March 2020 Archives by author

• Messages sorted by: [ thread ] [ subject ] [ date ]
• More info on this list...

Starting: Mon Mar 2 01:24:11 PST 2020
Ending: Tue Mar 31 21:34:52 PDT 2020
Messages: 263

• [Mlir-commits] [mlir] 8c70c42 - Fix MLIR clang-tidy: when tweaking it does not inherit from the parent   Mehdi Amini
• [Mlir-commits] [mlir] 82e9160 - [MLIR][Affine] NFC: add convenience method for affine data copy for a loop body   Mehdi Amini
• [Mlir-commits] [mlir] 5e080df - [MLIR] NFC: modernize affine loop fusion test cases   Mehdi Amini
• [Mlir-commits] [mlir] f80c6d8 - Fix MLIR build when NVPTX backend is not configured in   Mehdi Amini
• [Mlir-commits] [mlir] 90dbec2 - Fix MLIR build after header change in LLVM (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 49d4e0e - Remove CMake configuration for Sphinx targets in MLIR   Mehdi Amini
• [Mlir-commits] [mlir] 103678d - [mlir] Fix cross compiling MLIR   Mehdi Amini
• [Mlir-commits] [mlir] c94cfe6 - [MLIR] fix parse bound error message   Mehdi Amini
• [Mlir-commits] [mlir] 9dd92a5 - Remove spurious duplicated header include (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] bab5bcf - Add a flag on the context to protect against creation of operations in unregistered dialects   Mehdi Amini
• [Mlir-commits] [mlir] 111c932 - Fix test: add `-allow-unregistered-dialect` to Affine/loop-permute.mlir test (missed during rebase)   Mehdi Amini
• [Mlir-commits] [mlir] 0145a26 - [MLIR] Add explicit initial values for loop.parallel op.   Alexander Belyaev
• [Mlir-commits] [mlir] e0ce852 - [MLIR] Expose makeCanonicalStridedLayoutExpr in StandardTypes.h.   Alexander Belyaev
• [Mlir-commits] [mlir] ffcb492 - [MLIR] Add a comment to `requiredOperandCount` arg in LoopOps.cpp.   Alexander Belyaev
• [Mlir-commits] [mlir] 3147342 - [MLIR] Change custom printer/parser for loop.parallel and loop.reduce.   Alexander Belyaev
• [Mlir-commits] [mlir] c0735b2 - [MLIR] Update documentation for loop.reduce.   Alexander Belyaev
• [Mlir-commits] [mlir] 9f5d9bf - [MLIR] Reformat LoopOps.td documentation.   Alexander Belyaev
• [Mlir-commits] [mlir] 564ece9 - [MLIR] Insert loop.yield to IfOp regions only if it's void.   Alexander Belyaev
• [Mlir-commits] [mlir] d811aee - [MLIR][NFC] update/clean up affine PDT, related utils, its test case   Uday Bondhugula
• [Mlir-commits] [mlir] 332f0b3 - Affine expr simplification for add of const multiple of same expression   Uday Bondhugula
• [Mlir-commits] [mlir] 6e0aaaf - [MLIR][NFC] fix RankedTensorType doc comment   Uday Bondhugula
• [Mlir-commits] [mlir] 0ddd043 - [MLIR] Fix op folding to not run pre-replace when not constant folding   Uday Bondhugula
• [Mlir-commits] [mlir] d477df5 - [MLIR][NFC] fix memref type doc comment on dynamic shape   Uday Bondhugula
• [Mlir-commits] [mlir] 56e1c20 - [MLIR][NFC] rename ConvertStandardToLLVM, ConvertLoopToStandard to drop Convert prefix   Uday Bondhugula
• [Mlir-commits] [mlir] b873761 - [MLIR][NFC] Move some of the affine transforms / tests to dialect dirs   Uday Bondhugula
• [Mlir-commits] [mlir] 78e6149 - [MLIR][NFC] loop tiling - improve comments / naming   Uday Bondhugula
• [Mlir-commits] [mlir] 98fa615 - [MLIR] move loopUnrollJamBy*Factor to loop transforms utils   Uday Bondhugula
• [Mlir-commits] [mlir] bec785a - [MLIR][NFC] flat affine constraints - refactor to share, renames   Uday Bondhugula
• [Mlir-commits] [mlir] 8786cdb - [MLIR][NFC] std::is_same || -> llvm::is_one_of   Uday Bondhugula
• [Mlir-commits] [mlir] 92744f6 - [MLIR] Add flat affine constraints method to round trip integer set   Uday Bondhugula
• [Mlir-commits] [mlir] ad4b4ac - [MLIR][NFC] drop some unnecessary includes   Uday Bondhugula
