Uday Bondhugula [Sat, 7 Sep 2019 16:59:47 +0000 (09:59 -0700)]
Set mlir-cpu-runner JIT codegen opt level correctly
- the JIT codegen was being run at the default -O0 level; instead,
propagate the opt level from the cmd line.
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#123
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/123 from bondhugula:jit-runner
3b055e47f94c9a48bf487f6400787478738cda02
PiperOrigin-RevId:
267778586
Mehdi Amini [Sat, 7 Sep 2019 15:53:24 +0000 (08:53 -0700)]
Wrap debug dump in LLVM_DEBUG
PiperOrigin-RevId:
267774506
Lei Zhang [Sat, 7 Sep 2019 12:25:39 +0000 (05:25 -0700)]
Add doc for declarative rewrite rules
This doc serves as a manual for table-driven declarative rewrite rules.
It lists all the details regarding supported mechanisms.
PiperOrigin-RevId:
267761702
Mehdi Amini [Fri, 6 Sep 2019 19:30:06 +0000 (12:30 -0700)]
Fix typo in the documentation for tensor_cast (NFC)
PiperOrigin-RevId:
267650411
River Riddle [Fri, 6 Sep 2019 18:43:35 +0000 (11:43 -0700)]
Restrict affine inlining to just Function operations.
The current restrictions on dim/symbols require a top-level symbol for the conservative case of a non-affine region. This should be relaxed in the future.
PiperOrigin-RevId:
267641838
Nagy Mostafa [Fri, 6 Sep 2019 18:02:31 +0000 (11:02 -0700)]
Add custom builder for AffineIfOp
Closes tensorflow/mlir#109
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/109 from nmostafa:nmostafa/AffineIfOp
7dbf2115f0092ffab26381ea8704aa05a0253971
PiperOrigin-RevId:
267633077
Nicolas Vasilache [Fri, 6 Sep 2019 15:30:54 +0000 (08:30 -0700)]
Simplify Linalg ABI integration with external function calls.
View descriptors are converted to *pointer to* LLVM struct to avoid ABI issues related to C struct packing. This creates unnecessary complexity and hampers unification with memrefs.
Instead, this CL makes view descriptors convert to LLVM struct (as it was originally) and promotes all structs to pointers right before calling an external function.
PiperOrigin-RevId:
267602693
Alex Zinenko [Fri, 6 Sep 2019 08:22:24 +0000 (01:22 -0700)]
Fix typos in Interfaces.md
PiperOrigin-RevId:
267548530
Uday Bondhugula [Fri, 6 Sep 2019 06:12:01 +0000 (23:12 -0700)]
Integer set + operands / affine if op canonicalization
- turn canonicalizeMapAndOperands into a template that works on both
sets and maps, and use it to introduce a utility to canonicalize an
affine integer set and its operands
- add pattern to canonicalize affine if op's.
- rename IntegerSet::getNumOperands -> IntegerSet::getNumInputs to be
consistent with AffineMap
- add missing accessors for IntegerSet
Doesn't need extensive testing since canonicalizeSetAndOperands just
reuses canonicalizeMapAndOperands' logic, and the latter is tested on
affine.apply map + operands; the new method works the same way on an
integer set + operands of an affine if op for example.
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#112
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/112 from bondhugula:set-canonicalize
eff72f23250b96fa7d9f5caff3877440f5de2cec
PiperOrigin-RevId:
267532876
River Riddle [Thu, 5 Sep 2019 22:19:55 +0000 (15:19 -0700)]
Add support for conservatively inlining Affine operations.
This commit defines an initial implementation of the DialectInlinerInterface for the AffineOps dialect. This change allows for affine operations to be inlined into any region that is not an affine region. Inlining into affine regions requires special handling for dimension/symbol identifiers that will be added in followups.
PiperOrigin-RevId:
267467078
Lei Zhang [Thu, 5 Sep 2019 19:45:08 +0000 (12:45 -0700)]
[spirv] Add spv.loop
SPIR-V can explicitly declare structured control-flow constructs using merge
instructions. These explicitly declare a header block before the control
flow diverges and a merge block where control flow subsequently converges.
These blocks delimit constructs that must nest, and can only be entered
and exited in structured ways.
Instead of having a `spv.LoopMerge` op to directly model loop merge
instruction for indicating the merge and continue target, we use regions
to delimit the boundary of the loop: the merge target is the next op
following the `spv.loop` op and the continue target is the block that
has a back-edge pointing to the entry block inside the `spv.loop`'s region.
This way it's easier to discover all blocks belonging to a construct and
it plays nicer with the MLIR system.
Updated the SPIR-V.md doc.
PiperOrigin-RevId:
267431010
River Riddle [Thu, 5 Sep 2019 19:23:45 +0000 (12:23 -0700)]
Add the initial inlining infrastructure.
This defines a set of initial utilities for inlining a region(or a FuncOp), and defines a simple inliner pass for testing purposes.
A new dialect interface is defined, DialectInlinerInterface, that allows for dialects to override hooks controlling inlining legality. The interface currently provides the following hooks, but these are just premilinary and should be changed/added to/modified as necessary:
* isLegalToInline
- Determine if a region can be inlined into one of this dialect, *or* if an operation of this dialect can be inlined into a given region.
* shouldAnalyzeRecursively
- Determine if an operation with regions should be analyzed recursively for legality. This allows for child operations to be closed off from the legality checks for operations like lambdas.
