Merge pull request #11476 from chengduoZH/enable_more_type_for_SplitOpKernel

Enable more type for SplitOp and ConcatOp

paddle/fluid/operators/concat_op.cc

@@ -107,7 +107,13 @@ REGISTER_OPERATOR(concat, ops::ConcatOp, ops::ConcatOpMaker,
                       false> /* set false to disable empty grad */);
 REGISTER_OPERATOR(concat_grad, ops::ConcatOpGrad);
 REGISTER_OP_CPU_KERNEL(
-    concat, ops::ConcatKernel<paddle::platform::CPUDeviceContext, float>);
+    concat, ops::ConcatKernel<paddle::platform::CPUDeviceContext, double>,
+    ops::ConcatKernel<paddle::platform::CPUDeviceContext, float>,
+    ops::ConcatKernel<paddle::platform::CPUDeviceContext, int64_t>,
+    ops::ConcatKernel<paddle::platform::CPUDeviceContext, int>);
 REGISTER_OP_CPU_KERNEL(
     concat_grad,
-    ops::ConcatGradKernel<paddle::platform::CPUDeviceContext, float>);
+    ops::ConcatGradKernel<paddle::platform::CPUDeviceContext, double>,
+    ops::ConcatGradKernel<paddle::platform::CPUDeviceContext, float>,
+    ops::ConcatGradKernel<paddle::platform::CPUDeviceContext, int64_t>,
+    ops::ConcatGradKernel<paddle::platform::CPUDeviceContext, int>);

paddle/fluid/operators/concat_op.cu.cc

@@ -15,7 +15,13 @@ limitations under the License. */
 #include "paddle/fluid/operators/concat_op.h"
 namespace ops = paddle::operators;
 REGISTER_OP_CUDA_KERNEL(
-    concat, ops::ConcatKernel<paddle::platform::CUDADeviceContext, float>);
+    concat, ops::ConcatKernel<paddle::platform::CUDADeviceContext, double>,
+    ops::ConcatKernel<paddle::platform::CUDADeviceContext, float>,
+    ops::ConcatKernel<paddle::platform::CUDADeviceContext, int64_t>,
+    ops::ConcatKernel<paddle::platform::CUDADeviceContext, int>);
 REGISTER_OP_CUDA_KERNEL(
     concat_grad,
-    ops::ConcatGradKernel<paddle::platform::CUDADeviceContext, float>);
+    ops::ConcatGradKernel<paddle::platform::CUDADeviceContext, double>,
+    ops::ConcatGradKernel<paddle::platform::CUDADeviceContext, float>,
+    ops::ConcatGradKernel<paddle::platform::CUDADeviceContext, int64_t>,
+    ops::ConcatGradKernel<paddle::platform::CUDADeviceContext, int>);

paddle/fluid/operators/split_op.cc

@@ -115,4 +115,7 @@ USE_CPU_ONLY_OP(concat);
 
 REGISTER_OPERATOR(split, ops::SplitOp, ops::SplitOpMaker, ops::SplitGradMaker);
 REGISTER_OP_CPU_KERNEL(split,
-                       ops::SplitOpKernel<paddle::platform::CPUPlace, float>);
+                       ops::SplitOpKernel<paddle::platform::CPUPlace, double>,
+                       ops::SplitOpKernel<paddle::platform::CPUPlace, float>,
+                       ops::SplitOpKernel<paddle::platform::CPUPlace, int64_t>,
+                       ops::SplitOpKernel<paddle::platform::CPUPlace, int>);

paddle/fluid/operators/split_op.cu.cc

@@ -15,4 +15,7 @@ limitations under the License. */
 #include "paddle/fluid/operators/split_op.h"
 namespace ops = paddle::operators;
 REGISTER_OP_CUDA_KERNEL(
-    split, ops::SplitOpKernel<paddle::platform::CUDADeviceContext, float>);
+    split, ops::SplitOpKernel<paddle::platform::CUDADeviceContext, double>,
+    ops::SplitOpKernel<paddle::platform::CUDADeviceContext, float>,
+    ops::SplitOpKernel<paddle::platform::CUDADeviceContext, int64_t>,
+    ops::SplitOpKernel<paddle::platform::CUDADeviceContext, int>);