Split cwise_op_equal_to, cwise_op_not_equal, cwise_op_add, and cwise_op_mul

into two files each, to improve compilation times.

Remove the REGISTER10, REGISTER11, REGISTER12 macros; with that many types,
we'll want to shard into instead.
Change: 134616712

1 files changed, 37 insertions, 0 deletions

diff --git a/tensorflow/core/kernels/cwise_op_mul_1.cc b/tensorflow/core/kernels/cwise_op_mul_1.cc
new file mode 100644
index 0000000000..09e9f070da
--- /dev/null
+++ b/tensorflow/core/kernels/cwise_op_mul_1.cc
@@ -0,0 +1,37 @@
+/* Copyright 2015 The TensorFlow Authors. All Rights Reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+==============================================================================*/
+
+#include "tensorflow/core/kernels/cwise_ops_common.h"
+
+namespace tensorflow {
+
+REGISTER5(BinaryOp, CPU, "Mul", functor::mul, float, Eigen::half, double,
+          uint8, int32);
+#if GOOGLE_CUDA
+REGISTER4(BinaryOp, GPU, "Mul", functor::mul, float, Eigen::half, double,
+           uint8);
+// A special GPU kernel for int32.
+// TODO(b/25387198): Also enable int32 in device memory. This kernel
+// registration requires all int32 inputs and outputs to be in host memory.
+REGISTER_KERNEL_BUILDER(Name("Mul")
+                            .Device(DEVICE_GPU)
+                            .HostMemory("x")
+                            .HostMemory("y")
+                            .HostMemory("z")
+                            .TypeConstraint<int32>("T"),
+                        BinaryOp<CPUDevice, functor::mul<int32>>);
+#endif
+
+}  // namespace tensorflow