* handleTerminator
- Process a terminator that has been inlined.
This cl adds support for inlining StandardOps, but other dialects will be added in followups as necessary.
PiperOrigin-RevId:
267426759
Stephan Herhut [Thu, 5 Sep 2019 08:45:40 +0000 (01:45 -0700)]
Make GPU kernel outlining test independent of value names.
PiperOrigin-RevId:
267323604
Smit Hinsu [Thu, 5 Sep 2019 06:15:33 +0000 (23:15 -0700)]
Generalize I32ElementsAttr definition and introduce I64ElementsAttr
Also, fix constBuilderCall to return attribute of the storage class DenseIntElementsAttr
PiperOrigin-RevId:
267305813
Nicolas Vasilache [Thu, 5 Sep 2019 02:16:32 +0000 (19:16 -0700)]
Use transform function on llvm::Module in the ExecutionEngine
The refactoring of ExecutionEngine dropped the usage of the irTransform function used to pass -O3 and other options to LLVM. As a consequence, the proper optimizations do not kick in in LLMV-land.
This CL makes use of the transform function and allows producing avx512 instructions, on an internal example, when using:
`mlir-cpu-runner -dump-object-file=1 -object-filename=foo.o` combined with `objdump -D foo.o`.
Assembly produced resembles:
```
2b2e: 62 72 7d 48 18 04 0e vbroadcastss (%rsi,%rcx,1),%zmm8
2b35: 62 71 7c 48 28 ce vmovaps %zmm6,%zmm9
2b3b: 62 72 3d 48 a8 c9 vfmadd213ps %zmm1,%zmm8,%zmm9
2b41: 62 f1 7c 48 28 cf vmovaps %zmm7,%zmm1
2b47: 62 f2 3d 48 a8 c8 vfmadd213ps %zmm0,%zmm8,%zmm1
2b4d: 62 f2 7d 48 18 44 0e vbroadcastss 0x4(%rsi,%rcx,1),%zmm0
2b54: 01
2b55: 62 71 7c 48 28 c6 vmovaps %zmm6,%zmm8
2b5b: 62 72 7d 48 a8 c3 vfmadd213ps %zmm3,%zmm0,%zmm8
2b61: 62 f1 7c 48 28 df vmovaps %zmm7,%zmm3
2b67: 62 f2 7d 48 a8 da vfmadd213ps %zmm2,%zmm0,%zmm3
2b6d: 62 f2 7d 48 18 44 0e vbroadcastss 0x8(%rsi,%rcx,1),%zmm0
2b74: 02
2b75: 62 f2 7d 48 a8 f5 vfmadd213ps %zmm5,%zmm0,%zmm6
2b7b: 62 f2 7d 48 a8 fc vfmadd213ps %zmm4,%zmm0,%zmm7
```
etc.
Fixes tensorflow/mlir#120
PiperOrigin-RevId:
267281097
Rob Suderman [Thu, 5 Sep 2019 00:24:04 +0000 (17:24 -0700)]
Updated StructAttr to use the struct name for StorageType and ReturnType.
PiperOrigin-RevId:
267266687
MLIR Team [Wed, 4 Sep 2019 19:26:11 +0000 (12:26 -0700)]
Retain address space during MLIR > LLVM conversion.
PiperOrigin-RevId:
267206460
Alex Zinenko [Wed, 4 Sep 2019 15:37:39 +0000 (08:37 -0700)]
Move LLVMIR dialect tests from test/LLVMIR to test/Dialect and test/Conversion
This follows up on the recent restructuring that moved the dialects under
lib/Dialect and inter-dialect conversions to lib/Conversion. Originally, the
tests for both the LLVMIR dialect itself and the conversion from Standard to
LLVMIR dialect lived under test/LLVMIR. This no longer reflects the code
structure. Move the tests to either test/Dialect/LLVMIR or
test/Conversion/StandardToLLVM depending on the features they exercise.
PiperOrigin-RevId:
267159219
Jacques Pienaar [Wed, 4 Sep 2019 14:02:37 +0000 (07:02 -0700)]
Make isIsolatedAbove robuster to invalid IR
This function is only called from the verifier.
PiperOrigin-RevId:
267145495
Uday Bondhugula [Wed, 4 Sep 2019 13:58:39 +0000 (06:58 -0700)]
pipeline-data-transfer: remove dead tag alloc's and improve test coverage for replaceMemRefUsesWith / pipeline-data-transfer
- address remaining comments from PR tensorflow/mlir#87 for better test coverage for
pipeline-data-transfer/replaceAllMemRefUsesWith
- remove dead tag allocs the same way they are removed for the replaced buffers
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#106
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/106 from bondhugula:followup
9e868666d047e8d43e5f82f43e4093b838c710fa
PiperOrigin-RevId:
267144774
Alex Zinenko [Wed, 4 Sep 2019 13:32:54 +0000 (06:32 -0700)]
Move Linalg dialect tests to test/Dialect/Linalg
This was missing from the commit that moved the Linalg dialect to lib/Dialect.
PiperOrigin-RevId:
267141176
Stephan Herhut [Wed, 4 Sep 2019 13:15:40 +0000 (06:15 -0700)]
Make GPU kernel outlining inline constants.
It is generally beneficial to pass less arguments to a kernel, so cloning constants
into the kernel is beneficial.
PiperOrigin-RevId:
267139084
MLIR Team [Wed, 4 Sep 2019 10:45:38 +0000 (03:45 -0700)]
Add support for array-typed constants.
