Commit Graph

4054 Commits

Author SHA1 Message Date
Stephan Herhut ac9d742bbe [MLIR][LLVM] Make index type bitwidth configurable.
This change adds a new option to the StandardToLLVM lowering to configure
the bitwidth of the index type independently of the target architecture's
pointer size.

Differential revision: https://reviews.llvm.org/D76353
2020-03-27 12:42:54 +01:00
Denis Khalikov 8f4ab8c7d7 [mlir][vulkan-runner] Add support for 2D memref.
Summary:
This patch adds support for 2D memref in mlir-vulkan-runner.

Differential Revision: https://reviews.llvm.org/D76737
2020-03-27 13:59:17 +03:00
Alex Zinenko c16c07d4b9 [mlir] StandardToLLVM: use template aliases instead of dummy classes
Multiple operation conversions from the Standard dialect to the LLVM dialect
are trivial one-to-one conversions that use only the pattern defined in base
utility classes such as OneToOneConvertToLLVMPattern and
VectorConvertToLLVMPattern. Use template aliases ("using" declarations) instead
of creating derived classes without new functionality.
2020-03-27 11:14:44 +01:00
Uday Bondhugula ad4b4acbb0 [MLIR][NFC] drop some unnecessary includes
Drop unnecessary includes

Differential Revision: https://reviews.llvm.org/D76898
2020-03-27 09:17:27 +05:30
Marius Brehler 6946ca4b4c [mlir] Rename CMake target MLIRQuantOps to MLIRQuant
With commit 4d60f47 VectorOps was renamed to Vector and the naming of
the CMake target was adjusted. With commit 363dd3f QuantOps was
renamed to Quant, but the naming of the CMake target is left
untouched. This renames the CMake target.
2020-03-26 11:03:29 -07:00
Sean Silva 3dceb6d246 Allow IndexType inside tensors.
It's common in many dialects to use tensors to themselves hold tensor shapes (for example, the shape is itself the result of some non-trivial calculation). Currently, such dialects have to use `tensor<?xi64>` or worse (like allowing either i32 or i64 tensors to represent shapes). `tensor<?xindex>` is the natural type to represent this, but is currently disallowed. This patch allows it.

Differential Revision: https://reviews.llvm.org/D76726
2020-03-26 10:52:48 -07:00
Alex Zinenko 04ed07bc17 [mlir] StandardToLLVM: clean up conversion patterns for vector operations
Summary:
Provide a public VectorConvertToLLVMPattern utility class to implement
conversions with automatic unrolling of operation on multidimensional vectors
to lists of operations on single-dimensional vectors when lowering to the LLVM
dialect. Drop the template-based check on the number of operands since the
actual implementation does not depend on the operand number anymore. This check
only creates spurious concepts (UnaryOpLowering, BinaryOpLowering, etc).

Differential Revision: https://reviews.llvm.org/D76865
2020-03-26 18:24:10 +01:00
Alex Zinenko 987fbae0ad [mlir] StandardToLLVM: make one-to-one convresion pattern publicly available
Summary:
The Standard-to-LLVM dialect convresion has a set of utility classes that
simplify conversions, including patterns that provide one-to-one conversion
operation conversion with optional result packing. Expose these classes in a
public header so that conversions other than Standard-to-LLVM (e.g. vectors, or
LLVM-based intrinsics) could also use them. Since the patterns are implemented
as class templates and in order to keep the code size limited, keep the
implementation private by resorting to op identifiers instead of template-based
builders.

Differential Revision: https://reviews.llvm.org/D76864
2020-03-26 18:24:07 +01:00
Tres Popp 7af74ee89a [MLIR] Delete extra declaration of createAffineDataCopyGenerationPass.
This was caused by a bad rebase for
27c201aa1d
2020-03-26 09:55:47 +01:00
Tres Popp 27c201aa1d [MLIR] Add parallel loop collapsing.
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
2020-03-26 09:32:52 +01:00
Uday Bondhugula 92744f6247 [MLIR] Add flat affine constraints method to round trip integer set
- add method to get back an integer set from flat affine constraints;
  this allows a round trip
- use this to complete the simplification of integer sets in
  -simplify-affine-structures
- update FlatAffineConstraints::removeTrivialRedundancy to also do GCD
  tightening and normalize by GCD (while still keeping it linear time).

Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
2020-03-26 12:07:13 +05:30
Lei Zhang 2679d8dc7e [mlir][vulkan-runner] Add test to time a large vector add
Summary:
The test performs add on vector<16384xf32> with
number of workgroups = (128, 1, 1)
local workgroup size = (128, 1, 1)

On a NVIDIA Quadro P1000, I see the following results:

Command buffer submit time: 13us
Compute shader execution time: 19.616us

Differential Revision: https://reviews.llvm.org/D76799
2020-03-25 19:02:29 -04:00
Alex Zinenko ec74867c5e [mlir] Provide CustomOpAsmParser::parseOptionalOperand
Summary:
Some operations have custom syntax where an operand is always followed by a
specific token of streams if the operand is present. Parsing such operations
requires the ability to optionally parse an operand. Provide a relevant
function in the custom Op parser.

Differential Revision: https://reviews.llvm.org/D76779
2020-03-25 21:03:11 +01:00
River Riddle 8e83d5ea3e [mlir] Remove old VectorOps directory
This was accidentally re-added during a rebase.
2020-03-25 12:21:57 -07:00
Frej Drejhammar d8981ce5b9 [mlir][Parser] Fix attribute parser errors for ui64
Summary:
The attribute parser fails to correctly parse unsigned 64 bit
attributes as the check `isNegative ? (int64_t)-val.getValue() >= 0
: (int64_t)val.getValue() < 0` will falsely detect an overflow for
unsigned values larger than 2^63-1.

This patch reworks the overflow logic to instead of doing arithmetic
on int64_t use APInt::isSignBitSet() and knowledge of the attribute
type.

Test-cases which verify the de-facto behavior of the parser and
triggered the previous faulty handing of unsigned 64 bit attrbutes are
also added.

Differential Revision: https://reviews.llvm.org/D76493
2020-03-25 11:57:16 -07:00
Marcel Koester 2b529a396d [mlir] Removed TanHOp lowering from ConvertStandardToLLVM since there is no reasonable TanH representation in LLVM.
Summary: The current ConvertStandardToLLVM phase lowers the standard TanHOp to function calls to external tanh symbols. However, this leads to misunderstandings since these external symbols are not defined anywhere. This commit removes the TanHOp lowering functionality from ConvertStandardToLLVM, adapts the LowerGpuOpsToNVVMOps and LowerGpuOpsToROCDLOps passes and adjusts the affected test cases.

Reviewers: mravishankar, herhut

Subscribers: jholewinski, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, csigg, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, Joonsoo, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D75509
2020-03-25 16:43:45 +01:00
Uday Bondhugula 8786cdb3cd [MLIR][NFC] std::is_same || -> llvm::is_one_of
Switch std::is_same disjunctions to llvm::is_one_of

Differential Revision: https://reviews.llvm.org/D76745
2020-03-25 09:09:37 +05:30
MaheshRavishankar 46bb6613a3 [mlir][GPU] Use StructAttr to drive lowering from loop.parallel to
gpu.launch

Current implementation of lowering from loop.parallel to gpu.launch
uses a DictionaryAttr to specify the mapping. Moving this attribute to
be auto-generated from specification as a StructAttr. This simplifies
a lot the logic of looking up and creating this attribute.

Differential Revision: https://reviews.llvm.org/D76165
2020-03-24 16:16:55 -07:00
Jacques Pienaar 57ce79f74d [mlir] Clarify constraint on derived attribute
Summary:
The restriction that a derived attribute should represent an
attribute/be materializable as an attribute was not made clear.

Differential Revision: https://reviews.llvm.org/D76715
2020-03-24 13:00:48 -07:00
River Riddle 1a083f027f [mlir] Revamp operation documentation generation
Summary:
This revisions performs several cleanups to the generated dialect documentation:
* Standardizes format of attributes/operands/results sections
* Splits out operation/type/dialect documentation generation to allow for composing generated and hand-written documentation
* Add section for declarative assembly syntax and successors
* General cleanup

Differential Revision: https://reviews.llvm.org/D76573
2020-03-24 12:05:18 -07:00
Hanhan Wang 58cdb8bff0 [mlir][StandardToSPIRV] Add support for lowering unary ops
Differential Revision: https://reviews.llvm.org/D76661
2020-03-24 09:16:10 -04:00
Benjamin Kramer b6732056a4 Make helpers static. NFC. 2020-03-24 13:43:00 +01:00
Uday Bondhugula bec785ab70 [MLIR][NFC] flat affine constraints - refactor to share, renames
- refactor to remove duplicate code
- some renaming / comment updates for readability

Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>

Differential Revision: https://reviews.llvm.org/D76667
2020-03-24 10:57:42 +05:30
Uday Bondhugula 98fa615002 [MLIR] move loopUnrollJamBy*Factor to loop transforms utils
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
2020-03-24 08:08:57 +05:30
Uday Bondhugula 78e61496bc [MLIR][NFC] loop tiling - improve comments / naming
Improve comments, naming, and other cleanup

Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>

Differential Revision: https://reviews.llvm.org/D76616
2020-03-24 07:37:19 +05:30
aartbik 8d46bfa808 [mlir] [VectorOps] A "reference" lowering of vector.transpose to LLVM IR
Summary: Makes the vector.tranpose runnable on CPU.

Reviewers: nicolasvasilache, andydavis1, rriddle

Reviewed By: nicolasvasilache

Subscribers: mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, liufengdb, Joonsoo, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76644
2020-03-23 19:01:38 -07:00
Chris Lattner 4a219bf7ff Fix a bug in the .mlir lexer, where a \0 character in a file is treated as a colon (due to an accidental fall through) instead of whitespace.
Summary:
While here, simplify the lexer a bit by eliminating the unneeded 'operator'
classification of certain sigils, they can just be treated as 'punctuation'.

Reviewers: rriddle!

Subscribers: mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, liufengdb, Joonsoo, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76647
2020-03-23 17:35:17 -07:00
Stephen Neuendorffer de0758e5bd [MLIR] Fixes for BUILD_SHARED_LIBS=on 2020-03-23 15:21:44 -07:00
Alexander Belyaev 564ece93b8 [MLIR] Insert loop.yield to IfOp regions only if it's void.
Differential Revision: https://reviews.llvm.org/D76603
2020-03-23 23:21:10 +01:00
MaheshRavishankar 04f2b717d2 [mlir] Fix unsafe create operation in GreedyPatternRewriter
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
2020-03-23 11:50:40 -07:00
Chris Lattner 42d8f48ccf Fix a warning building on my machine, NFC. warning: unused function 'compilePtxToCubinForTesting'
Summary: Also eliminate the redunant anon namespace around the already static function.

Reviewers: herhut

Subscribers: hiraditya, steven_wu, dexonsmith, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, csigg, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, Joonsoo, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76627
2020-03-23 11:16:55 -07:00
Chris Lattner 596da62d21 Add support for custom op parser/printer hooks to know about result names.
Summary:
This allows the custom parser/printer hooks to do interesting things with
the SSA names.  This patch:

 - Adds a new 'getResultName' method to OpAsmParser that allows a parser
   implementation to get information about its result names, along with
   a getNumResults() method that allows op parser impls to know how many
   results are expected.
 - Adds a OpAsmPrinter::printOperand overload that takes an explicit stream.
 - Adds a test.string_attr_pretty_name operation that uses these hooks to
   do fancy things with the result name.

Reviewers: rriddle!

Subscribers: mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, liufengdb, Joonsoo, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76205
2020-03-23 08:58:05 -07:00
Christian Sigg b43ae21e60 Fix all-reduce int tests by host-registering memrefs.
Reduce amount of boiler plate to register host memory.

Summary: Fix all-reduce int tests by host-registering memrefs.

Reviewers: herhut

Reviewed By: herhut

Subscribers: clementval, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, liufengdb, Joonsoo, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76563
2020-03-23 11:48:13 +01:00
Uday Bondhugula b873761496 [MLIR][NFC] Move some of the affine transforms / tests to dialect dirs
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
2020-03-23 08:25:07 +05:30
Uday Bondhugula 56e1c20bfd [MLIR][NFC] rename ConvertStandardToLLVM, ConvertLoopToStandard to drop Convert prefix
This is in line with the convention agreed on https://llvm.discourse.group/t/rfc-canonical-file-paths-to-dialects/621

Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>

Differential Revision: https://reviews.llvm.org/D76583
2020-03-23 08:24:11 +05:30
Jacques Pienaar bb621cac3d [mlir] Change include image to be toplevel
This will match the changes mlir.llvm.org side.
2020-03-22 13:13:17 -07:00
River Riddle e8f5c072f6 [mlir] Move the testing pass for GpuKernelToCubin to the test/ directory
Summary:
This removes the static pass registration, and also cleans up some lingering technical debt.