• [Mlir-commits] [mlir] 43a95a5 - [MLIR] Introduce full/partial tile separation using if/else   Uday Bondhugula
• [Mlir-commits] [mlir] fec6c5a - [MLIR][NFC] Move TestDialect -> Dialect/Test   Uday Bondhugula
• [Mlir-commits] [mlir] 4e4ea2c - [MLIR] Add missing asserts in interchangeLoops util, doc comment update   Uday Bondhugula
• [Mlir-commits] [mlir] f273e5c - [MLIR] Fix permuteLoops utility   Uday Bondhugula
• [Mlir-commits] [mlir] 7fca0e9 - [MLIR] Add simple runner utilities for timing   Uday Bondhugula
• [Mlir-commits] [mlir] 5f9bf3f - [MLIR][NFC] Move test/Transforms/lower-affine.mlir -> test/Conversion   Uday Bondhugula
• [Mlir-commits] [mlir] e1fb9d5 - [MLIR][NFC] modernize affine.for unroll test pass   Uday Bondhugula
• [Mlir-commits] [mlir] 92a295e - [MLIR, OpenMP] Translation of OpenMP barrier construct to LLVM IR   Kiran Chandramohan
• [Mlir-commits] [mlir] e459596 - Temporarily Revert "[mlir] Add padding to 1-D Vector in CRunnerUtils.h"   Eric Christopher
• [Mlir-commits] [mlir] 57397eb - Revert "[mlir] Add padding to 1-D Vector in CRunnerUtils.h"   Eric Christopher
• [Mlir-commits] [mlir] 31a346c - [MLIR][Vector] Add support for TupleGetOp folding through InsertSlicesOp and ExtractSlicesOp.   Andy Davis
• [Mlir-commits] [mlir] 6677815 - [mlir] On Windows, silence warning on functions definition   Alexandre Ganea
• [Mlir-commits] [mlir] 855e738 - [VectorOps] Implement a simple folder for identity vector.transpose operations.   Alex Grosul
• [Mlir-commits] [mlir] 56ac9d3 - [MLIR] Add includes to PointerLikeTypeTraits where needed.   Stephan Herhut
• [Mlir-commits] [mlir] d17428d - [MLIR][GPU] fix loop trip count computation in LoopsToGPU   Stephan Herhut
• [Mlir-commits] [mlir] 57b8b2c - Revert "[mlir][ods] Add query for derived attribute"   Stephan Herhut
• [Mlir-commits] [mlir] 10ec186 - [MLIR][GPU] Add error checking to loop.parallel to gpu transform.   Stephan Herhut
• [Mlir-commits] [mlir] 2eff566 - [MLIR] Add `and`, `or`, `xor`, `min`, `max` too gpu.all_reduce and the nvvm lowering   Stephan Herhut
• [Mlir-commits] [mlir] f6790a1 - Revert "[MLIR] Add `and`, `or`, `xor`, `min`, `max` too gpu.all_reduce and the nvvm lowering"   Stephan Herhut
• [Mlir-commits] [mlir] c738099 - [MLIR] Add `and`, `or`, `xor`, `min`, `max` too gpu.all_reduce and the nvvm lowering   Stephan Herhut
• [Mlir-commits] [mlir] d4d62fc - [MLIR] Add test for multiple gpu.all_reduce in the same kernel when lowering to NVVM   Stephan Herhut
• [Mlir-commits] [mlir] ac9d742 - [MLIR][LLVM] Make index type bitwidth configurable.   Stephan Herhut
• [Mlir-commits] [mlir] a8901a0 - [mlir] NFC: Fix trivial typos in documents   Kazuaki Ishizaki
• [Mlir-commits] [mlir] e5a8512 - [mlir] NFC: fix trivial typo in source files   Kazuaki Ishizaki
• [Mlir-commits] [mlir] b632bd8 - [mlir] NFC: fix trivial typo in documents   Kazuaki Ishizaki
• [Mlir-commits] [mlir] 8f4ab8c - [mlir][vulkan-runner] Add support for 2D memref.   Denis Khalikov
• [Mlir-commits] [mlir] 2b529a3 - [mlir] Removed TanHOp lowering from ConvertStandardToLLVM since there is no reasonable TanH representation in LLVM.   Marcel Koester
• [Mlir-commits] [mlir] 86bbbb3 - [mlir] Extended Dominance analysis with a function to find the nearest common dominator of two given blocks.   Marcel Koester
• [Mlir-commits] [mlir] 2773c69 - Fix pessimizing move. NFC.   Benjamin Kramer
• [Mlir-commits] [mlir] 247a177 - Give helpers internal linkage. NFC.   Benjamin Kramer
• [Mlir-commits] [mlir] b673205 - Make helpers static. NFC.   Benjamin Kramer
• [Mlir-commits] [mlir] 91acb5b - Add rsqrt op to Standard dialect and lower it to LLVM dialect.   Adrian Kuegel
• [Mlir-commits] [mlir] 86306df - Extract common code to deal with multidimensional vectors.   Adrian Kuegel