PiperOrigin-RevId:
267121729
Alex Zinenko [Wed, 4 Sep 2019 10:01:17 +0000 (03:01 -0700)]
Update the syntax of splat attribute in LLVM.md
The syntax for splat attributes changed, but was not updated in the description
of the LLVM dialect constant operations in LLVM.md. Update the document to use
the correct syntax. Also add a dialect roundtrip test for such attribute,
which was previously missing.
PiperOrigin-RevId:
267116305
Alex Zinenko [Wed, 4 Sep 2019 09:42:50 +0000 (02:42 -0700)]
Mention clang-format in the developer guide
PiperOrigin-RevId:
267114122
Nicolas Vasilache [Tue, 3 Sep 2019 22:27:49 +0000 (15:27 -0700)]
Properly clone Linalg ops with regions
This CL adds support for proper cloning of Linalg ops that have regions (i.e. the generic linalg op). This is used to properly implement tiling and fusion for such ops. Adequate tests are added.
PiperOrigin-RevId:
267027176
Uday Bondhugula [Tue, 3 Sep 2019 19:13:59 +0000 (12:13 -0700)]
Utility to normalize memrefs with non-identity layout maps
- introduce utility to convert memrefs with non-identity layout maps to
ones with identity layout maps: convert the type and rewrite/remap all
its uses
- add this utility to -simplify-affine-structures pass for testing
purposes
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#104
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/104 from bondhugula:memref-normalize
f2c914aa1890e8860326c9e33f9aa160b3d65e6d
PiperOrigin-RevId:
266985317
Lei Zhang [Tue, 3 Sep 2019 19:09:07 +0000 (12:09 -0700)]
Add folding rule and dialect materialization hook for spv.constant
This will allow us to use MLIR's folding infrastructure to deduplicate
SPIR-V constants.
This CL also changed isValidSPIRVType in SPIRVDialect to a static method.
PiperOrigin-RevId:
266984403
Uday Bondhugula [Tue, 3 Sep 2019 18:52:39 +0000 (11:52 -0700)]
Fix affine data copy generation corner cases/bugs
- the [begin, end) range identified for copying could end in between the
block, which makes hoisting invalid in some cases. Change the range
identification to always end with end of block.
- add test case to exercise these (with fast mem capacity set to minimal so
that single element memref buffers are generated at the innermost loop)
- the location of begin/end of the block range for data copying was
being confused with the insert points for copy in and copy out code.
In cases, where we choose to hoist transfers, these are separate.
- when copy loops are single iteration ones, promote their bodies at
the end of the pass.
- change default fast mem space to 1 (setting it to zero made it
generate DMA op's that won't verify in the default case - since the
DMA ops have a check for src/dest memref spaces being different).
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Co-Authored-By: Mehdi Amini <joker.eph@gmail.com>
Closes tensorflow/mlir#88
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/88 from bondhugula:datacopy
88697267c45e850c3ced87671e16e4a930c02a42
PiperOrigin-RevId:
266980911
MLIR Team [Tue, 3 Sep 2019 18:39:36 +0000 (11:39 -0700)]
Add information about the SIG + Open Design meetings to the README.
PiperOrigin-RevId:
266978247
River Riddle [Tue, 3 Sep 2019 18:27:00 +0000 (11:27 -0700)]
Fix an invalid assert when processing escaped strings.
The assert assumed that the escaped character could not appear at the end of the string.
Fixes tensorflow/mlir#117
PiperOrigin-RevId:
266975471
Alex Torres [Tue, 3 Sep 2019 18:12:25 +0000 (11:12 -0700)]
Remove unused variables
Remove unused variables and attributes from BaseViewConversionHelper
on mlir/lib/Dialect/Linalg/Transforms/LowerToLLVMDialect.cpp
Closes tensorflow/mlir#116
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/116 from alexst07:fix-warnings
5f638e4677492cf71a9cc040eeb6b57427d32e06
PiperOrigin-RevId:
266972082
Alex Zinenko [Tue, 3 Sep 2019 16:10:24 +0000 (09:10 -0700)]
LLVM dialect: prefix auxiliary operations with "mlir."
Some of the operations in the LLVM dialect are required to model the LLVM IR in
MLIR, for example "constant" operations are needed to declare a constant value
since MLIR, unlike LLVM, does not support immediate values as operands. To
avoid confusion with actual LLVM operations, we prefix such axuiliary
operations with "mlir.".
PiperOrigin-RevId:
266942838
Smit Hinsu [Tue, 3 Sep 2019 06:43:36 +0000 (23:43 -0700)]
Support bf16 in Builder::getZeroAttr
PiperOrigin-RevId:
266863802
Mahesh Ravishankar [Tue, 3 Sep 2019 04:06:35 +0000 (21:06 -0700)]
Add Select operation to SPIR-V dialect.
The SelectOp models the semantics of OpSelect from SPIR-V spec.
PiperOrigin-RevId:
266849559
Smit Hinsu [Tue, 3 Sep 2019 02:59:08 +0000 (19:59 -0700)]
Enable OwningRewritePatternList insert overload with parameter pack only when
there is at least one template pattern type
Also remove the other insert overload with pattern pointer as there are no existing users nor any potential known use-case.
PiperOrigin-RevId:
266842920
River Riddle [Tue, 3 Sep 2019 02:24:47 +0000 (19:24 -0700)]
Refactor the pass manager to support operations other than FuncOp/ModuleOp.
