- Change AllocOp to have a getType() that always returns a MemRefType, since
that is what it requires.
- Rename StandardOps/StandardOpRegistration.cpp ->
StandardOps/OpRegistration.cpp to align with other op sets.
- Add AffineMap::getContext() helper and use it in the asmprinter.
PiperOrigin-RevId: 218205527
a step forward because now every AbstractOperation knows which Dialect it is
associated with, enabling things in the future like "constant folding
hooks" which will be important for layering. This is also a bit nicer on
the registration side of things.
PiperOrigin-RevId: 218104230
PatternMatcher clients up to date and provide a funnel point for newly added
operations. This is also progress towards the canonicalizer supporting
CFGFunctions.
This paves the way for more complex patterns, but by itself doesn't do much
useful, so no testcase.
PiperOrigin-RevId: 218101737
We should be able to represent arbitrary precision Float-point values inside
the IR, so compiler optimizations, such as constant folding can be done
independently on the compiling platform.
This CL also added a new field, AttrValueGetter, to the Attr class definition
for TableGen. This field is used to customize which mlir::Attr getter method to
get the defined PrimitiveType.
PiperOrigin-RevId: 218034983
Also rename Operation::is to Operation::isa
Introduce Operation::cast
All of these are for consistency with global dyn_cast/cast/isa operators.
PiperOrigin-RevId: 217878786
The SparseElementsAttr uses (COO) Coordinate List encoding to represents a
sparse tensor / vector. Specifically, the coordinates and values are stored as
two dense elements attributes. The first dense elements attribute is a 2-D
attribute with shape [N, ndims], which contains the indices of the elements
with nonzero values in the constant vector/tensor. The second elements
attribute is a 1-D attribute list with shape [N], which supplies the values for
each element in the first elements attribute. ndims is the rank of the
vector/tensor and N is the total nonzero elements.
The syntax is:
`sparse<` (tensor-type | vector-type)`, ` indices-attribute-list, values-attribute-list `>`
Example: a sparse tensor
sparse<vector<3x4xi32>, [[0, 0], [1, 2]], [1, 2]> represents the dense tensor
[[1, 0, 0, 0]
[0, 0, 2, 0]
[0, 0, 0, 0]]
PiperOrigin-RevId: 217764319
The syntax of dense vecor/tensor attribute value is
`dense<` (tensor-type | vector-type)`,` attribute-list`>`
and
attribute-list ::= `[` attribute-list (`, ` attribute-list)* `]`.
The construction of the dense vector/tensor attribute takes a vector/tensor
type and a character array as arguments. The size of the input array should be
larger than the size specified by the type argument. It also assumes the
elements of the vector or tensor have been trunked to the data type sizes in
the input character array, so it extends the trunked data to 64 bits when it is
retrieved.
PiperOrigin-RevId: 217762811
multiple TODOs.
- replace the fake test pass (that worked on just the first loop in the
MLFunction) to perform DMA pipelining on all suitable loops.
- nested DMAs work now (DMAs in an outer loop, more DMAs in nested inner loops)
- fix bugs / assumptions: correctly copy memory space and elemental type of source
memref for double buffering.
- correctly identify matching start/finish statements, handle multiple DMAs per
loop.
- introduce dominates/properlyDominates utitilies for MLFunction statements.
- move checkDominancePreservationOnShifts to LoopAnalysis.h; rename it
getShiftValidity
- refactor getContainingStmtPos -> findAncestorStmtInBlock - move into
Analysis/Utils.h; has two users.
- other improvements / cleanup for related API/utilities
- add size argument to dma_wait - for nested DMAs or in general, it makes it
easy to obtain the size to use when lowering the dma_wait since we wouldn't
want to identify the matching dma_start, and more importantly, in general/in the
future, there may not always be a dma_start dominating the dma_wait.
- add debug information in the pass
PiperOrigin-RevId: 217734892
This CL implements a very simple loop vectorization **test** and the basic
infrastructure to support it.
The test simply consists in:
1. matching the loops in the MLFunction and all the Load/Store operations
nested under the loop;
2. testing whether all the Load/Store are contiguous along the innermost
memory dimension along that particular loop. If any reference is
non-contiguous (i.e. the ForStmt SSAValue appears in the expression), then
the loop is not-vectorizable.
The simple test above can gradually be extended with more interesting
behaviors to account for the fact that a layout permutation may exist that
enables contiguity etc. All these will come in due time but it is worthwhile
noting that the test already supports detection of outer-vetorizable loops.