• [Mlir-commits] [mlir] c2b2472 - Fix a warning about an unreachable default in a switch statement.   Chris Lattner
• [Mlir-commits] [mlir] 89ecd8c - Teach the MLIR AsmPrinter to correctly escape asm names that use invalid characters.   Chris Lattner
• [Mlir-commits] [mlir] e0a93ce - incorporate feedback from River.   Chris Lattner
• [Mlir-commits] [mlir] 596da62 - Add support for custom op parser/printer hooks to know about result names.   Chris Lattner
• [Mlir-commits] [mlir] 42d8f48 - Fix a warning building on my machine, NFC. warning: unused function 'compilePtxToCubinForTesting'   Chris Lattner
• [Mlir-commits] [mlir] 4a219bf - 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.   Chris Lattner
• [Mlir-commits] [mlir] 216ef5b - [MLIR][NFC] Fix for VS2017 bug.   Frank Laub
• [Mlir-commits] [mlir] c4119a5 - [MLIR][Affine][NFC] Remove obsolete and ambiguous definitions   Frank Laub
• [Mlir-commits] [mlir] cdc5cba - [MLIR][Affine][NFC] Expose expandAffineMap   Frank Laub
• [Mlir-commits] [mlir] 0af6d27 - Add /bigobj for SPIRV dialect on MSVC.   Stella Laurenzo
• [Mlir-commits] [mlir] 166f83f - [QuantOps] Add the quant region definition   Feng Liu
• [Mlir-commits] [mlir] 942afe0 - [mlir/quant] fix a small typo in the quant utility   Feng Liu
• [Mlir-commits] [mlir] b58f6bb - Add a test for UsedDeclVisitor   Yaxun Liu
• [Mlir-commits] [mlir] f528df8 - Revert "Add a test for UsedDeclVisitor"   Yaxun Liu
• [Mlir-commits] [mlir] 1c82dd3 - [MLIR] Ensure that target_link_libraries() always has a keyword.   Stephen Neuendorffer
• [Mlir-commits] [mlir] 2488016 - [MLIR] Remove redundant library dependencies   Stephen Neuendorffer
• [Mlir-commits] [mlir] 4594d0e - [MLIR] Move from add_dependencies() to DEPENDS   Stephen Neuendorffer
• [Mlir-commits] [mlir] 7c64f6b - [MLIR] Add support for libMLIR.so   Stephen Neuendorffer
• [Mlir-commits] [mlir] 9f979d7 - [MLIR] Fixes for BUILD_SHARED_LIBS=on   Stephen Neuendorffer
• [Mlir-commits] [mlir] 7264cf4 - [MLIR] Add missing DEPENDS line for MLIRSPIRV   Stephen Neuendorffer
• [Mlir-commits] [mlir] d774fbc - [MLIR] Add document about creating a dialect.   Stephen Neuendorffer
• [Mlir-commits] [mlir] dc120ba - [MLIR] Do not link mlir-cpu-runner with X86 libs   Stephen Neuendorffer
• [Mlir-commits] [mlir] accede5 - [MLIR] Link MLIRMlirOptMain with the same libraries as mlir-opt   Stephen Neuendorffer
• [Mlir-commits] [mlir] 7ca473a - [MLIR] Add support for out of tree external projects using MLIR   Stephen Neuendorffer
• [Mlir-commits] [mlir] 6bc775a - [MLIR] Interfaces need to used add_mlir_library   Stephen Neuendorffer
• [Mlir-commits] [mlir] f7d4bd8 - [MLIR] Fix for out-of-tree builds from install area.   Stephen Neuendorffer
• [Mlir-commits] [mlir] de0758e - [MLIR] Fixes for BUILD_SHARED_LIBS=on   Stephen Neuendorffer
• [Mlir-commits] [mlir] 6946ca4 - [mlir] Rename CMake target MLIRQuantOps to MLIRQuant   Stephen Neuendorffer
• [Mlir-commits] [mlir] 5aa57c2 - [mlir][ods] Add query for derived attribute   Jacques Pienaar
• [Mlir-commits] [mlir] 1bedb23 - [mlir][ods] Add query for derived attribute   Jacques Pienaar
• [Mlir-commits] [mlir] 36e018b - [mlir] Add derived attribute op interface   Jacques Pienaar
• [Mlir-commits] [mlir] 69ce2fd - [mlir] Remove unused generator   Jacques Pienaar
• [Mlir-commits] [mlir] b2bb8b6 - [mlir] Automatically add DerivedAttribute op interface   Jacques Pienaar
• [Mlir-commits] [mlir] 9a65d68 - [mlir] Add target for Shape dialect   Jacques Pienaar
• [Mlir-commits] [mlir] bb621ca - [mlir] Change include image to be toplevel   Jacques Pienaar
• [Mlir-commits] [mlir] 57ce79f - [mlir] Clarify constraint on derived attribute   Jacques Pienaar
• [Mlir-commits] [mlir] 27c201a - [MLIR] Add parallel loop collapsing.   Tres Popp