This change generalizes the structure of the pass manager to allow arbitrary nesting pass managers for other operations, at any level. The only user visible change to existing code is the fact that a PassManager must now provide an MLIRContext on construction. A new class `OpPassManager` has been added that represents a pass manager on a specific operation type. `PassManager` will remain the top-level entry point into the pipeline, with OpPassManagers being nested underneath. OpPassManagers will still be implicitly nested if the operation type on the pass differs from the pass manager. To explicitly build a pipeline, the 'nest' methods on OpPassManager may be used:
// Pass manager for the top-level module.
PassManager pm(ctx);
// Nest a pipeline operating on FuncOp.
OpPassManager &fpm = pm.nest<FuncOp>();
fpm.addPass(...);
// Nest a pipeline under the FuncOp pipeline that operates on spirv::ModuleOp
OpPassManager &spvModulePM = pm.nest<spirv::ModuleOp>();
// Nest a pipeline on FuncOps inside of the spirv::ModuleOp.
OpPassManager &spvFuncPM = spvModulePM.nest<FuncOp>();
To help accomplish this a new general OperationPass is added that operates on opaque Operations. This pass can be inserted in a pass manager of any type to operate on any operation opaquely. An example of this opaque OperationPass is a VerifierPass, that simply runs the verifier opaquely on the current operation.
/// Pass to verify an operation and signal failure if necessary.
class VerifierPass : public OperationPass<VerifierPass> {
void runOnOperation() override {
Operation *op = getOperation();
if (failed(verify(op)))
signalPassFailure();
markAllAnalysesPreserved();
}
};
PiperOrigin-RevId:
266840344
River Riddle [Mon, 2 Sep 2019 03:06:42 +0000 (20:06 -0700)]
Add a new dialect interface for the OperationFolder `OpFolderDialectInterface`.
This interface will allow for providing hooks to interrop with operation folding. The first hook, 'shouldMaterializeInto', will allow for controlling which region to insert materialized constants into. The folder will generally materialize constants into the top-level isolated region, this allows for materializing into a lower level ancestor region if it is more profitable/correct.
PiperOrigin-RevId:
266702972
Mehdi Amini [Sun, 1 Sep 2019 23:31:40 +0000 (16:31 -0700)]
Add a `getUsedValuesDefinedAbove()` overload that takes an `Operation` pointer (NFC)
This is a convenient utility around the existing `getUsedValuesDefinedAbove()`
that take two regions.
PiperOrigin-RevId:
266686854
Mehdi Amini [Sun, 1 Sep 2019 23:15:14 +0000 (16:15 -0700)]
Add a convenient `clone()` method on the `Op` class that forward to the underlying `Operation` (NFC)
PiperOrigin-RevId:
266685852
Mehdi Amini [Sun, 1 Sep 2019 18:32:52 +0000 (11:32 -0700)]
Add missing lowering to CFG in mlir-cpu-runner + related cleanup
- the list of passes run by mlir-cpu-runner included -lower-affine and
-lower-to-llvm but was missing -lower-to-cfg (because -lower-affine at
some point used to lower straight to CFG); add -lower-to-cfg in
between. IR with affine ops can now be run by mlir-cpu-runner.
- update -lower-to-cfg to be consistent with other passes (create*Pass methods
were changed to return unique ptrs, but -lower-to-cfg appears to have been
missed).
- mlir-cpu-runner was unable to parse custom form of affine op's - fix
link options
- drop unnecessary run options from test/mlir-cpu-runner/simple.mlir
(none of the test cases had loops)
- -convert-to-llvmir was changed to -lower-to-llvm at some point, but the
create pass method name wasn't updated (this pass converts/lowers to LLVM
dialect as opposed to LLVM IR). Fix this.
(If we prefer "convert", the cmd-line options could be changed to
"-convert-to-llvm/cfg" then.)
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#115
PiperOrigin-RevId:
266666909
Mehdi Amini [Sat, 31 Aug 2019 22:23:31 +0000 (15:23 -0700)]
Add a link to the rational on lack of const for IR units in the developer guide
PiperOrigin-RevId:
266583374
Mehdi Amini [Sat, 31 Aug 2019 22:17:42 +0000 (15:17 -0700)]
Document that non-IR units are passed by non-const reference instead of pointer in general
PiperOrigin-RevId:
266583029
Mahesh Ravishankar [Sat, 31 Aug 2019 16:52:18 +0000 (09:52 -0700)]
Add floating-point comparison operations to SPIR-V dialect.
Use the existing SPV_LogicalOp specification to add the floating-point
comparison operations (both ordered and unordered versions).
To make it easier to import the op-definitions automatically modify
the dialect generation script to update the different .td files based
on whether the operation is an arithmetic op, logical op, etc. Also
allow specification of multiple opcodes with define_inst.sh.
Since this reuses the SPV_LogicalOp framework, no tests specific to
the floating point comparison ops are added with this CL.
PiperOrigin-RevId:
266561634
Lei Zhang [Sat, 31 Aug 2019 16:50:02 +0000 (09:50 -0700)]
Add missing link dependency to MLIRTableGenTests
PiperOrigin-RevId:
266561495
Uday Bondhugula [Sat, 31 Aug 2019 00:38:36 +0000 (17:38 -0700)]
update vim syntax file
- more highlighting: numbers, elemental types inside shaped types
- add some more keywords
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#110
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/110 from bondhugula:vim
029777db0ecb95bfc6453c0869af1c233d84d521
PiperOrigin-RevId:
266487768
River Riddle [Fri, 30 Aug 2019 23:49:01 +0000 (16:49 -0700)]
Add a canonicalization to erase empty AffineForOps.
