diff options
Diffstat (limited to 'mlir/lib/Dialect')
-rw-r--r-- | mlir/lib/Dialect/Bufferization/Transforms/DropEquivalentBufferResults.cpp | 5 | ||||
-rw-r--r-- | mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp | 28 | ||||
-rw-r--r-- | mlir/lib/Dialect/Linalg/IR/LinalgInterfaces.cpp | 3 | ||||
-rw-r--r-- | mlir/lib/Dialect/MemRef/IR/CMakeLists.txt | 3 | ||||
-rw-r--r-- | mlir/lib/Dialect/MemRef/IR/MemRefOps.cpp | 59 | ||||
-rw-r--r-- | mlir/lib/Dialect/OpenACC/IR/OpenACC.cpp | 261 |
6 files changed, 348 insertions, 11 deletions
diff --git a/mlir/lib/Dialect/Bufferization/Transforms/DropEquivalentBufferResults.cpp b/mlir/lib/Dialect/Bufferization/Transforms/DropEquivalentBufferResults.cpp index 624519f..70faa71 100644 --- a/mlir/lib/Dialect/Bufferization/Transforms/DropEquivalentBufferResults.cpp +++ b/mlir/lib/Dialect/Bufferization/Transforms/DropEquivalentBufferResults.cpp @@ -64,12 +64,13 @@ mlir::bufferization::dropEquivalentBufferResults(ModuleOp module) { module.walk([&](func::CallOp callOp) { if (func::FuncOp calledFunc = dyn_cast_or_null<func::FuncOp>(callOp.resolveCallable())) { - callerMap[calledFunc].insert(callOp); + if (!calledFunc.isPublic() && !calledFunc.isExternal()) + callerMap[calledFunc].insert(callOp); } }); for (auto funcOp : module.getOps<func::FuncOp>()) { - if (funcOp.isExternal()) + if (funcOp.isExternal() || funcOp.isPublic()) continue; func::ReturnOp returnOp = getAssumedUniqueReturnOp(funcOp); // TODO: Support functions with multiple blocks. diff --git a/mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp b/mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp index 5edcc40b..ab54183 100644 --- a/mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp +++ b/mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp @@ -309,6 +309,17 @@ LogicalResult ConvertBF16x2ToF8x2Op::verify() { return success(); } +LogicalResult ConvertF32x2ToF4x2Op::verify() { + mlir::MLIRContext *ctx = getContext(); + + if (!llvm::isa<mlir::Float4E2M1FNType>(getDstTy())) + return emitOpError("Only ") + << mlir::Float4E2M1FNType::get(ctx) + << " type is supported for conversions from f32x2 to f4x2."; + + return success(); +} + LogicalResult BulkStoreOp::verify() { if (getInitVal() != 0) return emitOpError("only 0 is supported for initVal, got ") << getInitVal(); @@ -2047,6 +2058,23 @@ ConvertFloatToTF32Op::getIntrinsicID(NVVM::FPRoundingMode rnd, } } +NVVM::IDArgPair +ConvertF32x2ToF4x2Op::getIntrinsicIDAndArgs(NVVM::ConvertF32x2ToF4x2Op op, + LLVM::ModuleTranslation &mt, + llvm::IRBuilderBase &builder) { + llvm::SmallVector<llvm::Value *> args; + args.push_back(mt.lookupValue(op.getA())); + args.push_back(mt.lookupValue(op.getB())); + + bool hasRelu = op.getRelu(); + + llvm::Intrinsic::ID intId = + hasRelu ? llvm::Intrinsic::nvvm_ff_to_e2m1x2_rn_relu_satfinite + : llvm::Intrinsic::nvvm_ff_to_e2m1x2_rn_satfinite; + + return {intId, std::move(args)}; +} + #define GET_F32x2_TO_F6x2_ID(type, has_relu) \ has_relu ? llvm::Intrinsic::nvvm_ff_to_##type##_rn_relu_satfinite \ : llvm::Intrinsic::nvvm_ff_to_##type##_rn_satfinite diff --git a/mlir/lib/Dialect/Linalg/IR/LinalgInterfaces.cpp b/mlir/lib/Dialect/Linalg/IR/LinalgInterfaces.cpp index c477c6c..dcc1ef9 100644 --- a/mlir/lib/Dialect/Linalg/IR/LinalgInterfaces.cpp +++ b/mlir/lib/Dialect/Linalg/IR/LinalgInterfaces.cpp @@ -315,7 +315,8 @@ bool mlir::linalg::detail::isContractionBody( Value yielded = getSourceSkipUnary(terminator->getOperand(0)); Operation *reductionOp = yielded.getDefiningOp(); - if (reductionOp->getNumResults() != 1 || reductionOp->getNumOperands() != 2) { + if (!reductionOp || reductionOp->getNumResults() != 1 || + reductionOp->getNumOperands() != 2) { errs << "expected reduction op to be binary"; return false; } diff --git a/mlir/lib/Dialect/MemRef/IR/CMakeLists.txt