• [Mlir-commits] [mlir] 7af74ee - [MLIR] Delete extra declaration of createAffineDataCopyGenerationPass.   Tres Popp
• [Mlir-commits] [mlir] de5a81b - [mlir] Update several usages of IntegerType to properly handled unsignedness.   River Riddle
• [Mlir-commits] [mlir] 7a25bd1 - [mlir][DialectConversion] Abort early if a subregion has a disconnected CFG.   River Riddle
• [Mlir-commits] [mlir] c108966 - [mlir] Generate CmpFPredicate as an EnumAttr in tablegen   River Riddle
• [Mlir-commits] [mlir] cb530ec - [mlir][Tutorial] Make parsing an empty file print a better error.   River Riddle
• [Mlir-commits] [mlir] d09d0bd - [mlir][NFC] Sort the operations alphabetically and add header blocks   River Riddle
• [Mlir-commits] [mlir] c0fd5e6 - [mlir] Add traits for verifying the number of successors and providing relevant accessors.   River Riddle
• [Mlir-commits] [mlir] 621d7cc - [mlir] Add a new BranchOpInterface to allow for opaquely interfacing with branching terminator operations.   River Riddle
• [Mlir-commits] [mlir] 01f7431 - [mlir][DeclarativeParser] Add support for formatting operations with AttrSizedOperandSegments.   River Riddle
• [Mlir-commits] [mlir] 988249a - [mlir] Refactor a few users to no longer rely on the successor operand API of Operation.   River Riddle
• [Mlir-commits] [mlir] c98cff5 - [mlir] Automatically populate `operand_segment_sizes` in the auto-generated build methods.   River Riddle
• [Mlir-commits] [mlir] cb17771 - [mlir] Remove successor operands from the Operation class   River Riddle
• [Mlir-commits] [mlir] f892358 - [mlir][SideEffects] Define a set of interfaces and traits for defining side effects   River Riddle
• [Mlir-commits] [mlir] 20dca52 - [mlir][SideEffects] Enable specifying side effects directly on the arguments/results of an operation.   River Riddle
• [Mlir-commits] [mlir] f240d30 - [mlir] Explicitly qualify Effect to avoid MSVC build failure   River Riddle
• [Mlir-commits] [mlir] 91153e0 - [mlir][NFC] remove stray decl of toAffineExpr, rename for readability   River Riddle
• [Mlir-commits] [mlir] c310840 - [mlir][nfc] Fix building mlir_c_runner_utils for Windows   River Riddle
• [Mlir-commits] [mlir] 320f0b0 - [mlir] Change EffectKind in unsigned for bitfield to avoid miscompile in   River Riddle
• [Mlir-commits] [mlir] b10c662 - [mlir][SideEffects] Replace the old SideEffects dialect interface with the newly added op interfaces/traits.   River Riddle
• [Mlir-commits] [mlir] 936fc55 - [MLIR] Add custom option parser type to PassOption   River Riddle
• [Mlir-commits] [mlir] 7ce1e7a - [mlir][NFC] Move the operation interfaces out of Analysis/ and into a new Interfaces/ directory.   River Riddle
• [Mlir-commits] [mlir] 153720a - [mlir][NFC] Move the interfaces and traits for side effects out of IR/ to Interfaces/   River Riddle
• [Mlir-commits] [mlir] d2f3e5f - [mlir] Add support for non-identifier attribute names.   River Riddle
• [Mlir-commits] [mlir] 4977a5f - [mlir][NFC] Use fold expressions instead of variadic class templates for adding operations/etc. to dialects.   River Riddle
• [Mlir-commits] [mlir] d5f5325 - [mlir][SideEffects] Mark the CFG only terminator operations as NoSideEffect   River Riddle
• [Mlir-commits] [mlir] 483f82b - [mlir][SideEffects][NFC] Move the .td definitions for NoSideEffect/RecursiveSideEffect to SideEffects.td   River Riddle
• [Mlir-commits] [mlir] 7c211cf - [mlir][NFC] Move the definition of AffineApplyOp to ODS   River Riddle
• [Mlir-commits] [mlir] 907403f - [mlir] Add a new `ConstantLike` trait to better identify operations that represent a "constant".   River Riddle
• [Mlir-commits] [mlir] 0ddba0b - [mlir][SideEffects] Replace HasNoSideEffect with the memory effect interfaces.   River Riddle