AffineForOp themselves are pure and can be removed if there are no internal operations.
PiperOrigin-RevId:
266481293
MLIR Team [Fri, 30 Aug 2019 22:40:51 +0000 (15:40 -0700)]
Splits DictionaryAttr into DictionaryAttrBase and DictionaryAttr.
This maintains consistency with other *AttrBase/Attr splits.
PiperOrigin-RevId:
266469869
Logan Chien [Fri, 30 Aug 2019 21:53:28 +0000 (14:53 -0700)]
Add TensorRankOf for ranked tensor types with specific ranks
This commit adds `TensorRankOf<types, typeNames, ranks>` to specify ranked
tensor types with the specified types and ranks. For example,
`TensorRankOf<[I32, F32], ["i32", "F32"], [0, 1]>` matches `tensor<i32>`,
`tensor<?xi32>`, `tensor<f32>`, or `tensor<?xf32>`.
PiperOrigin-RevId:
266461256
Rob Suderman [Fri, 30 Aug 2019 21:09:46 +0000 (14:09 -0700)]
Fix StructsGenTest.cpp CMakeFile build error
PiperOrigin-RevId:
266452719
River Riddle [Fri, 30 Aug 2019 20:16:13 +0000 (13:16 -0700)]
Generalize the pass hierarchy by adding a general OpPass<PassT, OpT>.
This pass class generalizes the current functionality between FunctionPass and ModulePass, and allows for operating on any operation type. The pass manager currently only supports OpPasses operating on FuncOp and ModuleOp, but this restriction will be relaxed in follow-up changes. A utility class OpPassBase<OpT> allows for generically referring to operation specific passes: e.g. FunctionPassBase == OpPassBase<FuncOp>.
PiperOrigin-RevId:
266442239
Jacques Pienaar [Fri, 30 Aug 2019 20:01:34 +0000 (13:01 -0700)]
Add mechanism to dump JIT-compiled objects to files
This commit introduces the bits to be able to dump JIT-compile
objects to external files by passing an object cache to OrcJit.
The new functionality is tested in mlir-cpu-runner under the flag
`dump-object-file`.
Closes tensorflow/mlir#95
PiperOrigin-RevId:
266439265
Rob Suderman [Fri, 30 Aug 2019 19:51:31 +0000 (12:51 -0700)]
Added a TableGen generator for structured data
Similar to enum, added a generator for structured data. This provide Dictionary that stores a fixed set of values and guarantees the values are valid. It is intended to store a fixed number of values by a given name.
PiperOrigin-RevId:
266437460
River Riddle [Fri, 30 Aug 2019 19:47:24 +0000 (12:47 -0700)]
Add support for early exit walk methods.
This is done by providing a walk callback that returns a WalkResult. This result is either `advance` or `interrupt`. `advance` means that the walk should continue, whereas `interrupt` signals that the walk should stop immediately. An example is shown below:
auto result = op->walk([](Operation *op) {
if (some_invariant)
return WalkResult::interrupt();
return WalkResult::advance();
});
if (result.wasInterrupted())
...;
PiperOrigin-RevId:
266436700
Lei Zhang [Fri, 30 Aug 2019 19:17:21 +0000 (12:17 -0700)]
Add spv.Branch and spv.BranchConditional
This CL just covers the op definition, its parsing, printing,
and verification. (De)serialization is to be implemented
in a subsequent CL.
PiperOrigin-RevId:
266431077
River Riddle [Fri, 30 Aug 2019 05:19:29 +0000 (22:19 -0700)]
Change the parseSource* methods to return OwningModuleRef instead of ModuleOp.
This avoids potential memory leaks from misuse of the API.
PiperOrigin-RevId:
266305750
River Riddle [Thu, 29 Aug 2019 20:04:22 +0000 (13:04 -0700)]
Refactor the 'walk' methods for operations.
This change refactors and cleans up the implementation of the operation walk methods. After this refactoring is that the explicit template parameter for the operation type is no longer needed for the explicit op walks. For example:
op->walk<AffineForOp>([](AffineForOp op) { ... });
is now accomplished via:
op->walk([](AffineForOp op) { ... });
PiperOrigin-RevId:
266209552
Jacques Pienaar [Thu, 29 Aug 2019 19:14:02 +0000 (12:14 -0700)]
Make dumping using generic form more robust when IR ill-formed
PiperOrigin-RevId:
266198057
Feng Liu [Thu, 29 Aug 2019 17:08:46 +0000 (10:08 -0700)]
Add tests to verify 0.0 is quantized correctly
We should consider both signed and narrow_range cases.
PiperOrigin-RevId:
266167366
Uday Bondhugula [Thu, 29 Aug 2019 08:13:01 +0000 (01:13 -0700)]
Extend map canonicalization to propagate constant operands
- extend canonicalizeMapAndOperands to propagate constant operands into
the map's expressions (and thus drop those operands).
- canonicalizeMapAndOperands previously only dropped duplicate and
unused operands; however, operands that were constants were
retained.
This change makes IR maps/expressions generated by various
utilities/passes even simpler; also makes some of the test checks more
accurate and simpler -- for eg., 0' instead of symbol(%{{.*}}).
