diff --git a/mlir/lib/Dialect/Tensor/Transforms/Bufferize.cpp b/mlir/lib/Dialect/Tensor/Transforms/Bufferize.cpp
--- a/mlir/lib/Dialect/Tensor/Transforms/Bufferize.cpp
+++ b/mlir/lib/Dialect/Tensor/Transforms/Bufferize.cpp
@@ -59,6 +59,19 @@
   }
 };
 
+struct BufferizeInsertOp : public OpConversionPattern<tensor::InsertOp> {
+  using OpConversionPattern::OpConversionPattern;
+  LogicalResult
+  matchAndRewrite(tensor::InsertOp op, OpAdaptor adaptor,
+                  ConversionPatternRewriter &rewriter) const override {
+
+    rewriter.create<memref::StoreOp>(op.getLoc(), adaptor.scalar(),
+                                     adaptor.dest(), adaptor.indices());
+    rewriter.replaceOp(op, {adaptor.dest()});
+    return success();
+  }
+};
+
 struct BufferizeFromElementsOp
     : public OpConversionPattern<tensor::FromElementsOp> {
 public:
@@ -208,7 +221,7 @@
                                       StandardOpsDialect>(
         [&](Operation *op) { return typeConverter.isLegal(op); });
     target.addLegalOp<CallOp, ReturnOp>();
-    target.addIllegalOp<tensor::CastOp, tensor::ExtractOp,
+    target.addIllegalOp<tensor::CastOp, tensor::ExtractOp, tensor::InsertOp,
                         tensor::FromElementsOp, tensor::GenerateOp>();
     bufferization::populateBufferizeMaterializationLegality(target);
 
@@ -226,8 +239,8 @@
     bufferization::BufferizeTypeConverter &typeConverter,
     RewritePatternSet &patterns) {
   patterns.add<BufferizeCastOp, BufferizeDimOp, BufferizeExtractOp,
-               BufferizeFromElementsOp, BufferizeGenerateOp, BufferizeRankOp>(
-      typeConverter, patterns.getContext());
+               BufferizeInsertOp, BufferizeFromElementsOp, BufferizeGenerateOp,
+               BufferizeRankOp>(typeConverter, patterns.getContext());
 }
 
 std::unique_ptr<Pass> mlir::createTensorBufferizePass() {
diff --git a/mlir/test/Dialect/Tensor/bufferize.mlir b/mlir/test/Dialect/Tensor/bufferize.mlir
--- a/mlir/test/Dialect/Tensor/bufferize.mlir
+++ b/mlir/test/Dialect/Tensor/bufferize.mlir
@@ -242,3 +242,17 @@
   } : tensor<?xindex>
   return %tensor : tensor<?xindex>
 }
+
+// CHECK-LABEL:  func @tensor.insert(
+// CHECK-SAME:              %[[TENSOR:.*]]: tensor<?xf32>,
+// CHECK-SAME:              %[[ELEM_VAL:.*]]: f32,
+// CHECK-SAME:              %[[IDX:.*]]: index) -> tensor<?xf32> {
+// CHECK:       %[[MEMREF:.*]] = bufferization.to_memref %[[TENSOR]] : memref<?xf32>
+// CHECK:       memref.store %[[ELEM_VAL]], %[[MEMREF]][%[[IDX]]] : memref<?xf32>
+// CHECK:       %[[RET:.*]] = bufferization.to_tensor %[[MEMREF]] : memref<?xf32>
+// CHECK:       return %[[RET]] : tensor<?xf32>
+// CHECK:  }
+func @tensor.insert(%arg0: tensor<?xf32>, %arg1: f32, %arg2: index) -> tensor<?xf32> {
+  %0 = tensor.insert %arg1 into %arg0[%arg2] : tensor<?xf32>
+  return %0 : tensor<?xf32>
+}