In implementing this test, I also added a recursive MLFunctionMatcher and some
sugar that can capture patterns
such as `auto gemmLike = Doall(Doall(Red(LoadStore())))` and allows iterating
on the matched IR structures. For now it just uses in order traversal but
post-order DFS will be useful in the future once IR rewrites start occuring.
One may note that the memory management design decision follows a different
pattern from MLIR. After evaluating different designs and how they quickly
increase cognitive overhead, I decided to opt for the simplest solution in my
view: a class-wide (threadsafe) RAII context.
This way, a pass that needs MLFunctionMatcher can just have its own locally
scoped BumpPtrAllocator and everything is cleaned up when the pass is destroyed.
If passes are expected to have a longer lifetime, then the contexts can easily
be scoped inside the runOnMLFunction call and storage lifetime reduced.
Lastly, whatever the scope of threading (module, function, pass), this is
expected to also be future-proof wrt concurrency (but this is a detail atm).
PiperOrigin-RevId: 217622889
Change how attributes can be added to an Op to make the syntax in the td file a bit cleaner. Also avoid unnecessarily emitting verify method (trivial return false one that's already in base) and use custom syntax in test.
PiperOrigin-RevId: 217330036
Updates ComposeAffineMaps test pass to use this method.
Updates affine map composition test cases to handle the new pass, which can be reused when this method is used in a future instruction combine pass.
PiperOrigin-RevId: 217163351
Create tblgen based tool to generate the C++ Op definitions. The modelling is
currently simple (ops, attributes, properties) with the printer/parser/verifier
the bodies of those functions and builders being very explicit.
PiperOrigin-RevId: 217150213
Associate BasicBlocks with the function being parsed to avoid leaks in the case of parse failures. Associating with the function means that we can no longer determine if defined/fwd declared simply by considering if a BasicBlock has an associated function, so track forward declared block references explicitly (this should also allow flagging multiple undeclared fwd references). Split out getting the named block from defining it, in the case of definition move the block to the end of the function.
Also destroy all forward reference placeholders in FunctionParser.
Return parse failure in parseAttributeDict if there is no left brace instead of
asserting.
PiperOrigin-RevId: 217049507
- Make it so OpPointer implicitly converts to SSAValue* when the underlying op
has a single value. This eliminates a lot more ->getResult() calls and makes
the behavior more LLVM-like
- Fill out PatternBenefit to be typed instead of just a typedef for int with
magic numbers.
- Simplify various code due to these changes.
PiperOrigin-RevId: 217020717
- add util to create a private / exclusive / single use affine
computation slice for an op stmt (see method doc comment); a single
multi-result affine_apply op is prepended to the op stmt to provide all
results needed for its operands as a function of loop iterators and symbols.
- use it for DMA pipelining (to create private slices for DMA start stmt's);
resolve TODOs/feature request (b/117159533)
- move createComposedAffineApplyOp to Transforms/Utils; free it from taking a
memref as input / generalize it.
PiperOrigin-RevId: 216926818
out canonicalization pass to drive it, and a simple (x-x) === 0 pattern match
as a test case.
There is a tremendous number of improvements that need to land, and the
matcher/rewriter and patterns will be split out of this file, but this is a
starting point.
PiperOrigin-RevId: 216788604
* Move Return, Constant and AffineApply out into BuiltinOps;
* BuiltinOps are always registered, while StandardOps follow the same dynamic registration;
* Kept isValidX in MLValue as we don't have a verify on AffineMap so need to keep it callable from Parser (I wanted to move it to be called in verify instead);
PiperOrigin-RevId: 216592527
We allow the name of an operation to be different from the name of the
'ConcreteType' op it was instantiated with. This can happen when you sub-class
an existing op and provide a getOperationName for it. Such a situation leads to
an assertion too deep and at a place seeminly unrelated, and typically when the
module is printed with the trace:
printOperation, printAssembly, Op::print, getOperand, dyn_cast<OperationStmt>,
isa. 'isa' will complain about being called on a null pointer, and the null
pointer actually comes from the getAs<> in printAssembly. This should have been
caught in printAssembly.
On another note, it is also weird that we allow setting the op's name to
something independent of the ConcreteType that op was instantiated with - so,
getAs<ConcreteType> will fail since ConcreteType::isClassFor won't succeed on
it.
PiperOrigin-RevId: 216580294
This CL applies the same pattern as AffineMap to IntegerSet: a simple struct
that acts as the storage is allocated in the bump pointer. The IntegerSet is
immutable and accessed everywhere by value.
Note that unlike AffineMap, it is not possible to remove the MLIRContext
parameter when constructing an IntegerSet for now. One possible way to achieve
this would be to add an enum to distinguish between the mathematically empty
set, the universe set and other sets.
This is left for future discussion.