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#107
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/107 from bondhugula:canonicalize-maps
c889a51486d14fbf7db489f224f881e7e1ff7d72
PiperOrigin-RevId:
266085289
Uday Bondhugula [Thu, 29 Aug 2019 06:42:17 +0000 (23:42 -0700)]
fix loop unroll and jam - operand mapping - imperfect nest case
- fix operand mapping while cloning sub-blocks to jam - was incorrect
for imperfect nests where def/use was across sub-blocks
- strengthen/generalize the first test case to cover the previously
missed scenario
- clean up the other cases while on this.
Previously, unroll-jamming the following nest
```
affine.for %arg0 = 0 to 2048 {
%0 = alloc() : memref<512x10xf32>
affine.for %arg1 = 0 to 10 {
%1 = affine.load %0[%arg0, %arg1] : memref<512x10xf32>
}
dealloc %0 : memref<512x10xf32>
}
```
would yield
```
%0 = alloc() : memref<512x10xf32>
%1 = affine.apply #map0(%arg0)
%2 = alloc() : memref<512x10xf32>
affine.for %arg1 = 0 to 10 {
%4 = affine.load %0[%arg0, %arg1] : memref<512x10xf32>
%5 = affine.apply #map0(%arg0)
%6 = affine.load %0[%5, %arg1] : memref<512x10xf32>
}
dealloc %0 : memref<512x10xf32>
%3 = affine.apply #map0(%arg0)
dealloc %0 : memref<512x10xf32>
```
instead of
```
module {
affine.for %arg0 = 0 to 2048 step 2 {
%0 = alloc() : memref<512x10xf32>
%1 = affine.apply #map0(%arg0)
%2 = alloc() : memref<512x10xf32>
affine.for %arg1 = 0 to 10 {
%4 = affine.load %0[%arg0, %arg1] : memref<512x10xf32>
%5 = affine.apply #map0(%arg0)
%6 = affine.load %2[%5, %arg1] : memref<512x10xf32>
}
dealloc %0 : memref<512x10xf32>
%3 = affine.apply #map0(%arg0)
dealloc %2 : memref<512x10xf32>
}
```
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#98
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/98 from bondhugula:ujam
ddbc853f69b5608b3e8ff9b5ac1f6a5a0bb315a4
PiperOrigin-RevId:
266073460
Stephan Herhut [Thu, 29 Aug 2019 06:39:20 +0000 (23:39 -0700)]
Add verification for dimension attribute on GPUDialect index operations.
PiperOrigin-RevId:
266073204
Uday Bondhugula [Thu, 29 Aug 2019 06:22:39 +0000 (23:22 -0700)]
Add vim scripts for indent/syntax
- some of it has been adapted from LLVM's vim utils
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#90
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/90 from bondhugula:vim
22b1c958818c4b09de0ec8e1d7a4893171a03dbf
PiperOrigin-RevId:
266071752
Feng Liu [Wed, 28 Aug 2019 23:39:18 +0000 (16:39 -0700)]
Fix the equality check of two floating point values
PiperOrigin-RevId:
266022088
River Riddle [Wed, 28 Aug 2019 22:10:37 +0000 (15:10 -0700)]
Generalize the analysis manager framework to work on any operation at any nesting.
The pass manager is moving towards being able to run on operations at arbitrary nesting. An operation may have both parent and child operations, and the AnalysisManager must be able to handle this generalization. The AnalysisManager class now contains generic 'getCachedParentAnalysis' and 'getChildAnalysis/getCachedChildAnalysis' functions to query analyses on parent/child operations. This removes the hard coded nesting relationship between Module/Function.
PiperOrigin-RevId:
266003636
Eric Schweitz [Wed, 28 Aug 2019 20:55:11 +0000 (13:55 -0700)]
Tweak to the pretty type parser to recognize that `->` is a special token.
Tweak to the pretty type parser to recognize that `->` is a special token that
shouldn't be split into two characters. This change allows dialect
types to wrap function types as in `!my.ptr_type<(i32) -> i32>`.
Closes tensorflow/mlir#105
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/mlir/pull/105 from schweitzpgi:parse-arrow
8b2d768053f419daae5a1a864121a44c4319acbe
PiperOrigin-RevId:
265986240
Stephan Herhut [Wed, 28 Aug 2019 18:25:19 +0000 (11:25 -0700)]
Add implementation for tensor_load and tensor_store operations.
This change adds definitions, parsing and verification for both ops.
PiperOrigin-RevId:
265954051
Stephan Herhut [Wed, 28 Aug 2019 08:50:28 +0000 (01:50 -0700)]
Port mlir-cuda-runner to use dialect conversion framework.
Instead of lowering the program in two steps (Standard->LLVM followed
by GPU->NVVM), leading to invalid IR inbetween, the runner now uses
one pattern based rewrite step to go directly from Standard+GPU to
LLVM+NVVM.
PiperOrigin-RevId:
265861934
Uday Bondhugula [Wed, 28 Aug 2019 00:56:25 +0000 (17:56 -0700)]
Refactor / improve replaceAllMemRefUsesWith
Refactor replaceAllMemRefUsesWith to split it into two methods: the new
method does the replacement on a single op, and is used by the existing
one.
- make the methods return LogicalResult instead of bool
- Earlier, when replacement failed (due to non-deferencing uses of the
memref), the set of ops that had already been processed would have
been replaced leaving the IR in an inconsistent state. Now, a
pass is made over all ops to first check for non-deferencing
uses, and then replacement is performed. No test cases were affected
because all clients of this method were first checking for
non-deferencing uses before calling this method (for other reasons).
