[mlir][NFC] update mlir/Dialect create APIs (14/n)

mlir/lib/Dialect/AMDGPU/Transforms/EmulateAtomics.cpp

@@ -99,8 +99,8 @@ static Value flattenVecToBits(ConversionPatternRewriter &rewriter, Location loc,
       vectorType.getElementTypeBitWidth() * vectorType.getNumElements();
   Type allBitsType = rewriter.getIntegerType(bitwidth);
   auto allBitsVecType = VectorType::get({1}, allBitsType);
-  Value bitcast = rewriter.create<vector::BitCastOp>(loc, allBitsVecType, val);
-  Value scalar = rewriter.create<vector::ExtractOp>(loc, bitcast, 0);
+  Value bitcast = vector::BitCastOp::create(rewriter, loc, allBitsVecType, val);
+  Value scalar = vector::ExtractOp::create(rewriter, loc, bitcast, 0);
   return scalar;
 }
 
@@ -118,27 +118,27 @@ LogicalResult RawBufferAtomicByCasPattern<AtomicOp, ArithOp>::matchAndRewrite(
 
   SmallVector<NamedAttribute> loadAttrs;
   patchOperandSegmentSizes(origAttrs, loadAttrs, DataArgAction::Drop);
-  Value initialLoad =
-      rewriter.create<RawBufferLoadOp>(loc, dataType, invariantArgs, loadAttrs);
+  Value initialLoad = RawBufferLoadOp::create(rewriter, loc, dataType,
+                                              invariantArgs, loadAttrs);
   Block *currentBlock = rewriter.getInsertionBlock();
   Block *afterAtomic =
       rewriter.splitBlock(currentBlock, rewriter.getInsertionPoint());
   Block *loopBlock = rewriter.createBlock(afterAtomic, {dataType}, {loc});
 
   rewriter.setInsertionPointToEnd(currentBlock);
-  rewriter.create<cf::BranchOp>(loc, loopBlock, initialLoad);
+  cf::BranchOp::create(rewriter, loc, loopBlock, initialLoad);
 
   rewriter.setInsertionPointToEnd(loopBlock);
   Value prevLoad = loopBlock->getArgument(0);
-  Value operated = rewriter.create<ArithOp>(loc, data, prevLoad);
+  Value operated = ArithOp::create(rewriter, loc, data, prevLoad);
   dataType = operated.getType();
 
   SmallVector<NamedAttribute> cmpswapAttrs;
   patchOperandSegmentSizes(origAttrs, cmpswapAttrs, DataArgAction::Duplicate);
   SmallVector<Value> cmpswapArgs = {operated, prevLoad};
   cmpswapArgs.append(invariantArgs.begin(), invariantArgs.end());
-  Value atomicRes = rewriter.create<RawBufferAtomicCmpswapOp>(
-      loc, dataType, cmpswapArgs, cmpswapAttrs);
+  Value atomicRes = RawBufferAtomicCmpswapOp::create(rewriter, loc, dataType,
+                                                     cmpswapArgs, cmpswapAttrs);
 
   // We care about exact bitwise equality here, so do some bitcasts.
   // These will fold away during lowering to the ROCDL dialect, where
@@ -150,14 +150,15 @@ LogicalResult RawBufferAtomicByCasPattern<AtomicOp, ArithOp>::matchAndRewrite(
   if (auto floatDataTy = dyn_cast<FloatType>(dataType)) {
     Type equivInt = rewriter.getIntegerType(floatDataTy.getWidth());
     prevLoadForCompare =
-        rewriter.create<arith::BitcastOp>(loc, equivInt, prevLoad);
+        arith::BitcastOp::create(rewriter, loc, equivInt, prevLoad);
     atomicResForCompare =
-        rewriter.create<arith::BitcastOp>(loc, equivInt, atomicRes);
+        arith::BitcastOp::create(rewriter, loc, equivInt, atomicRes);
   }
-  Value canLeave = rewriter.create<arith::CmpIOp>(
-      loc, arith::CmpIPredicate::eq, atomicResForCompare, prevLoadForCompare);
-  rewriter.create<cf::CondBranchOp>(loc, canLeave, afterAtomic, ValueRange{},
-                                    loopBlock, atomicRes);
+  Value canLeave =
+      arith::CmpIOp::create(rewriter, loc, arith::CmpIPredicate::eq,
+                            atomicResForCompare, prevLoadForCompare);
+  cf::CondBranchOp::create(rewriter, loc, canLeave, afterAtomic, ValueRange{},
+                           loopBlock, atomicRes);
   rewriter.eraseOp(atomicOp);
   return success();
 }