b/mlir/lib/Dialect/MemRef/IR/CMakeLists.txt index e25a012..1382c7ac 100644 --- a/mlir/lib/Dialect/MemRef/IR/CMakeLists.txt +++ b/mlir/lib/Dialect/MemRef/IR/CMakeLists.txt @@ -5,7 +5,7 @@ add_mlir_dialect_library(MLIRMemRefDialect ValueBoundsOpInterfaceImpl.cpp ADDITIONAL_HEADER_DIRS - ${PROJECT_SOURCE_DIR}/inlude/mlir/Dialect/MemRefDialect + ${PROJECT_SOURCE_DIR}/inlude/mlir/Dialect/MemRef/IR DEPENDS MLIRMemRefOpsIncGen @@ -18,6 +18,7 @@ add_mlir_dialect_library(MLIRMemRefDialect MLIRDialectUtils MLIRInferIntRangeCommon MLIRInferIntRangeInterface + MLIRInferStridedMetadataInterface MLIRInferTypeOpInterface MLIRIR MLIRMemOpInterfaces diff --git a/mlir/lib/Dialect/MemRef/IR/MemRefOps.cpp b/mlir/lib/Dialect/MemRef/IR/MemRefOps.cpp index e9bdcda..507597b 100644 --- a/mlir/lib/Dialect/MemRef/IR/MemRefOps.cpp +++ b/mlir/lib/Dialect/MemRef/IR/MemRefOps.cpp @@ -3437,6 +3437,65 @@ SubViewOp::bubbleDownCasts(OpBuilder &builder) { return bubbleDownCastsPassthroughOpImpl(*this, builder, getSourceMutable()); } +void SubViewOp::inferStridedMetadataRanges( + ArrayRef<StridedMetadataRange> ranges, GetIntRangeFn getIntRange, + SetStridedMetadataRangeFn setMetadata, int32_t indexBitwidth) { + auto isUninitialized = + +[](IntegerValueRange range) { return range.isUninitialized(); }; + + // Bail early if any of the operands metadata is not ready: + SmallVector<IntegerValueRange> offsetOperands = + getIntValueRanges(getMixedOffsets(), getIntRange, indexBitwidth); + if (llvm::any_of(offsetOperands, isUninitialized)) + return; + + SmallVector<IntegerValueRange> sizeOperands = + getIntValueRanges(getMixedSizes(), getIntRange, indexBitwidth); + if (llvm::any_of(sizeOperands, isUninitialized)) + return; + + SmallVector<IntegerValueRange> stridesOperands = + getIntValueRanges(getMixedStrides(), getIntRange, indexBitwidth); + if (llvm::any_of(stridesOperands, isUninitialized)) + return; + + StridedMetadataRange sourceRange = + ranges[getSourceMutable().getOperandNumber()]; + if (sourceRange.isUninitialized()) + return; + + ArrayRef<ConstantIntRanges> srcStrides = sourceRange.getStrides(); + + // Get the dropped dims. + llvm::SmallBitVector droppedDims = getDroppedDims(); + + // Compute the new offset, strides and sizes. + ConstantIntRanges offset = sourceRange.getOffsets()[0]; + SmallVector<ConstantIntRanges> strides, sizes; + + for (size_t i = 0, e = droppedDims.size(); i < e; ++i) { + bool dropped = droppedDims.test(i); + // Compute the new offset. + ConstantIntRanges off = + intrange::inferMul({offsetOperands[i].getValue(), srcStrides[i]}); + offset = intrange::inferAdd({offset, off}); + + // Skip dropped dimensions. + if (dropped) + continue; + // Multiply the strides. + strides.push_back( + intrange::inferMul({stridesOperands[i].getValue(), srcStrides[i]})); + // Get the sizes. + sizes.push_back(sizeOperands[i].getValue()); + } + + setMetadata(getResult(), + StridedMetadataRange::getRanked( + SmallVector<ConstantIntRanges>({std::move(offset)}), + std::move(sizes), std::move(strides))); +} + //===----------------------------------------------------------------------===// // TransposeOp //===----------------------------------------------------------------------===// diff --git a/mlir/lib/Dialect/OpenACC/IR/OpenACC.cpp b/mlir/lib/Dialect/OpenACC/IR/OpenACC.cpp index 6564a4e..642ced9 100644 --- a/mlir/lib/Dialect/OpenACC/IR/OpenACC.cpp +++ b/mlir/lib/Dialect/OpenACC/IR/OpenACC.cpp @@ -17,6 +17,7 @@ #include "mlir/IR/DialectImplementation.h" #include "mlir/IR/Matchers.h" #include "mlir/IR/OpImplementation.h" +#include "mlir/IR/SymbolTable.h" #include "mlir/Support/LLVM.h" #include "mlir/Transforms/DialectConversion.h" #include "llvm/ADT/SmallSet.h" @@ -74,14 +75,16 @@ struct MemRefPointerLikeModel } mlir::Value genAllocate(Type pointer, OpBuilder &builder, Location loc, - StringRef varName, Type varType, - Value originalVar) const { + StringRef varName, Type varType, Value originalVar, + bool &needsFree) const { auto memrefTy = cast<MemRefType>(pointer); // Check if this is a static memref (all dimensions are known) - if yes // then we can generate an alloca operation. - if (memrefTy.hasStaticShape()) + if (memrefTy.hasStaticShape()) { + needsFree = false; // alloca doesn't need deallocation return memref::AllocaOp::create(builder, loc, memrefTy).getResult(); + } // For dynamic memrefs, extract sizes from the original variable if // provided. Otherwise they cannot be handled. @@ -99,6 +102,7 @@ struct MemRefPointerLikeModel // Note: We only add dynamic sizes to the dynamicSizes array // Static dimensions are handled automatically by AllocOp } + needsFree = true; // alloc needs deallocation return memref::AllocOp::create(builder, loc, memrefTy, dynamicSizes) .getResult(); } @@ -108,10 +112,14 @@ struct MemRefPointerLikeModel } bool genFree(Type pointer, OpBuilder &builder, Location loc, - TypedValue<PointerLikeType> varPtr, Type varType) const { - if (auto memrefValue = dyn_cast<TypedValue<MemRefType>>(varPtr)) { + TypedValue<PointerLikeType> varToFree, Value allocRes, + Type varType) const { + if (auto memrefValue = dyn_cast<TypedValue<MemRefType>>(varToFree)) { + // Use allocRes if provided to determine the allocation type + Value valueToInspect = allocRes ? allocRes : memrefValue; + // Walk through casts to find the original allocation - Value currentValue = memrefValue; + Value currentValue = valueToInspect; Operation *originalAlloc = nullptr; // Follow the chain of operations to find the original allocation @@ -150,7 +158,7 @@ struct MemRefPointerLikeModel return true; } if (isa<memref::AllocOp>(originalAlloc)) { - // This is an alloc - generate dealloc + // This is an alloc - generate dealloc on varToFree memref::DeallocOp::create(builder, loc, memrefValue); return true; } @@ -1003,6 +1011,142 @@ struct RemoveConstantIfConditionWithRegion : public OpRewritePattern<OpTy> { } }; +//===----------------------------------------------------------------------===// +// Recipe Region Helpers +//===----------------------------------------------------------------------===// + +/// Create and populate an init region for privatization recipes. +/// Returns the init block on success, or nullptr on failure. +/// Sets needsFree to indicate if the allocated memory requires deallocation. +static std::unique_ptr<Block> createInitRegion(OpBuilder &builder, Location loc, + Type varType, StringRef varName, + ValueRange bounds, + bool &needsFree) { + // Create init block with arguments: original value + bounds + SmallVector<Type> argTypes{varType}; + SmallVector<Location> argLocs{loc}; + for (Value bound : bounds) { + argTypes.push_back(bound.getType()); + argLocs.push_back(loc); + } + + auto initBlock = std::make_unique<Block>(); + initBlock->addArguments(argTypes, argLocs); + builder.setInsertionPointToStart(initBlock.get()); + + Value privatizedValue; + + // Get the block argument that represents the original variable + Value blockArgVar = initBlock->getArgument(0); + + // Generate init region body based on variable type + if (isa<MappableType>(varType)) { + auto mappableTy = cast<MappableType>(varType); + auto typedVar = cast<TypedValue<MappableType>>(blockArgVar); + privatizedValue = mappableTy.generatePrivateInit( + builder, loc, typedVar, varName, bounds, {}, needsFree); + if (!privatizedValue) + return nullptr; + } else { + assert(isa<PointerLikeType>(varType) && "Expected PointerLikeType"); + auto pointerLikeTy = cast<PointerLikeType>(varType); + // Use PointerLikeType's allocation API with the block argument + privatizedValue = pointerLikeTy.genAllocate(builder, loc, varName, varType, + blockArgVar, needsFree); + if (!privatizedValue) + return nullptr; + } + + // Add yield operation to init block + acc::YieldOp::create(builder, loc, privatizedValue); + + return initBlock; +} + +/// Create and populate a copy region for firstprivate recipes. +/// Returns the copy block on success, or nullptr on failure. +/// TODO: Handle MappableType - it does not yet have a copy API. +static std::unique_ptr<Block> createCopyRegion(OpBuilder &builder, Location loc, + Type varType, + ValueRange bounds) { + // Create copy block with arguments: original value + privatized value + + // bounds + SmallVector<Type> copyArgTypes{varType, varType}; + SmallVector<Location> copyArgLocs{loc, loc}; + for (Value bound : bounds) { + copyArgTypes.push_back(bound.getType()); + copyArgLocs.push_back(loc); + } + + auto copyBlock = std::make_unique<Block>(); + copyBlock->addArguments(copyArgTypes, copyArgLocs); + builder.setInsertionPointToStart(copyBlock.get()); + + bool isMappable = isa<MappableType>(varType); + bool isPointerLike = isa<PointerLikeType>(varType); + // TODO: Handle MappableType - it does not yet have a copy API. + // Otherwise, for now just fallback to pointer-like behavior. + if (isMappable && !isPointerLike) + return nullptr; + + // Generate copy region body based on variable type + if (isPointerLike) { + auto pointerLikeTy = cast<PointerLikeType>(varType); + Value originalArg = copyBlock->getArgument(0); + Value privatizedArg = copyBlock->getArgument(1); + + // Generate copy operation using PointerLikeType interface + if (!pointerLikeTy.genCopy( + builder, loc, cast<TypedValue<PointerLikeType>>(privatizedArg), + cast<TypedValue<PointerLikeType>>(originalArg), varType)) + return nullptr; + } + + // Add terminator to copy block + acc::TerminatorOp::create(builder, loc); + + return copyBlock; +} + +/// Create and populate a destroy region for privatization recipes. +/// Returns the destroy block on success, or nullptr if not needed. +static std::unique_ptr<Block> createDestroyRegion(OpBuilder &builder, + Location loc, Type varType, + Value allocRes, + ValueRange bounds) { + // Create destroy block with arguments: original value + privatized value + + // bounds + SmallVector<Type> destroyArgTypes{varType, varType}; + SmallVector<Location> destroyArgLocs{loc, loc}; + for (Value bound : bounds) { + destroyArgTypes.push_back(bound.getType()); + destroyArgLocs.push_back(loc); + } + + auto destroyBlock = std::make_unique<Block>(); + destroyBlock->addArguments(destroyArgTypes, destroyArgLocs); + builder.setInsertionPointToStart(destroyBlock.get()); + + bool isMappable = isa<MappableType>(varType); + bool isPointerLike = isa<PointerLikeType>(varType); + // TODO: Handle MappableType - it does not yet have a deallocation API. + // Otherwise, for now just fallback to pointer-like behavior. + if (isMappable && !isPointerLike) + return nullptr; + + assert(isa<PointerLikeType>(varType) && "Expected PointerLikeType"); + auto pointerLikeTy = cast<PointerLikeType>(varType); + auto privatizedArg = + cast<TypedValue<PointerLikeType>>(destroyBlock->getArgument(1)); + // Pass allocRes to help determine the allocation type + if (!pointerLikeTy.genFree(builder, loc, privatizedArg, allocRes, varType)) + return nullptr; + + acc::TerminatorOp::create(builder, loc); + + return destroyBlock; +} + } // namespace //===----------------------------------------------------------------------===// @@ -1050,6 +1194,55 @@ LogicalResult acc::PrivateRecipeOp::verifyRegions() { return success(); } +std::optional<PrivateRecipeOp> +PrivateRecipeOp::createAndPopulate(OpBuilder &builder, Location loc, + StringRef recipeName, Type varType, + StringRef varName, ValueRange bounds) { + // First, validate that we can handle this variable type + bool isMappable = isa<MappableType>(varType); + bool