This isn't true for a use case in another upcoming PR (scalar
replacement); clients can now bail out with consistent IR on failure
of replaceAllMemRefUsesWith. Add test case.
- multiple deferencing uses of the same memref in a single op is
possible (we have no such use cases/scenarios), and this has always
remained unsupported. Add an assertion for this.
- minor fix to another test pipeline-data-transfer case.
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
Closes tensorflow/mlir#87
PiperOrigin-RevId:
265808183
River Riddle [Tue, 27 Aug 2019 19:43:55 +0000 (12:43 -0700)]
Update Ch.2 of the Toy tutorial.
The code and documentation for this chapter of the tutorial have been updated to follow the new flow. The toy 'array' type has been replaced by usages of the MLIR tensor type. The code has also been cleaned up and modernized.
Closes tensorflow/mlir#101
PiperOrigin-RevId:
265744086
MLIR Team [Tue, 27 Aug 2019 17:55:47 +0000 (10:55 -0700)]
Add 3 additional intrinsic ops to NVVM dialect, in preparation to implement block-wide reduce.
PiperOrigin-RevId:
265720077
Lei Zhang [Tue, 27 Aug 2019 17:50:58 +0000 (10:50 -0700)]
[spirv] Fix the entry block to start with OpLabel
Each basic block in SPIR-V must start with an OpLabel instruction.
We don't support control flow yet, so this CL just makes sure that
the entry block follows this rule and is valid.
PiperOrigin-RevId:
265718841
Mahesh Ravishankar [Tue, 27 Aug 2019 17:49:53 +0000 (10:49 -0700)]
Enhance GPU To SPIR-V conversion to support builtins and load/store ops.
To support a conversion of a simple load-compute-store kernel from GPU
dialect to SPIR-V dialect, the conversion of operations like
"gpu.block_dim", "gpu.thread_id" which allow threads to get the launch
conversion is needed. In SPIR-V these are specified as global
variables with builin attributes. This CL adds support to specify
builtin variables in SPIR-V conversion framework. This is used to
convert the relevant operations from GPU dialect to SPIR-V dialect.
Also add support for conversion of load/store operation in Standard
dialect to SPIR-V dialect.
To simplify the conversion add a method to build a spv.AccessChain
operation that automatically determines the return type based on the
base pointer type and the indices provided.
PiperOrigin-RevId:
265718525
Denis Khalikov [Tue, 27 Aug 2019 17:41:07 +0000 (10:41 -0700)]
[spirv] Add Block decoration for spv.struct.
Add Block decoration for top-level spv.struct.
Closes tensorflow/mlir#102
PiperOrigin-RevId:
265716241
River Riddle [Tue, 27 Aug 2019 00:34:06 +0000 (17:34 -0700)]
NFC: Remove the explicit context from Operation::create and OperationState.
The context can easily be recovered from the Location in these situations.
PiperOrigin-RevId:
265578574
Eric Schweitz [Mon, 26 Aug 2019 21:18:47 +0000 (14:18 -0700)]
Add FPToSI/FPExt/FPTrunc cast ops to the LLVM dialect.
Closes tensorflow/mlir#99
PiperOrigin-RevId:
265538731
River Riddle [Mon, 26 Aug 2019 20:53:22 +0000 (13:53 -0700)]
NFC: Remove unnecessary context parameters from several Location getters.
The context can be recovered by other means in these methods and doesn't need to be passed explicitly.
PiperOrigin-RevId:
265532956
MLIR Team [Mon, 26 Aug 2019 17:27:38 +0000 (10:27 -0700)]
Update documentation for custom rewrite specs.
PiperOrigin-RevId:
265485862
Andy Ly [Mon, 26 Aug 2019 16:44:09 +0000 (09:44 -0700)]
Support folding of ops with inner ops in GreedyPatternRewriteDriver.
This fixes a bug when folding ops with inner ops and inner ops are still being visited.
PiperOrigin-RevId:
265475780
Alina Sbirlea [Sat, 24 Aug 2019 04:00:40 +0000 (21:00 -0700)]
NFC: Add doc for id-punct
PiperOrigin-RevId:
265190168
River Riddle [Sat, 24 Aug 2019 01:11:29 +0000 (18:11 -0700)]
NFC: Update Ch.1 of the Toy tutorial.
Change the use of 'array' to 'tensor' to reflect the new flow that the tutorial will follow. Also tidy up some of the documentation, code comments, and fix a few out-dated links.
PiperOrigin-RevId:
265174676
Nicolas Vasilache [Sat, 24 Aug 2019 00:44:55 +0000 (17:44 -0700)]
Lower linalg.copy to LLVM dialect in the presence of transposes.
Add an extra RewritePattern that does not convert types to rewrite a CopyOp that has non-identity permutations into a sequence of TransposeOp followed by a CopyOp without such permutations.
This RewitePattern is made to fail in the non-permutation case so that the conversion pattern can kick in to lower to LLVM.
This is an instance of A->A->B lowering where A->A is done by a RewritePattern in case_1 and A->B is done by a ConversionPatternRewriter when not(case_1).
PiperOrigin-RevId:
265171380
Nicolas Vasilache [Sat, 24 Aug 2019 00:28:51 +0000 (17:28 -0700)]
Lower linalg.transpose to LLVM dialect
Add a conversion pattern that transforms a linalg.transpose op into:
1. A function entry `alloca` operation to allocate a ViewDescriptor.
2. A load of the ViewDescriptor from the pointer allocated in 1.
3. Updates to the ViewDescriptor to introduce the data ptr, offset, size
and stride. Size and stride are permutations of the original values.