mlir/lib/Dialect/AMDGPU/Transforms/MaskedloadToLoad.cpp

@@ -54,11 +54,11 @@ static Value createVectorLoadForMaskedLoad(OpBuilder &builder, Location loc,
                                            vector::MaskedLoadOp maskedOp,
                                            bool passthru) {
   VectorType vectorType = maskedOp.getVectorType();
-  Value load = builder.create<vector::LoadOp>(
-      loc, vectorType, maskedOp.getBase(), maskedOp.getIndices());
+  Value load = vector::LoadOp::create(
+      builder, loc, vectorType, maskedOp.getBase(), maskedOp.getIndices());
   if (passthru)
-    load = builder.create<arith::SelectOp>(loc, vectorType, maskedOp.getMask(),
-                                           load, maskedOp.getPassThru());
+    load = arith::SelectOp::create(builder, loc, vectorType, maskedOp.getMask(),
+                                   load, maskedOp.getPassThru());
   return load;
 }
 
@@ -108,7 +108,7 @@ struct MaskedLoadLowering final : OpRewritePattern<vector::MaskedLoadOp> {
     SmallVector<OpFoldResult> indices = maskedOp.getIndices();
 
     auto stridedMetadata =
-        rewriter.create<memref::ExtractStridedMetadataOp>(loc, src);
+        memref::ExtractStridedMetadataOp::create(rewriter, loc, src);
     SmallVector<OpFoldResult> strides =
         stridedMetadata.getConstifiedMixedStrides();
     SmallVector<OpFoldResult> sizes = stridedMetadata.getConstifiedMixedSizes();
@@ -122,47 +122,47 @@ struct MaskedLoadLowering final : OpRewritePattern<vector::MaskedLoadOp> {
 
     // delta = bufferSize - linearizedOffset
     Value vectorSizeOffset =
-        rewriter.create<arith::ConstantIndexOp>(loc, vectorSize);
+        arith::ConstantIndexOp::create(rewriter, loc, vectorSize);
     Value linearIndex =
         getValueOrCreateConstantIndexOp(rewriter, loc, linearizedIndices);
     Value totalSize = getValueOrCreateConstantIndexOp(
         rewriter, loc, linearizedInfo.linearizedSize);
-    Value delta = rewriter.create<arith::SubIOp>(loc, totalSize, linearIndex);
+    Value delta = arith::SubIOp::create(rewriter, loc, totalSize, linearIndex);
 
     // 1) check if delta < vectorSize
-    Value isOutofBounds = rewriter.create<arith::CmpIOp>(
-        loc, arith::CmpIPredicate::ult, delta, vectorSizeOffset);
+    Value isOutofBounds = arith::CmpIOp::create(
+        rewriter, loc, arith::CmpIPredicate::ult, delta, vectorSizeOffset);
 