• [Mlir-commits] [mlir] 396a42d - [mlir] Use llvm::ElementCount when constructing an llvm splat vector.   River Riddle
• [Mlir-commits] [mlir] 40f4a9f - [mlir][NFC] Removed unnecessary StandardOp includes   River Riddle
• [Mlir-commits] [mlir] bf0cc6b - [mlir][NFC] modernize / clean up some loop transform utils, affine analysis utils   River Riddle
• [Mlir-commits] [mlir] 43959a2 - [mlir][NFC] Move the LoopLike interface out of Transforms/ and into Interfaces/   River Riddle
• [Mlir-commits] [mlir] 4df44c4 - [mlir] Only treat "Alloc" effects as dead if they are for operation results.   River Riddle
• [Mlir-commits] [mlir] 429d792 - [mlir] Add support for generating dialect declarations via tablegen.   River Riddle
• [Mlir-commits] [mlir] 9b15138 - [mlir][NFC] Add missing include for std::string.   River Riddle
• [Mlir-commits] [mlir] 2d723d4 - [mlir] Avoid the use of auto in templates to fix MSVC build   River Riddle
• [Mlir-commits] [mlir] bd5941b - [mlir] Remove the PatternState class and simplify PatternMatchResult.   River Riddle
• [Mlir-commits] [mlir] 032743e - [mlir] Add support for the attribute verifiers in the dialect declaration generator.   River Riddle
• [Mlir-commits] [mlir] 5267f5e - [mlir] Add a hook to PatternRewriter to allow for patterns to notify why a match failed.   River Riddle
• [Mlir-commits] [mlir] 363dd3f - [mlir][NFC] Rename QuantOps to Quant   River Riddle
• [Mlir-commits] [mlir] 4d60f47 - [mlir][NFC] Renamed VectorOps to Vector   River Riddle
• [Mlir-commits] [mlir] 3145427 - [mlir][NFC] Replace all usages of PatternMatchResult with LogicalResult   River Riddle
• [Mlir-commits] [mlir] bd0ca26 - [mlir] Update DRR patterns to notify the rewriter why a pattern fails to match.   River Riddle
• [Mlir-commits] [mlir] 34d0d6b - [mlir][DialectConversion] Print the operation being legalized if it has no regions   River Riddle
• [Mlir-commits] [mlir] 4be504a - [mlir] Add support for detecting single use callables in the Inliner.   River Riddle
• [Mlir-commits] [mlir] 64a5e57 - [mlir] Disable notifyMatchFailure in NDEBUG   River Riddle
• [Mlir-commits] [mlir] b72e13c - [MLIR] Deduplicate dialect registration by ClassID   River Riddle
• [Mlir-commits] [mlir] cd1212d - [mlir] Introduced CallOp Dialect Conversion   River Riddle
• [Mlir-commits] [mlir] 2c1ba63 - [mlir] Change missed usage PatternMatchResult to LogicalResult   River Riddle
• [Mlir-commits] [mlir] e708471 - [mlir][NFC] Cleanup AffineOps directory structure   River Riddle
• [Mlir-commits] [mlir] e9482ed - [mlir] Move several static cl::opts to be pass options instead.   River Riddle
• [Mlir-commits] [mlir] e74961e - [mlir][NFC] Remove Analysis/Passes.h   River Riddle
• [Mlir-commits] [mlir] e8f5c07 - [mlir] Move the testing pass for GpuKernelToCubin to the test/ directory   River Riddle
• [Mlir-commits] [mlir] 1a083f0 - [mlir] Revamp operation documentation generation   River Riddle
• [Mlir-commits] [mlir] d8981ce - [mlir][Parser] Fix attribute parser errors for ui64   River Riddle
• [Mlir-commits] [mlir] 8e83d5e - [mlir] Remove old VectorOps directory   River Riddle
• [Mlir-commits] [mlir] 3d44f48 - [mlir][Diagnostics] Don't print note source line if it is the same as the previous diagnostic   River Riddle
• [Mlir-commits] [mlir] f86104b - [mlir][NFC] Use the auto-generated op documentation in the standard dialect documentation   River Riddle
• [Mlir-commits] [mlir] 16f27b7 - [mlir][NFC] Update dialect/op documentation to be consistent   River Riddle
• [Mlir-commits] [mlir] 01c857b - [mlir] Update all dialects docs to use 'dialect-namespace' in the header   River Riddle
• [Mlir-commits] [mlir] 7b5d466 - [MLIR] Allow global with an external linkage to include initial value   Eric Schweitz