isPointerLike = isa<PointerLikeType>(varType); + + // Unsupported type + if (!isMappable && !isPointerLike) + return std::nullopt; + + // Create init and destroy blocks using shared helpers + OpBuilder::InsertionGuard guard(builder); + + // Save the original insertion point for creating the recipe operation later + auto originalInsertionPoint = builder.saveInsertionPoint(); + + bool needsFree = false; + auto initBlock = + createInitRegion(builder, loc, varType, varName, bounds, needsFree); + if (!initBlock) + return std::nullopt; + + // Only create destroy region if the allocation needs deallocation + std::unique_ptr<Block> destroyBlock; + if (needsFree) { + // Extract the allocated value from the init block's yield operation + auto yieldOp = cast<acc::YieldOp>(initBlock->getTerminator()); + Value allocRes = yieldOp.getOperand(0); + + destroyBlock = createDestroyRegion(builder, loc, varType, allocRes, bounds); + if (!destroyBlock) + return std::nullopt; + } + + // Now create the recipe operation at the original insertion point and attach + // the blocks + builder.restoreInsertionPoint(originalInsertionPoint); + auto recipe = PrivateRecipeOp::create(builder, loc, recipeName, varType); + + // Move the blocks into the recipe's regions + recipe.getInitRegion().push_back(initBlock.release()); + if (destroyBlock) + recipe.getDestroyRegion().push_back(destroyBlock.release()); + + return recipe; +} + //===----------------------------------------------------------------------===// // FirstprivateRecipeOp //===----------------------------------------------------------------------===// @@ -1080,6 +1273,60 @@ LogicalResult acc::FirstprivateRecipeOp::verifyRegions() { return success(); } +std::optional<FirstprivateRecipeOp> +FirstprivateRecipeOp::createAndPopulate(OpBuilder &builder, Location loc, + StringRef recipeName, Type varType, + StringRef varName, ValueRange bounds) { + // First, validate that we can handle this variable type + bool isMappable = isa<MappableType>(varType); + bool isPointerLike = isa<PointerLikeType>(varType); + + // Unsupported type + if (!isMappable && !isPointerLike) + return std::nullopt; + + // Create init, copy, and destroy blocks using shared helpers + OpBuilder::InsertionGuard guard(builder); + + // Save the original insertion point for creating the recipe operation later + auto originalInsertionPoint = builder.saveInsertionPoint(); + + bool needsFree = false; + auto initBlock = + createInitRegion(builder, loc, varType, varName, bounds, needsFree); + if (!initBlock) + return std::nullopt; + + auto copyBlock = createCopyRegion(builder, loc, varType, bounds); + if (!copyBlock) + return std::nullopt; + + // Only create destroy region if the allocation needs deallocation + std::unique_ptr<Block> destroyBlock; + if (needsFree) { + // Extract the allocated value from the init block's yield operation + auto yieldOp = cast<acc::YieldOp>(initBlock->getTerminator()); + Value allocRes = yieldOp.getOperand(0); + + destroyBlock = createDestroyRegion(builder, loc, varType, allocRes, bounds); + if (!destroyBlock) + return std::nullopt; + } + + // Now create the recipe operation at the original insertion point and attach + // the blocks + builder.restoreInsertionPoint(originalInsertionPoint); + auto recipe = FirstprivateRecipeOp::create(builder, loc, recipeName, varType); + + // Move the blocks into the recipe's regions + recipe.getInitRegion().push_back(initBlock.release()); + recipe.getCopyRegion().push_back(copyBlock.release()); + if (destroyBlock) + recipe.getDestroyRegion().push_back(destroyBlock.release()); + + return recipe; +} + //===----------------------------------------------------------------------===// // ReductionRecipeOp //===----------------------------------------------------------------------===// |