4. A store of the resulting ViewDescriptor to the alloca'ed pointer.
The linalg.transpose op is replaced by the alloca'ed pointer.
PiperOrigin-RevId:
265169112
Nicolas Vasilache [Fri, 23 Aug 2019 21:47:46 +0000 (14:47 -0700)]
Add a linalg.transpose op
A linalg.transpose op is a pure metadata operation that takes a view + permutation map and produces
another view of the same underlying data, with a different reindexing. This is a
pure metadata operation that does not touch the underlying data.
Example:
```
%t = linalg.transpose %v (i, j) -> (j, i) : !linalg.view<?x?xf32>
```
PiperOrigin-RevId:
265139429
River Riddle [Fri, 23 Aug 2019 18:28:19 +0000 (11:28 -0700)]
NFC: Add a note to 'applyPatternsGreedily' that it also performs folding/dce.
Fixes tensorflow/mlir#72
PiperOrigin-RevId:
265097597
Nicolas Vasilache [Fri, 23 Aug 2019 18:08:59 +0000 (11:08 -0700)]
Add lowering of linalg.copy to an external C++ library and a test.
This CL extends support for lowering of linalg to external C++ libraries with CopyOp. Currently this can only work when the permutation maps in the copies are identity. Future support for permutations will be added later.
PiperOrigin-RevId:
265093025
Nicolas Vasilache [Fri, 23 Aug 2019 18:08:33 +0000 (11:08 -0700)]
Update Linalg slice and subview documentation - NFC
PiperOrigin-RevId:
265092922
Lei Zhang [Fri, 23 Aug 2019 18:07:13 +0000 (11:07 -0700)]
[spirv] NFC: move SPIR-V control flow ops to a separate file
This CL is also purely moving code around for better file organization.
PiperOrigin-RevId:
265092566
Chris Lattner [Fri, 23 Aug 2019 17:35:24 +0000 (10:35 -0700)]
Introduce the ability for "isolated from above" ops to introduce shadowing
names for the basic block arguments in their body.
PiperOrigin-RevId:
265084627
MLIR Team [Fri, 23 Aug 2019 17:34:04 +0000 (10:34 -0700)]
NFC: Update in-code documentation. Make the two grammar definitions of static-dimension-list consistent.
PiperOrigin-RevId:
265084348
Lei Zhang [Fri, 23 Aug 2019 17:26:13 +0000 (10:26 -0700)]
[spirv] NFC: move arithmetic and logical ops to separate files
This is purely moving code around for better file organization.
PiperOrigin-RevId:
265082517
Nicolas Vasilache [Fri, 23 Aug 2019 17:15:29 +0000 (10:15 -0700)]
Fix BufferAllocOp builder.
One of the BufferAllocOp builders was improperly specified which triggered infinite recursion. This CL fixes it.
PiperOrigin-RevId:
265080371
River Riddle [Fri, 23 Aug 2019 17:08:42 +0000 (10:08 -0700)]
NFC: Move the operation, region, and block sections to after the dialect section.
Operations/Regions/Blocks represent the core IR building blocks and should be introduced before types and attributes.
PiperOrigin-RevId:
265079103
MLIR Team [Fri, 23 Aug 2019 02:05:07 +0000 (19:05 -0700)]
Add I32ElementsAttr to OpBase
PiperOrigin-RevId:
264969142
River Riddle [Fri, 23 Aug 2019 01:58:51 +0000 (18:58 -0700)]
Add iterator support to ElementsAttr and SparseElementsAttr.
This will allow iterating the values of a non-opaque ElementsAttr, with all of the types currently supported by DenseElementsAttr. This should help reduce the amount of specialization on DenseElementsAttr.
PiperOrigin-RevId:
264968151
River Riddle [Fri, 23 Aug 2019 00:51:06 +0000 (17:51 -0700)]
NFC: Cleanup the Attribute section in the LangRef.
* Add a section on dialect attribute values and attribute aliases
* Move FloatAttr into its alphabetically correct place
* Add a "Standard Attribute Values" section
PiperOrigin-RevId:
264959306
River Riddle [Thu, 22 Aug 2019 23:43:06 +0000 (16:43 -0700)]
NFC: Cleanup the type system section of the LangRef.
* Alphabetize the type definitions
* Make 'Dialect specific types' a type-system subsection
* Merge Builtin types and Standard types
PiperOrigin-RevId:
264947721
Lei Zhang [Thu, 22 Aug 2019 23:01:13 +0000 (16:01 -0700)]
[spirv] Add support for extension (de)serialization
Only a few important KHR extensions are registered to the
SPIR-V dialect for now.
PiperOrigin-RevId:
264939428
River Riddle [Thu, 22 Aug 2019 22:53:41 +0000 (15:53 -0700)]
NFC: Rework and cleanup the High-Level structure and Dialect sections.
Both sections are out-of-date and need to be updated. The dialect section is particularly bad in that it never actually mentions what a 'Dialect' is.
PiperOrigin-RevId:
264937905
River Riddle [Thu, 22 Aug 2019 20:20:28 +0000 (13:20 -0700)]
NFC: Remove mentions of the TensorFlow dialect from the langref.
PiperOrigin-RevId:
264904489