| Commit message (Collapse) | Author | Age | Files | Lines |
... | |
| |
| |
| |
| | |
PiperOrigin-RevId: 275310747
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
This pattern is error prone and unfortunately none of the sanitizer is catching
it at the moment.
Fixes tensorflow/mlir#192
Closes tensorflow/mlir#193
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/193 from joker-eph:fix_array_ref 8092252e64c426c6a8a790b7638f847bea4818b1
PiperOrigin-RevId: 275280201
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Previously when we bind a symbol to an op in DRR, it means to capture
the op's result(s) and later references will be expanded to result(s).
This means for ops without result, we are replacing the symbol with
nothing. This CL treats non-result op capturing and referencing as a
special case to mean the op itself.
PiperOrigin-RevId: 275269702
|
| |
| |
| |
| |
| |
| |
| |
| |
| | |
NativeCodeCall is handled differently than normal op creation in RewriterGen
(because its flexibility). It will only be materialized to output stream if
it is used. But when using it for auxiliary patterns, we still want the side
effect even if it is not replacing matched root op's results.
PiperOrigin-RevId: 275265467
|
| |
| |
| |
| |
| |
| |
| |
| |
| | |
It's usually hard to understand what went wrong if mlir-tblgen
crashes on some input. This CL adds a few useful LLVM_DEBUG
statements so that we can use mlir-tblegn -debug to figure
out the culprit for a crash.
PiperOrigin-RevId: 275253532
|
| |
| |
| |
| |
| |
| | |
The transpose in the example had the same result type as its input, which is incorrect.
PiperOrigin-RevId: 275186568
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
We just need to implement a few interface hooks to DialectInlinerInterface
and CallOpInterface to gain the benefits of an inliner. :)
Right now only supports some trivial cases:
* Inlining single block with spv.Return/spv.ReturnValue
* Inlining multi block with spv.Return
* Inlining spv.selection/spv.loop without return ops
More advanced cases will require block argument and Phi support.
PiperOrigin-RevId: 275151132
|
| |
| |
| |
| |
| |
| | |
This chapter adds a partial lowering of toy operations, all but PrintOp, to a combination of the Affine and Std dialects. This chapter focuses on introducing the conversion framework, the benefits of partial lowering, and how easily dialects may co-exist in the IR.
PiperOrigin-RevId: 275150649
|
| |
| |
| |
| |
| |
| | |
The GenericCallOp needed to have the CallOpInterface to be picked up by the inliner. This also adds a CastOp to perform shape casts that are generated during inlining. The casts generated by the inliner will be folded away after shape inference.
PiperOrigin-RevId: 275150438
|
| |
| |
| |
| | |
PiperOrigin-RevId: 275147795
|
| |
| |
| |
| |
| |
| |
| |
| | |
Create a ComplexType for table gen references. Include an AnyComplex type
to check whether the resulting tensor can be complex. Expand tensors to
allow complex types.
PiperOrigin-RevId: 275144804
|
| |
| |
| |
| |
| |
| | |
This change performs general cleanups of the implementation of ch.4 and fixes some bugs. For example, the operations currently don't inherit from the shape inference interface.
PiperOrigin-RevId: 275089914
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
This Chapter now introduces and makes use of the Interface concept
in MLIR to demonstrate ShapeInference.
END_PUBLIC
Closes tensorflow/mlir#191
PiperOrigin-RevId: 275085151
|
| |
| |
| |
| | |
PiperOrigin-RevId: 275084969
|
| |
| |
| |
| |
| |
| | |
This was missed when the type was renamed.
PiperOrigin-RevId: 275082588
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Makes the spv.module generated by the GPU to SPIR-V conversion SPIR-V
spec compliant (validated using spirv-val from Vulkan tools).
1) Separate out the VulkanLayoutUtils from
DecorateSPIRVCompositeTypeLayoutPass to make it reusable within the
Type converter in SPIR-V lowering infrastructure. This is used to
compute the layout of the !spv.struct used in global variable type
description.
2) Set the capabilities of the spv.module to Shader (needed for use of
Logical Memory Model, and the extensions to
SPV_KHR_storage_buffer_storage_class for use of Storage Buffer)
PiperOrigin-RevId: 275081486
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
In addition to specifying the type of accumulation through the 'op' attribute, the accumulation can now also be specified as arbitrary code region.
Adds a gpu.yield op to specify the result of the accumulation.
Also support more types (integers) and accumulations (mul).
PiperOrigin-RevId: 275065447
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
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
|
| |
| |
| |
| |
| |
| | |
This hook is useful when an operation is known to be dead, and no replacement values make sense.
PiperOrigin-RevId: 275052756
|
| |
| |
| |
| |
| |
| |
| | |
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
|
| |
| |
| |
| | |
PiperOrigin-RevId: 275025323
|
| |
| |
| |
| | |
PiperOrigin-RevId: 275004258
|
| |
| |
| |
| |
| |
| | |
These traits are added in chapter 3 when we begin discussion optimization on the toy operations.
PiperOrigin-RevId: 274974010
|
| |
| |
| |
| |
| |
| | |
This change refactors the toyc driver to be much cleaner and easier to extend. It also cleans up a few comments in the combiner.
PiperOrigin-RevId: 274973808
|
| |
| |
| |
| | |
PiperOrigin-RevId: 274935374
|
| |
| |
| |
| | |
PiperOrigin-RevId: 274905193
|
| |
| |
| |
| | |
PiperOrigin-RevId: 274902838
|
| |
| |
| |
| |
| |
| | |
This fixes an issue with make where it fails to properly handle the dependency ordering.