PiperOrigin-RevId: 216545361
This attribute represents a reference to a splat vector or tensor, where all
the elements have the same value. The syntax of the attribute is:
`splat<` (tensor-type | vector-type)`,` attribute-value `>`
PiperOrigin-RevId: 216537997
AbstractOperation* or an Identifier. This makes it possible to get to stuff in
AbstractOperation faster than going through a hash table lookup. This makes
constant folding a bit faster now, but will become more important with
subsequent changes.
PiperOrigin-RevId: 216476772
This CL applies the same pattern as AffineExpr to AffineMap: a simple struct
that acts as the storage is allocated in the bump pointer. The AffineMap is
immutable and accessed everywhere by value.
PiperOrigin-RevId: 216445930
Add target independent standard DMA ops: dma.start, dma.wait. Update pipeline
data transfer to use these to detect DMA ops.
While on this
- return failure from mlir-opt::performActions if a pass generates invalid output
- improve error message for verify 'n' operand traits
PiperOrigin-RevId: 216429885
This CL sketches what it takes for AffineExpr to fully have by-value semantics
and not be a not-so-smart pointer anymore.
This essentially makes the underyling class a simple storage struct and
implements the operations on the value type directly. Since there is no
forwarding of operations anymore, we can full isolate the storage class and
make a hard visibility barrier by moving detail::AffineExpr into
AffineExprDetail.h.
AffineExprDetail.h is only included where storage-related information is
needed.
PiperOrigin-RevId: 216385459
This CL:
1. performs the global codemod AffineXExpr->AffineXExprClass and
AffineXExprRef -> AffineXExpr;
2. simplifies function calls by removing the redundant MLIRContext parameter;
3. adds missing binary operator versions of scalar op AffineExpr where it
makes sense.
PiperOrigin-RevId: 216242674
This CL introduces a series of cleanups for AffineExpr value types:
1. to make it clear that the value types should be used, the pointer
AffineExpr types are put in the detail namespace. Unfortunately, since the
value type operator-> only forwards to the underlying pointer type, we
still
need to expose this in the include file for now;
2. AffineExprKind is ok to use, it thus comes out of detail and thus of
AffineExpr
3. getAffineDimExpr, getAffineSymbolExpr, getAffineConstantExpr are
similarly
extracted as free functions and their naming is mande consistent across
Builder, MLContext and AffineExpr
4. AffineBinaryOpEx::simplify functions are made into static free
functions.
In particular it is moved away from AffineMap.cpp where it does not belong
5. operator AffineExprType is made explicit
6. uses the binary operators everywhere possible
7. drops the pointer usage everywhere outside of AffineExpr.cpp,
MLIRContext.cpp and AsmPrinter.cpp
PiperOrigin-RevId: 216207212
This CL makes AffineExprRef into a value type.
Notably:
1. drops llvm isa, cast, dyn_cast on pointer type and uses member functions on
the value type. It may be possible to still use classof (in a followup CL)
2. AffineBaseExprRef aggressively casts constness away: if we mean the type is
immutable then let's jump in with both feet;
3. Drop implicit casts to the underlying pointer type because that always
results in surprising behavior and is not needed in practice once enough
cleanup has been applied.
The remaining negative I see is that we still need to mix operator. and
operator->. There is an ugly solution that forwards the methods but that ends
up duplicating the class hierarchy which I tried to avoid as much as
possible. But maybe it's not that bad anymore since AffineExpr.h would still
contain a single class hierarchy (the duplication would be impl detail in.cpp)
PiperOrigin-RevId: 216188003
1) affineint (as it is named) is not a type suitable for general computation (e.g. the multiply/adds in an integer matmul). It has undefined width and is undefined on overflow. They are used as the indices for forstmt because they are intended to be used as indexes inside the loop.
2) It can be used in both cfg and ml functions, and in cfg functions. As you mention, “symbols” are not affine, and we use affineint values for symbols.
3) Integers aren’t affine, the algorithms applied to them can be. :)
4) The only suitable use for affineint in MLIR is for indexes and dimension sizes (i.e. the bounds of those indexes).
PiperOrigin-RevId: 216057974
- Fold the lower/upper bound of a loop to a constant whenever the result of the
application of the bound's affine map on the operand list yields a constant.
- Update/complete 'for' stmt's API to set lower/upper bounds with operands.
Resolve TODOs for ForStmt::set{Lower,Upper}Bound.
- Moved AffineExprConstantFolder into AffineMap.cpp and added
AffineMap::constantFold to be used by both AffineApplyOp and
ForStmt::constantFoldBound.
PiperOrigin-RevId: 215997346
Chris Lattner