     // 2) check if (detla % elements_per_word != 0)
-    Value elementsPerWord = rewriter.create<arith::ConstantIndexOp>(
-        loc, llvm::divideCeil(32, elementBitWidth));
-    Value isNotWordAligned = rewriter.create<arith::CmpIOp>(
-        loc, arith::CmpIPredicate::ne,
-        rewriter.create<arith::RemUIOp>(loc, delta, elementsPerWord),
-        rewriter.create<arith::ConstantIndexOp>(loc, 0));
+    Value elementsPerWord = arith::ConstantIndexOp::create(
+        rewriter, loc, llvm::divideCeil(32, elementBitWidth));
+    Value isNotWordAligned = arith::CmpIOp::create(
+        rewriter, loc, arith::CmpIPredicate::ne,
+        arith::RemUIOp::create(rewriter, loc, delta, elementsPerWord),
+        arith::ConstantIndexOp::create(rewriter, loc, 0));
 
     // We take the fallback of maskedload default lowering only it is both
     // out-of-bounds and not word aligned. The fallback ensures correct results
     // when loading at the boundary of the buffer since buffer load returns
     // inconsistent zeros for the whole word when boundary is crossed.
     Value ifCondition =
-        rewriter.create<arith::AndIOp>(loc, isOutofBounds, isNotWordAligned);
+        arith::AndIOp::create(rewriter, loc, isOutofBounds, isNotWordAligned);
 
     auto thenBuilder = [&](OpBuilder &builder, Location loc) {
       Operation *read = builder.clone(*maskedOp.getOperation());
       read->setAttr(kMaskedloadNeedsMask, builder.getUnitAttr());
       Value readResult = read->getResult(0);
-      builder.create<scf::YieldOp>(loc, readResult);
+      scf::YieldOp::create(builder, loc, readResult);
     };
 
     auto elseBuilder = [&](OpBuilder &builder, Location loc) {
       Value res = createVectorLoadForMaskedLoad(builder, loc, maskedOp,
                                                 /*passthru=*/true);
-      rewriter.create<scf::YieldOp>(loc, res);
+      scf::YieldOp::create(rewriter, loc, res);
     };
 
     auto ifOp =
-        rewriter.create<scf::IfOp>(loc, ifCondition, thenBuilder, elseBuilder);
+        scf::IfOp::create(rewriter, loc, ifCondition, thenBuilder, elseBuilder);
 
     rewriter.replaceOp(maskedOp, ifOp);
 
@@ -185,13 +185,13 @@ struct FullMaskedLoadToConditionalLoad
     auto trueBuilder = [&](OpBuilder &builder, Location loc) {
       Value res = createVectorLoadForMaskedLoad(builder, loc, loadOp,
                                                 /*passthru=*/false);
-      rewriter.create<scf::YieldOp>(loc, res);
+      scf::YieldOp::create(rewriter, loc, res);
     };
     auto falseBuilder = [&](OpBuilder &builder, Location loc) {
-      rewriter.create<scf::YieldOp>(loc, loadOp.getPassThru());
+      scf::YieldOp::create(rewriter, loc, loadOp.getPassThru());
     };
-    auto ifOp = rewriter.create<scf::IfOp>(loadOp.getLoc(), cond, trueBuilder,
-                                           falseBuilder);
+    auto ifOp = scf::IfOp::create(rewriter, loadOp.getLoc(), cond, trueBuilder,
+                                  falseBuilder);
     rewriter.replaceOp(loadOp, ifOp);
     return success();
   }
@@ -210,11 +210,12 @@ struct FullMaskedStoreToConditionalStore
     Value cond = maybeCond.value();
 
     auto trueBuilder = [&](OpBuilder &builder, Location loc) {
-      rewriter.create<vector::StoreOp>(loc, storeOp.getValueToStore(),
-                                       storeOp.getBase(), storeOp.getIndices());
-      rewriter.create<scf::YieldOp>(loc);
+      vector::StoreOp::create(rewriter, loc, storeOp.getValueToStore(),
+                              storeOp.getBase(), storeOp.getIndices());
+      scf::YieldOp::create(rewriter, loc);
     };
-    auto ifOp = rewriter.create<scf::IfOp>(storeOp.getLoc(), cond, trueBuilder);
+    auto ifOp =
+        scf::IfOp::create(rewriter, storeOp.getLoc(), cond, trueBuilder);
     rewriter.replaceOp(storeOp, ifOp);
     return success();
   }