Differential Revision: https://reviews.llvm.org/D76554
2020-03-22 03:38:09 -07:00
River Riddle e74961eee2 [mlir][NFC] Remove Analysis/Passes.h
Summary:
This file only contains references to test passes, and was never removed when the test passes were moved to the test/ directory.

Differential Revision: https://reviews.llvm.org/D76553
2020-03-22 03:16:51 -07:00
River Riddle e9482ed194 [mlir] Move several static cl::opts to be pass options instead.
This removes the reliance on global options, and also simplifies the pass registration.

Differential Revision: https://reviews.llvm.org/D76552
2020-03-22 03:16:21 -07:00
Uday Bondhugula d477df59cf [MLIR][NFC] fix memref type doc comment on dynamic shape
Fix memref type doc comment to state that -1 indicates a dynamically
shaped dimension and not any negative number.

Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>

Differential Revision: https://reviews.llvm.org/D76557
2020-03-22 06:08:38 +05:30
Baden Hughes 49ccb32fd4 Update ConversionToLLVMDialect.md
Minor editorial/typographic fixes
2020-03-21 13:04:44 +01:00
nmostafa 141e5890d8 [MLIR] Add an IfOp builder with results
Summary:
Add an additional builder to IfOp to allow the operation to
define operands.

Differential Revision: https://reviews.llvm.org/D76524
2020-03-20 16:53:56 -07:00
Aaron Smith aa1e0e01d8 [MLIR] Fix Xcode build due to incorrect library path
Two MLIR examples do not link because the library path is different when using Xcode vs Makefiles.
This change adds the configuration name to the library path when building with Xcode.

i.e. LLVM_BUILD_DIR/debug/lib
2020-03-20 16:38:16 -07:00
Nicolas Vasilache 6aef702ab6 [mlir][AVX512] Hotfix - Add cmake dependence on MLIRSideEffects 2020-03-20 19:35:08 -04:00
aartbik 479ee11061 [mlir] [VectorOps] Introduce vector.transpose
Summary: Introduced in order to introduce specialized lowering passes that implement transposition operations efficiently.

Reviewers: nicolasvasilache, andydavis1

Reviewed By: nicolasvasilache

Subscribers: mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, liufengdb, Joonsoo, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76460
2020-03-20 15:47:44 -07:00
Rob Suderman e708471395 [mlir][NFC] Cleanup AffineOps directory structure
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
2020-03-20 14:23:43 -07:00
Nicolas Vasilache 40fc80a023 [mlir][AVX512] Hotfix - Fix CMake Doc generation dependence 2020-03-20 16:32:18 -04:00
Ahmed Taei 08a9147349 [mlir][LLVMIR] Fix fusion for rank-0 tensors
Summary: This diff fixes fusion craching for ops with rank-0 tensors

Reviewers: mravishankar, nicolasvasilache, rriddle!

Subscribers: mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, arpith-jacob, mgester, lucyrfox, liufengdb, Joonsoo, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76479
2020-03-20 13:17:19 -07:00
Hanhan Wang be4e9db579 [mlir][Linalg] NFC: Clean up for 0-D abstraction.
Summary:
After D75831 has been landed, both the generic op and indexed_generic op can
handle 0-D edge case. In the previous patch, only generic op has been updated.
This patch updates the lowering to loops for indexed_generic op. Since they are
almost the sanme, the patch also refactors the common part.

Differential Revision: https://reviews.llvm.org/D76413
2020-03-20 13:07:14 -07:00
Nicolas Vasilache 462db62053 [mlir][AVX512] Start a primitive AVX512 dialect
The Vector Dialect [document](https://mlir.llvm.org/docs/Dialects/Vector/) discusses the vector abstractions that MLIR supports and the various tradeoffs involved.

One of the layer that is missing in OSS atm is the Hardware Vector Ops (HWV) level.

This revision proposes an AVX512-specific to add a new Dialect/Targets/AVX512 Dialect that would directly target AVX512-specific intrinsics.

Atm, we rely too much on LLVM’s peephole optimizer to do a good job from small insertelement/extractelement/shufflevector. In the future, when possible, generic abstractions such as VP intrinsics should be preferred.

The revision will allow trading off HW-specific vs generic abstractions in MLIR.

Differential Revision: https://reviews.llvm.org/D75987
2020-03-20 14:11:57 -04:00