• [Mlir-commits] [mlir] ced0dd8 - [MLIR] Guard DMA-specific logic with DMA option   Tim Shen
• [Mlir-commits] [mlir] d00f563 - [mlir] Add a simplifying wrapper for generateCopy and expose it.   Tim Shen
• [Mlir-commits] [mlir] fc421d7 - [MLIR] Remove all-reduce lowering from GPU to NVVM. Use in-dialect lowering instead.   Christian Sigg
• [Mlir-commits] [mlir] b43ae21 - Fix all-reduce int tests by host-registering memrefs.   Christian Sigg
• [Mlir-commits] [mlir] 94f848d - Add Builder::getI64VectorAttr.   Sean Silva
• [Mlir-commits] [mlir] c31ee83 - Add Builder::get{I32, I64}TensorAttr.   Sean Silva
• [Mlir-commits] [mlir] 3dceb6d - Allow IndexType inside tensors.   Sean Silva
• [Mlir-commits] [mlir] 569e4f9 - `shape` dialect: add some ops   Sean Silva
• [Mlir-commits] [mlir] 6677477 - Verify number of result types in generated builder.   Sean Silva
• [Mlir-commits] [mlir] aa1e0e0 - [MLIR] Fix Xcode build due to incorrect library path   Aaron Smith
• [Mlir-commits] [mlir] 6dab806 - [mlir] Add exp2 conversion to llvm.intr.exp2   Aaron Smith
• [Mlir-commits] [mlir] 18fc42f - [mlir][LLVMIR] Add a support for boolean type arguments conversion   Ahmed Taei
• [Mlir-commits] [mlir] 08a9147 - [mlir][LLVMIR] Fix fusion for rank-0 tensors   Ahmed Taei
• [Mlir-commits] [mlir] 221fa96 - Fix linalg.generic access of hoisted constants   Ahmed Taei
• [Mlir-commits] [mlir] c224b4d - [mlir] NFC - Move Vector structure from RunnerUtils.h to CRunnerUtils.h   Nicolas Vasilache
• [Mlir-commits] [mlir] 78f9e5d - [mlir] Add padding to 1-D Vector in CRunnerUtils.h   Nicolas Vasilache
• [Mlir-commits] [mlir] a68235d - [mlir] Add padding to 1-D Vector in CRunnerUtils.h   Nicolas Vasilache
• [Mlir-commits] [mlir] bcee898 - [mlir] Hotfix - Fix Windows build   Nicolas Vasilache
• [Mlir-commits] [mlir] 9a8f296 - [mlir] Hotfix - Fix Windows build   Nicolas Vasilache
• [Mlir-commits] [mlir] 63b2ff0 - [mlir] Add padding to 1-D Vector in CRunnerUtils.h   Nicolas Vasilache
• [Mlir-commits] [mlir] cac1ed1 - [mlir] Introduce an intrinsic for llvm.matrix.multiply   Nicolas Vasilache
• [Mlir-commits] [mlir] c494ff0 - [mlir] NFC - Add predicates and types for VectorOfRank   Nicolas Vasilache
• [Mlir-commits] [mlir] 55622fd - [mlir][LLVM] Add remaining llvm.matrix intrinsics   Nicolas Vasilache
• [Mlir-commits] [mlir] 9032240 - [mlir][Vector] Allow lowering of vector.shape_cast 2D <-> 1D   Nicolas Vasilache
• [Mlir-commits] [mlir] 63b683a - [mlir][Vector] Add a vector.matrix_multiply op on 1-D vectors   Nicolas Vasilache
• [Mlir-commits] [mlir] e241573 - [mlir] NFC: remove IntegerValueSet / MutableIntegerSet   Nicolas Vasilache
• [Mlir-commits] [mlir] 47ec870 - [mlir][Linalg] Revisit 0-D abstraction   Nicolas Vasilache
• [Mlir-commits] [mlir] 8093e31 - [mlir][CRunnerUtils] Enable compilation with C++11 toolchain on microcontroller platforms.   Nicolas Vasilache
• [Mlir-commits] [mlir] bbf3ef8 - [mlir][Vector]Lower vector.contract to llvm.intr.matrix_multiply   Nicolas Vasilache
• [Mlir-commits] [mlir] 2fae787 - [mlir][Vector] Mostly-NFC - Restructure options for lowering to LLVM Matrix Intrinsics   Nicolas Vasilache
• [Mlir-commits] [mlir] 1e43132 - [mlir][LLVM] Add masked reads and writes.   Nicolas Vasilache
• [Mlir-commits] [mlir] 462db62 - [mlir][AVX512] Start a primitive AVX512 dialect   Nicolas Vasilache
• [Mlir-commits] [mlir] 40fc80a - [mlir][AVX512] Hotfix - Fix CMake Doc generation dependence   Nicolas Vasilache
• [Mlir-commits] [mlir] 6aef702 - [mlir][AVX512] Hotfix - Add cmake dependence on MLIRSideEffects   Nicolas Vasilache
• [Mlir-commits] [mlir] c0f4408 - [mlir] Create a std op instead of chain of ops.   Hanhan Wang