mlir/lib/Dialect/AMDGPU/Transforms/ResolveStridedMetadata.cpp

@@ -37,8 +37,8 @@ struct ExtractStridedMetadataOnFatRawBufferCastFolder final
       return rewriter.notifyMatchFailure(metadataOp,
                                          "not a fat raw buffer cast");
     Location loc = castOp.getLoc();
-    auto sourceMetadata = rewriter.create<memref::ExtractStridedMetadataOp>(
-        loc, castOp.getSource());
+    auto sourceMetadata = memref::ExtractStridedMetadataOp::create(
+        rewriter, loc, castOp.getSource());
     SmallVector<Value> results;
     if (metadataOp.getBaseBuffer().use_empty()) {
       results.push_back(nullptr);
@@ -48,13 +48,13 @@ struct ExtractStridedMetadataOnFatRawBufferCastFolder final
       if (baseBufferType == castOp.getResult().getType()) {
         results.push_back(castOp.getResult());
       } else {
-        results.push_back(rewriter.create<memref::ReinterpretCastOp>(
-            loc, baseBufferType, castOp.getResult(), /*offset=*/0,
+        results.push_back(memref::ReinterpretCastOp::create(
+            rewriter, loc, baseBufferType, castOp.getResult(), /*offset=*/0,
             /*sizes=*/ArrayRef<int64_t>{}, /*strides=*/ArrayRef<int64_t>{}));
       }
     }
     if (castOp.getResetOffset())
-      results.push_back(rewriter.create<arith::ConstantIndexOp>(loc, 0));
+      results.push_back(arith::ConstantIndexOp::create(rewriter, loc, 0));
     else
       results.push_back(sourceMetadata.getOffset());
     llvm::append_range(results, sourceMetadata.getSizes());

mlir/lib/Dialect/AMX/IR/AMXDialect.cpp

@@ -76,8 +76,8 @@ static SmallVector<Value> getTileSizes(Location loc, amx::TileType tType,
   auto mattr = rewriter.getI16IntegerAttr(tType.getDimSize(0));
   auto nattr = rewriter.getI16IntegerAttr(tType.getDimSize(1) * bytes);
   return SmallVector<Value>{
-      rewriter.create<LLVM::ConstantOp>(loc, llvmInt16Type, mattr),
-      rewriter.create<LLVM::ConstantOp>(loc, llvmInt16Type, nattr)};
+      LLVM::ConstantOp::create(rewriter, loc, llvmInt16Type, mattr),
+      LLVM::ConstantOp::create(rewriter, loc, llvmInt16Type, nattr)};
 }
 
 /// Maps the 2-dim memref shape to the 64-bit stride. Note that the buffer
@@ -95,15 +95,15 @@ static Value getStride(Location loc, MemRefType mType, Value base,
     // Dynamic stride needs code to compute the stride at runtime.
     MemRefDescriptor memrefDescriptor(base);
     auto attr = rewriter.getI64IntegerAttr(bytes);
-    Value scale = rewriter.create<LLVM::ConstantOp>(loc, llvmInt64Type, attr);
+    Value scale = LLVM::ConstantOp::create(rewriter, loc, llvmInt64Type, attr);
     return rewriter
         .create<LLVM::MulOp>(loc, llvmInt64Type, scale,
                              memrefDescriptor.stride(rewriter, loc, preLast))
         .getResult();
   }
   // Use direct constant for static stride.
   auto attr = rewriter.getI64IntegerAttr(strides[preLast] * bytes);
-  return rewriter.create<LLVM::ConstantOp>(loc, llvmInt64Type, attr)
+  return LLVM::ConstantOp::create(rewriter, loc, llvmInt64Type, attr)
       .getResult();
 }
 

mlir/lib/Dialect/Affine/Transforms/AffineDataCopyGeneration.cpp

@@ -202,7 +202,7 @@ void AffineDataCopyGeneration::runOnBlock(Block *block,
 void AffineDataCopyGeneration::runOnOperation() {
   func::FuncOp f = getOperation();
   OpBuilder topBuilder(f.getBody());
-  zeroIndex = topBuilder.create<arith::ConstantIndexOp>(f.getLoc(), 0);
+  zeroIndex = arith::ConstantIndexOp::create(topBuilder, f.getLoc(), 0);
 
