requirements of SPIR-V/Vulkan, split the process into two
1) While lowering a function to SPIR-V (when the function is an entry
point function), allow specifying attributes on arguments and
function itself that describe the ABI of the function.
2) Add a pass that materializes the ABI described in the function.
Two attributes are needed.
1) Attribute on arguments of the entry point function that describe
the descriptor_set, binding, storage class, etc, of the
spv.globalVariable this argument will be replaced by
2) Attribute on function that specifies workgroup size, etc. (for now
only workgroup size).
Add the pass -spirv-lower-abi-attrs to materialize the ABI described
by the attributes.
This change makes the SPIRVBasicTypeConverter class unnecessary and is
removed, further simplifying the SPIR-V lowering path.
PiperOrigin-RevId: 282387587
Change vector op names from VectorFooOp to Vector_FooOp and from
vector::VectorFooOp to vector::FooOp.
Closestensorflow/mlir#257
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/257 from Kayjukh:master dfc3a0e04114885aaec8740d5951d6984d6e1577
PiperOrigin-RevId: 281967461
This moves the different canonicalizations of regions into one place and invokes them in the fixed-point iteration of the canonicalizer.
PiperOrigin-RevId: 281617072
This is a simple multi-level DCE pass that operates pretty generically on
the IR. Its key feature compared to the existing peephole dead op folding
that happens during canonicalization is being able to delete recursively
dead cycles of the use-def graph, including block arguments.
PiperOrigin-RevId: 281568202
This CL uses the pattern rewrite infrastructure to implement a simple VectorOps -> VectorOps legalization strategy to unroll coarse-grained vector operations into finer grained ones.
The transformation is written using local pattern rewrites to allow composition with other rewrites. It proceeds by iteratively introducing fake cast ops and cleaning canonicalizing or lowering them away where appropriate.
This is an example of writing transformations as compositions of local pattern rewrites that should enable us to make them significantly more declarative.
PiperOrigin-RevId: 281555100
This method is needed for N->1 conversion patterns to retrieve remapped
Values used in the original N operations.
Closestensorflow/mlir#237
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/237 from dcaballe:dcaballe/getRemappedValue 1f64fadcf2b203f7b336ff0c5838b116ae3625db
PiperOrigin-RevId: 281321881
This CL utilizies the more robust fusion feasibility analysis being built out in LoopFusionUtils, which will eventually be used to replace the current affine loop fusion pass.
PiperOrigin-RevId: 281112340
This is step 1/n in refactoring infrastructure along the Vector dialect to make it ready for retargetability and composable progressive lowering.
PiperOrigin-RevId: 280529784
This CL moves VectorOps to Tablegen and cleans up the implementation.
This is almost NFC but 2 changes occur:
1. an interface change occurs in the padding value specification in vector_transfer_read:
the value becomes non-optional. As a shortcut we currently use %f0 for all paddings.
This should become an OpInterface for vectorization in the future.
2. the return type of vector.type_cast is trivial and simplified to `memref<vector<...>>`
Relevant roundtrip and invalid tests that used to sit in core are moved to the vector dialect.
The op documentation is moved to the .td file.
PiperOrigin-RevId: 280430869
This refactors the implementation of block signature(type) conversion to not insert fake cast operations to perform the type conversion, but to instead create a new block containing the proper signature. This has the benefit of enabling the use of pre-computed analyses that rely on mapping values. It also leads to a much cleaner implementation overall. The major user facing change is that applySignatureConversion will now replace the entry block of the region, meaning that blocks generally shouldn't be cached over calls to applySignatureConversion.
PiperOrigin-RevId: 280226936
This also previously triggered the warning:
warning: missing field 'isRecursivelyLegal' initializer [-Wmissing-field-initializers]
legalOperations[op] = {action};
^
PiperOrigin-RevId: 279399175
A pattern rewriter hook, mergeBlock, is added that allows for merging the operations of one block into the end of another. This is used to support a canonicalization pattern for branch operations that folds the branch when the successor has a single predecessor(the branch block).
Example:
^bb0:
%c0_i32 = constant 0 : i32
br ^bb1(%c0_i32 : i32)
^bb1(%x : i32):
return %x : i32
becomes:
^bb0:
%c0_i32 = constant 0 : i32
return %c0_i32 : i32
PiperOrigin-RevId: 278677825
The current lowering of loops to GPU only supports lowering of loop
nests where the loops mapped to workgroups and workitems are perfectly
nested. Here a new lowering is added to handle lowering of imperfectly
nested loop body with the following properties
1) The loops partitioned to workgroups are perfectly nested.
2) The loop body of the inner most loop partitioned to workgroups can
contain one or more loop nests that are to be partitioned across
workitems. Each individual loops nests partitioned to workitems should
also be perfectly nested.
3) The number of workgroups and workitems are not deduced from the
loop bounds but are passed in by the caller of the lowering as values.
4) For statements within the perfectly nested loop nest partitioned
across workgroups that are not loops, it is valid to have all threads
execute that statement. This is NOT verified.
PiperOrigin-RevId: 277958868
Rewrite patterns may make modifications to the CFG, including dropping edges between blocks. This change adds a simple unreachable block elimination run at the end of each iteration to ensure that the CFG remains valid.
PiperOrigin-RevId: 277545805
When we removed a pattern, we removed it from worklist but not from
worklistMap. Then, when we tried to add a new pattern on the same Operation
again, the pattern wasn't added since it already existed in the
worklistMap (but not in the worklist).