• [Mlir-commits] [mlir] 92f7e81 - [mlir][Linalg] Implement padding for linalg.conv and lowering to loops.   Hanhan Wang
• [Mlir-commits] [mlir] ae7bda5 - [mlir][Linalg] Remove initial value for conditions.   Hanhan Wang
• [Mlir-commits] [mlir] be4e9db - [mlir][Linalg] NFC: Clean up for 0-D abstraction.   Hanhan Wang
• [Mlir-commits] [mlir] 65c7031 - [mlir] Fix typos in DeclarativeRewrites.md   Hanhan Wang
• [Mlir-commits] [mlir] 69ddee1 - [mlir][Linalg] Introduce linalg.pooling_min/max/sum op.   Hanhan Wang
• [Mlir-commits] [mlir] 6dd696a - [mlir][Linalg] Extend fusion to support WAW atm on buffers.   Hanhan Wang
• [Mlir-commits] MLIR is broken, can not be built: CommandLine Error: Option 'help-list' registered more than once   Yuri
• [Mlir-commits] [mlir] 440ef33 - [mlir][spirv] Add get() method to TargetEnvAttr taking raw values   Lei Zhang
• [Mlir-commits] [mlir] 5b2cc6c - [mlir][ods] Improve integer signedness modelling   Lei Zhang
• [Mlir-commits] [mlir] 9600b55 - [mlir][spirv] Support integer signedness   Lei Zhang
• [Mlir-commits] [mlir] f6981ac - [mlir][vulkan-runner] Add basic timing for compute pipeline   Lei Zhang
• [Mlir-commits] [mlir] a50c031 - [mlir][ods] Fix AnyInteger predicate   Lei Zhang
• [Mlir-commits] [mlir] 1090a83 - [mlir][vulkan-runner] Update mlir-vulkan-runner execution driver.   Lei Zhang
• [Mlir-commits] [mlir] 5b0c60c - [mlir][vulkan-runner] Use std::make_tuple to create tuple   Lei Zhang
• [Mlir-commits] [mlir] e115a40 - [mlir][spirv] Use separate attribute for (version, capabilities, extensions)   Lei Zhang
• [Mlir-commits] [mlir] 66c378d - [mlir][spirv] Use larger range for target environment lookup function   Lei Zhang
• [Mlir-commits] [mlir] 9414db1 - [mlir][spirv] Add a pass to deduce version/extension/capability   Lei Zhang
• [Mlir-commits] [mlir] c818c3c - [mlir][spirv] NFC: put SPIR-V attributes in separate files   Lei Zhang
• [Mlir-commits] [mlir] 3148f10 - [mlir][spirv] Use spv.vce in spv.module and wire up (de)serialization   Lei Zhang
• [Mlir-commits] [mlir] 2ae5e47 - [mlir][spirv] Use SmallVector<ArrayRef> for availability queries   Lei Zhang
• [Mlir-commits] [mlir] e5c85a5 - [mlir][spirv] Support querying type extension/capability requirements   Lei Zhang
• [Mlir-commits] [mlir] 8fa261c - [mlir][spirv] Remove unnecessary friend class declaration   Lei Zhang
• [Mlir-commits] [mlir] bfb2ce0 - [mlir][vulkan-runner] Use C-compatible wrapper emission.   Lei Zhang
• [Mlir-commits] [mlir] 3b35f9d - [mlir][spirv] Use memref memory space for storage class   Lei Zhang
• [Mlir-commits] [mlir] 67e8690 - [mlir][spirv] Let SPIRVConversionTarget consider type availability   Lei Zhang
• [Mlir-commits] [mlir] 58df5e6 - [mlir][spirv] Plumbing target environment into type converter   Lei Zhang
• [Mlir-commits] [mlir] f741b8e - [mlir][spirv] Move type checks from dialect class to type hierarchy   Lei Zhang
• [Mlir-commits] [mlir] 9efb4b4 - [mlir][spirv] Make SPIRVTypeConverter target environment aware   Lei Zhang
• [Mlir-commits] [mlir] ffd4583 - [mlir][spirv] Change standard op patterns to consider type conversion   Lei Zhang
• [Mlir-commits] [mlir] 73431a4 - [mlir][spirv] Consolidate std.constant to spv.constant conversions   Lei Zhang
• [Mlir-commits] [mlir] 58cdb8b - [mlir][StandardToSPIRV] Add support for lowering unary ops   Lei Zhang
• [Mlir-commits] [mlir] 2679d8d - [mlir][vulkan-runner] Add test to time a large vector add   Lei Zhang
• [Mlir-commits] [mlir] d0af438 - [mlir][spirv] Add return to function to please MSVC   Lei Zhang
• [Mlir-commits] [mlir] d26435c - [mlir][spirv] Change op doc description autogen separator   Lei Zhang
• [Mlir-commits] [mlir] ee77607 - [mlir][spirv] Include SPIR-V op definitions in main SPIR-V doc   Lei Zhang