   // Nests that are copy-in's or copy-out's; the root AffineForOps of those
   // nests are stored herein.

mlir/lib/Dialect/Affine/Transforms/AffineExpandIndexOps.cpp

@@ -58,8 +58,9 @@ static SmallVector<Value> computeStrides(Location loc, RewriterBase &rewriter,
       // Note: basis elements and their products are, definitionally,
       // non-negative, so `nuw` is justified.
       if (dynamicPart)
-        dynamicPart = rewriter.create<arith::MulIOp>(
-            loc, dynamicPart, dynamicBasis[dynamicIndex - 1], ovflags);
+        dynamicPart =
+            arith::MulIOp::create(rewriter, loc, dynamicPart,
+                                  dynamicBasis[dynamicIndex - 1], ovflags);
       else
         dynamicPart = dynamicBasis[dynamicIndex - 1];
       --dynamicIndex;
@@ -74,7 +75,7 @@ static SmallVector<Value> computeStrides(Location loc, RewriterBase &rewriter,
           rewriter.createOrFold<arith::ConstantIndexOp>(loc, staticPart);
       if (dynamicPart)
         stride =
-            rewriter.create<arith::MulIOp>(loc, dynamicPart, stride, ovflags);
+            arith::MulIOp::create(rewriter, loc, dynamicPart, stride, ovflags);
       result.push_back(stride);
     }
   }
@@ -106,20 +107,20 @@ affine::lowerAffineDelinearizeIndexOp(RewriterBase &rewriter,
   Value zero = rewriter.createOrFold<arith::ConstantIndexOp>(loc, 0);
 
   Value initialPart =
-      rewriter.create<arith::FloorDivSIOp>(loc, linearIdx, strides.front());
+      arith::FloorDivSIOp::create(rewriter, loc, linearIdx, strides.front());
   results.push_back(initialPart);
 
   auto emitModTerm = [&](Value stride) -> Value {
-    Value remainder = rewriter.create<arith::RemSIOp>(loc, linearIdx, stride);
-    Value remainderNegative = rewriter.create<arith::CmpIOp>(
-        loc, arith::CmpIPredicate::slt, remainder, zero);
+    Value remainder = arith::RemSIOp::create(rewriter, loc, linearIdx, stride);
+    Value remainderNegative = arith::CmpIOp::create(
+        rewriter, loc, arith::CmpIPredicate::slt, remainder, zero);
     // If the correction is relevant, this term is <= stride, which is known
     // to be positive in `index`. Otherwise, while 2 * stride might overflow,
     // this branch won't be taken, so the risk of `poison` is fine.
-    Value corrected = rewriter.create<arith::AddIOp>(
-        loc, remainder, stride, arith::IntegerOverflowFlags::nsw);
-    Value mod = rewriter.create<arith::SelectOp>(loc, remainderNegative,
-                                                 corrected, remainder);
+    Value corrected = arith::AddIOp::create(rewriter, loc, remainder, stride,
+                                            arith::IntegerOverflowFlags::nsw);
+    Value mod = arith::SelectOp::create(rewriter, loc, remainderNegative,
+                                        corrected, remainder);
     return mod;
   };
 
@@ -131,7 +132,7 @@ affine::lowerAffineDelinearizeIndexOp(RewriterBase &rewriter,
     // We know both inputs are positive, so floorDiv == div.
     // This could potentially be a divui, but it's not clear if that would
     // cause issues.
-    Value divided = rewriter.create<arith::DivSIOp>(loc, modulus, nextStride);
+    Value divided = arith::DivSIOp::create(rewriter, loc, modulus, nextStride);
     results.push_back(divided);
   }
 