Closestensorflow/mlir#211
PiperOrigin-RevId: 277319669
In some cases, it may be desirable to mark entire regions of operations as legal. This provides an additional granularity of context to the concept of "legal". The `ConversionTarget` supports marking operations, that were previously added as `Legal` or `Dynamic`, as `recursively` legal. Recursive legality means that if an operation instance is legal, either statically or dynamically, all of the operations nested within are also considered legal. An operation can be marked via `markOpRecursivelyLegal<>`:
```c++
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) { ... });
```
PiperOrigin-RevId: 277086382
This allows for them to be used on other non-function, or even other function-like, operations. The algorithms are already generic, so this is simply changing the derived pass type. The majority of this change is just ensuring that the nesting of these passes remains the same, as the pass manager won't auto-nest them anymore.
PiperOrigin-RevId: 276573038
This allows mixing linalg operations with vector transfer operations (with additional modifications to affine ops) and is a step towards solving tensorflow/mlir#189.
PiperOrigin-RevId: 275543361
This Chapter now introduces and makes use of the Interface concept
in MLIR to demonstrate ShapeInference.
END_PUBLIC
Closestensorflow/mlir#191
PiperOrigin-RevId: 275085151
The current SignatureConversion framework (part of DialectConversion)
allows remapping input arguments to a function from 1->0, 1->1 or
1->many arguments during conversion. Another case is where the
argument itself is dropped, but it's use are remapped to another
Value*.
An example of this is: The Vulkan/SPIR-V spec requires entry functions
to be of type void(void). The GPU -> SPIR-V conversion implemented
this without having the DialectConversion framework track the
remapping that lead to some undefined behavior. The changes here
addresses that.
PiperOrigin-RevId: 275059656
b843cc5d5a introduced a new op LICM transformation and a LoopLike interface,
but missed the CMake aspects of it. This should fix the build.
PiperOrigin-RevId: 275038533
When dealing with regions, or other patterns that need to generate temporary operations, it is useful to be able to replace other operations than the root op being matched. Before this PR, these operations would still be considered for legalization meaning that the conversion would either fail, erroneously need to mark these ops as legal, or add unnecessary patterns.
PiperOrigin-RevId: 274598513
This will allow for inlining newly devirtualized calls, as well as give a more accurate cost model(when we have one). Currently canonicalization will only run for nodes that have no child edges, as the child nodes may be erased during canonicalization. We can support this in the future, but it requires more intricate deletion tracking.
PiperOrigin-RevId: 274011386
When an operation with regions gets replaced, we currently require that all of the remaining nested operations are still converted even though they are going to be replaced when the rewrite is finished. This cl adds a tracking for a minimal set of operations that are known to be "dead". This allows for ignoring the legalization of operations that are won't survive after conversion.
PiperOrigin-RevId: 274009003
This PR is a stepping stone towards supporting generic multi-store
source loop nests in affine loop fusion. It extends the algorithm to
support fusion of multi-store loop nests that:
1. have only one store that writes to a function-local live out, and
2. the remaining stores are involved in loop nest self dependences
or no dependences within the function.
Closestensorflow/mlir#162
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/162 from dcaballe:dcaballe/multi-output-fusion 7fb7dec6fe8b45f5ce176f018bfe37b256420c45
PiperOrigin-RevId: 273773907
This is similar to the `inlineRegionBefore` hook, except the original blocks are unchanged. The region to be cloned *must* not have been modified during the conversion process at the point of cloning, i.e. it must belong an operation that has yet to be converted, or the operation that is currently being converted.
PiperOrigin-RevId: 273622533
- bodies would earlier appear in the order (i, i+3, i+2, i+1) instead of
(i, i+1, i+2, i+3) for example for factor 4.
- clean up hardcoded test cases
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closestensorflow/mlir#170
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/170 from bondhugula:ujam b66b405b2b1894a03b376952e32a9d0292042665
PiperOrigin-RevId: 273613131
Some dialects have implicit conversions inherent in their modeling, meaning that a call may have a different type that the type that the callable expects. To support this, a hook is added to the dialect interface that allows for materializing conversion operations during inlining when there is a mismatch. A hook is also added to the callable interface to allow for introspecting the expected result types.
PiperOrigin-RevId: 272814379
This allows for the inliner to work on arbitrary call operations. The updated inliner will also work bottom-up through the callgraph enabling support for multiple levels of inlining.
PiperOrigin-RevId: 272813876
The generated build methods have result type before the arguments (operands and attributes, which are also now adjacent in the explicit create method). This also results in changing the create method's ordering to match most build method's ordering.
PiperOrigin-RevId: 271755054
- also remove stale terminology/references in docs
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closestensorflow/mlir#148
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/148 from bondhugula:cleanup e846b641a3c2936e874138aff480a23cdbf66591
PiperOrigin-RevId: 271618279
The strided MemRef RFC discusses a normalized descriptor and interaction with library calls (https://groups.google.com/a/tensorflow.org/forum/#!topic/mlir/MaL8m2nXuio).
Lowering of nested LLVM structs as value types does not play nicely with externally compiled C/C++ functions due to ABI issues.
Solving the ABI problem generally is a very complex problem and most likely involves taking
a dependence on clang that we do not want atm.
A simple workaround is to pass pointers to memref descriptors at function boundaries, which this CL implement.
PiperOrigin-RevId: 271591708
- fix store to load forwarding for a certain set of cases (where
forwarding shouldn't have happened); use AffineValueMap difference
based MemRefAccess equality checking; utility logic is also greatly
simplified
- add missing equality/inequality operators for AffineExpr ==/!= ints
- add == != operators on MemRefAccess
Closestensorflow/mlir#136
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/136 from bondhugula:store-load-forwarding d79fd1add8bcfbd9fa71d841a6a9905340dcd792
PiperOrigin-RevId: 270457011
Mehdi Amini