• [Mlir-commits] [mlir] d85821d - [MLIR] Added llvm.freeze   Alex Zinenko
• [Mlir-commits] [mlir] 464223b - [mlir] mlir-opt: print a newline after the top-level module   Alex Zinenko
• [Mlir-commits] [mlir] efa2d53 - [mlir] error out on unsupported attribute kinds in LLVM global translation   Alex Zinenko
• [Mlir-commits] [mlir] d7fbfbb - [mlir] ExecutionEngine: fix assertion on the error path   Alex Zinenko
• [Mlir-commits] [mlir] 8ba8ab8 - [mlir] support reductions in loop to std conversion   Alex Zinenko
• [Mlir-commits] [mlir] 8fc3e5c - [mlir] Format AffineOps.td. NFC   Alex Zinenko
• [Mlir-commits] [mlir] aff6bf4 - [mlir] support conversion of parallel reduction loops to std   Alex Zinenko
• [Mlir-commits] [mlir] e119980 - [mlir] LLVM dialect: move ensureDistinctSuccessors out of std->LLVM conversion   Alex Zinenko
• [Mlir-commits] [mlir] 76cf140 - [MLIR] Added llvm.fence   Alex Zinenko
• [Mlir-commits] [mlir] bc18624 - [mlir] vector.type_cast: disallow memrefs with layout in verifier   Alex Zinenko
• [Mlir-commits] [mlir] ff77397 - [mlir] Added llvm.resume and personality functions in LLVM IR Dialect   Alex Zinenko
• [Mlir-commits] [mlir] ec74867 - [mlir] Provide CustomOpAsmParser::parseOptionalOperand   Alex Zinenko
• [Mlir-commits] [mlir] 987fbae - [mlir] StandardToLLVM: make one-to-one convresion pattern publicly available   Alex Zinenko
• [Mlir-commits] [mlir] 04ed07b - [mlir] StandardToLLVM: clean up conversion patterns for vector operations   Alex Zinenko
• [Mlir-commits] [mlir] c16c07d - [mlir] StandardToLLVM: use template aliases instead of dummy classes   Alex Zinenko
• [Mlir-commits] [mlir] 755c050 - [mlir][Linalg] Fix load/store operations generated while lower loops when   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 3f44495 - [mlir][GPU] Expose the functionality to create a GPUFuncOp from a LaunchOp   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 0d92470 - [mlir] [VectorOps] Merge VectorReduction/VectorReductionV2 into one Op   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] d1186fc - [mlir] [ExecutionEngine] add option to enable/disable GDB notification listener   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 27dfb22 - [mlir] [VectorOps] Correctly account for rank-0 affine-map result in vector.contract   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 078776a - [mlir] [VectorOps] Progressively lower vector.outerproduct to LLVM   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] a213ece - [mlir] [VectorOps, LinAlg] Remove direct LLVM lowering for vector.broadcast   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 479ee11 - [mlir] [VectorOps] Introduce vector.transpose   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 141e589 - [MLIR] Add an IfOp builder with results   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 49ccb32 - Update ConversionToLLVMDialect.md   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 04f2b71 - [mlir] Fix unsafe create operation in GreedyPatternRewriter   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 8d46bfa - [mlir] [VectorOps] A "reference" lowering of vector.transpose to LLVM IR   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 46bb661 - [mlir][GPU] Use StructAttr to drive lowering from loop.parallel to   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 3b20970 - Fix unused-variable error when assertions are disabled   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] da7b6fe - [mlir][Linalg] Allow tiling of batch dimension for convolution ops with padding.   llvmlistbot at llvm.org

Last message date: Tue Mar 31 21:34:52 PDT 2020
Archived on: Tue Mar 31 21:34:56 PDT 2020

• Messages sorted by: [ thread ] [ subject ] [ date ]
• More info on this list...