@@ -167,8 +168,8 @@ LogicalResult affine::lowerAffineLinearizeIndexOp(RewriterBase &rewriter,
   // our hands on an `OpOperand&` for the loop invariant counting function.
   for (auto [stride, idxOp] :
        llvm::zip_equal(strides, llvm::drop_end(op.getMultiIndexMutable()))) {
-    Value scaledIdx = rewriter.create<arith::MulIOp>(
-        loc, idxOp.get(), stride, arith::IntegerOverflowFlags::nsw);
+    Value scaledIdx = arith::MulIOp::create(rewriter, loc, idxOp.get(), stride,
+                                            arith::IntegerOverflowFlags::nsw);
     int64_t numHoistableLoops = numEnclosingInvariantLoops(idxOp);
     scaledValues.emplace_back(scaledIdx, numHoistableLoops);
   }
@@ -184,8 +185,8 @@ LogicalResult affine::lowerAffineLinearizeIndexOp(RewriterBase &rewriter,
   Value result = scaledValues.front().first;
   for (auto [scaledValue, numHoistableLoops] : llvm::drop_begin(scaledValues)) {
     std::ignore = numHoistableLoops;
-    result = rewriter.create<arith::AddIOp>(loc, result, scaledValue,
-                                            arith::IntegerOverflowFlags::nsw);
+    result = arith::AddIOp::create(rewriter, loc, result, scaledValue,
+                                   arith::IntegerOverflowFlags::nsw);
   }
   rewriter.replaceOp(op, result);
   return success();

mlir/lib/Dialect/Affine/Transforms/DecomposeAffineOps.cpp

@@ -88,8 +88,8 @@ static AffineApplyOp createSubApply(RewriterBase &rewriter,
   auto rhsMap = AffineMap::get(m.getNumDims(), m.getNumSymbols(), expr, ctx);
   SmallVector<Value> rhsOperands = originalOp->getOperands();
   canonicalizeMapAndOperands(&rhsMap, &rhsOperands);
-  return rewriter.create<AffineApplyOp>(originalOp.getLoc(), rhsMap,
-                                        rhsOperands);
+  return AffineApplyOp::create(rewriter, originalOp.getLoc(), rhsMap,
+                               rhsOperands);
 }
 
 FailureOr<AffineApplyOp> mlir::affine::decompose(RewriterBase &rewriter,
@@ -160,8 +160,8 @@ FailureOr<AffineApplyOp> mlir::affine::decompose(RewriterBase &rewriter,
   auto current = createSubApply(rewriter, op, subExpressions[0]);
   for (int64_t i = 1, e = subExpressions.size(); i < e; ++i) {
     Value tmp = createSubApply(rewriter, op, subExpressions[i]);
-    current = rewriter.create<AffineApplyOp>(op.getLoc(), binMap,
-                                             ValueRange{current, tmp});
+    current = AffineApplyOp::create(rewriter, op.getLoc(), binMap,
+                                    ValueRange{current, tmp});
     LLVM_DEBUG(DBGS() << "--reassociate into: " << current << "\n");
   }
 

mlir/lib/Dialect/Affine/Transforms/LoopFusion.cpp

@@ -424,7 +424,7 @@ static Value createPrivateMemRef(AffineForOp forOp,
   // consumer loop nests to reduce their live range. Currently they are added
   // at the beginning of the block, because loop nests can be reordered
   // during the fusion pass.
-  Value newMemRef = top.create<memref::AllocOp>(forOp.getLoc(), newMemRefType);
+  Value newMemRef = memref::AllocOp::create(top, forOp.getLoc(), newMemRefType);
 
   // Build an AffineMap to remap access functions based on lower bound offsets.
   SmallVector<AffineExpr, 4> remapExprs;