diff --git a/mlir/include/mlir/Conversion/AffineToStandard/AffineToStandard.h b/mlir/include/mlir/Conversion/AffineToStandard/AffineToStandard.h
--- a/mlir/include/mlir/Conversion/AffineToStandard/AffineToStandard.h
+++ b/mlir/include/mlir/Conversion/AffineToStandard/AffineToStandard.h
@@ -15,6 +15,7 @@
 class AffineExpr;
 class AffineForOp;
 class AffineMap;
+class AffineParallelOp;
 class Location;
 struct LogicalResult;
 class MLIRContext;
diff --git a/mlir/lib/Conversion/AffineToStandard/AffineToStandard.cpp b/mlir/lib/Conversion/AffineToStandard/AffineToStandard.cpp
--- a/mlir/lib/Conversion/AffineToStandard/AffineToStandard.cpp
+++ b/mlir/lib/Conversion/AffineToStandard/AffineToStandard.cpp
@@ -357,6 +357,36 @@
   }
 };
 
+/// Convert an "affine.parallel" (loop nest) operation into a "scf.parallel"
+/// operation.
+class AffineParallelLowering : public OpRewritePattern<AffineParallelOp> {
+public:
+  using OpRewritePattern<AffineParallelOp>::OpRewritePattern;
+
+  LogicalResult matchAndRewrite(AffineParallelOp op,
+                                PatternRewriter &rewriter) const override {
+    Location loc = op.getLoc();
+    SmallVector<Value, 4> steps;
+    SmallVector<Value, 4> upperBound;
+    SmallVector<Value, 4> lowerBound;
+    upperBound = *expandAffineMap(rewriter, loc, op.upperBoundsMap(),
+                                  op.getUpperBoundsOperands());
+    lowerBound = *expandAffineMap(rewriter, loc, op.lowerBoundsMap(),
+                                  op.getLowerBoundsOperands());
+    for (unsigned i = 0, e = op.steps().size(); i < e; ++i) {
+      steps.push_back(rewriter.create<ConstantIndexOp>(
+          loc, op.steps()[i].cast<IntegerAttr>().getInt()));
+    }
+    auto parallelOp =
+        rewriter.create<scf::ParallelOp>(loc, lowerBound, upperBound, steps);
+    rewriter.eraseBlock(parallelOp.getBody());
+    rewriter.inlineRegionBefore(op.region(), parallelOp.region(),
+                                parallelOp.region().end());
+    rewriter.eraseOp(op);
+    return success();
+  }
+};
+
 class AffineIfLowering : public OpRewritePattern<AffineIfOp> {
 public:
   using OpRewritePattern<AffineIfOp>::OpRewritePattern;
@@ -615,6 +645,7 @@
       AffineLoadLowering,
       AffineMinLowering,
       AffineMaxLowering,
+      AffineParallelLowering,
       AffinePrefetchLowering,
       AffineStoreLowering,
       AffineForLowering,
diff --git a/mlir/test/Conversion/AffineToStandard/lower-affine.mlir b/mlir/test/Conversion/AffineToStandard/lower-affine.mlir
--- a/mlir/test/Conversion/AffineToStandard/lower-affine.mlir
+++ b/mlir/test/Conversion/AffineToStandard/lower-affine.mlir
@@ -620,3 +620,19 @@
   %0 = affine.max affine_map<(d0,d1) -> (d0 - d1, d1 - d0)>(%arg0, %arg1)
   return %0 : index
 }
+
+// CHECK-LABEL: func @dot(
+// CHECK-SAME: %[[ARG0:.*]]: memref<100x100xf32>, %[[ARG1:.*]]: memref<100x100xf32>) {
+func @dot(%o: memref<100x100xf32>, %a: memref<100x100xf32>) {
+  affine.parallel (%i, %j) = (0, 0) to (100, 100) {
+  }
+  return
+}
+
+// CHECK-DAG:    %[[C100:.*]] = constant 100
+// CHECK-DAG:    %[[C100_1:.*]] = constant 100
+// CHECK-DAG:    %[[C0:.*]] = constant 0
+// CHECK-DAG:    %[[C0_1:.*]] = constant 0
+// CHECK-DAG:    %[[C1:.*]] = constant 1
+// CHECK-DAG:    %[[C1_1:.*]] = constant 1
+// CHECK-DAG:    scf.parallel (%arg2, %arg3) = (%[[C0]], %[[C0_1]]) to (%[[C100]], %[[C100_1]]) step (%[[C1]], %[[C1_1]]) {