PiperOrigin-RevId: 274897702
|
| |
| |
| |
| | |
PiperOrigin-RevId: 274894550
|
| |
| |
| |
| |
| |
| |
| |
| | |
The SpecId decoration is the handle for providing external specialization.
Similar to descriptor set and binding on global variables, we directly
bake it into assembly parsing and printing.
PiperOrigin-RevId: 274893879
|
| |
| |
| |
| | |
PiperOrigin-RevId: 274892763
|
| |
| |
| |
| | |
PiperOrigin-RevId: 274866986
|
| |
| |
| |
| |
| |
| |
| |
| |
| | |
This is using Table-driven Declarative Rewrite Rules (DRR), the previous
version of the tutorial only showed the C++ patterns.
Closes tensorflow/mlir#187
PiperOrigin-RevId: 274852321
|
| |
| |
| |
| | |
PiperOrigin-RevId: 274848361
|
| |
| |
| |
| |
| |
| | |
This should fix the OSS build by only using int in template types.
PiperOrigin-RevId: 274843584
|
| |
| |
| |
| |
| |
| |
| | |
This CL adds a missing lowering for splat of multi-dimensional vectors.
Additional support is also added to the runtime utils library to allow printing memrefs with such vectors.
PiperOrigin-RevId: 274794723
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Python bindings currently currently provide a makeScalarType function that
constructs one of the predefined types. It was implemented in the bindings
directly to circumvent the absence of standalone type parsing function. Now
that mlir::parseType has been made available, rely on the core parsing
procedure to construct types from strings in the bindings.
This changes includes a library reshuffling that splits out "CoreAPIs"
implementing the binding helper APIs into a separate library and makes that
dependent on the Parser library.
PiperOrigin-RevId: 274794516
|
| |
| |
| |
| |
| |
| |
| |
| | |
The value defined in a loop was not being used and the function producing it
re-evaluated instead. Use the value to avoid both the warning and the
re-evaluation.
PiperOrigin-RevId: 274794459
|
| |
| |
| |
| |
| |
| | |
This effectively rewrites Ch.2 to introduce dialects, operations, and registration instead of deferring to Ch.3. This allows for introducing the best practices up front(using ODS, registering operations, etc.), and limits the opaque API to the chapter document instead of the code.
PiperOrigin-RevId: 274724289
|
| |
| |
| |
| |
| |
| | |
It is more idiomatic to use the llvm::cast infrastructure for checking the type of a value.
PiperOrigin-RevId: 274684945
|
| |
| |
| |
| |
| |
| | |
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
|
| |
| |
| |
| |
| |
| | |
ldflags can contain double-quoted paths, so must use single quotes here.
PiperOrigin-RevId: 274581983
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
When the implementation of the strided memref [RFC](https://groups.google.com/a/tensorflow.org/forum/#!msg/mlir/MaL8m2nXuio/1scRqZa6AQAJ) landed, linalg started using this type instead of the now retired !linalg.view.
As static and partially static cases appear, the stride information needs to be maintained properly. In particular, the result type of the subview op was generally incorrect.
This CL fixes the issue by computing a return type that:
1. always has dynamic sizes, which is generally the only correct way to construct a subview in the absence of data padding and/or code versioning.
2. has the same strides as the base strided memref.
Point 1. above can be further refined but will needs further analysis and canonicalization to optimize the particular case where:
1. The base memref has static size along a given dimension.
2. The subview size can be statically derived (e.g. after canonicalization).
3. *And* the subview size is an even divisor of the base memref.
This 3rd constraint is well-known in the case of tiled layouts that don't assume implicit padding: the boundary tile may be only partial and has size given by `problem_size % tile_size`.
Tests are updated as appropriate.
PiperOrigin-RevId: 274578624
|
| |
| |
| |
| |
| |
| |
| |
| |
| | |
This fixes an omission that prevents Linalg to lower generic ops regions operating on ops in the VectorOps dialect.
To achieve this we simply need to `populateVectorToLLVMConversionPatterns` in the conversion.
Relevant tests are added.
PiperOrigin-RevId: 274577325
|
| |
| |
| |
| |
| |
| |
| | |
Closes tensorflow/mlir#184
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/184 from schweitzpgi:more-float-types ca27d00510a86ffc9c79c65fb3a0193b5ea097a0
PiperOrigin-RevId: 274288813
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Originally, the lowering of `alloc` operations has been computing the number of
bytes to allocate when lowering based on the properties of MLIR type. This does
not take into account type legalization that happens when compiling LLVM IR
down to target assembly. This legalization can widen the type, potentially
leading to out-of-bounds accesses to `alloc`ed data due to mismatches between
address computation that takes the widening into account and allocation that
does not. Use the LLVM IR's equivalent of `sizeof` to compute the number of
bytes to be allocated:
%0 = getelementptr %type* null, %indexType 0
%1 = ptrtoint %type* %0 to %indexType
adapted from
http://nondot.org/sabre/LLVMNotes/SizeOf-OffsetOf-VariableSizedStructs.txt
PiperOrigin-RevId: 274159900
|
| |
| |
| |
| |
| |
| |
| |
| | |
Similarly to `llvm.mlir.undef`, this auxiliary operation creates an SSA value
that corresponds to `null` in LLVM IR. This operation is necessary to model
sizeof(<...>) behavior when allocating memory.
PiperOrigin-RevId: 274158760
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
- dropping what looks like outdated code post some of the previous
updates
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#179
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/179 from bondhugula:llfix 2a72ea441fe1b3924802273ffbe9870afeb90f91
PiperOrigin-RevId: 274158273
|
| |
| |
| |
| | |
PiperOrigin-RevId: 274154655
|
| |
| |
| |
| | |
PiperOrigin-RevId: 274152154
|