Fix compile

paddle/framework/CMakeLists.txt

@@ -5,7 +5,11 @@ cc_library(ddim SRCS ddim.cc DEPS eigen3)
 cc_test(ddim_test SRCS ddim_test.cc DEPS ddim)
 nv_test(dim_test SRCS dim_test.cu DEPS ddim)
 
-cc_library(tensor SRCS tensor.cc DEPS ddim place paddle_memory device_context)
+if (WITH_GPU)
+  nv_binary(tensor SRCS tensor.cc tensor_util.cu DEPS ddim place paddle_memory device_context)
+else()
+  cc_library(tensor SRCS tensor.cc tensor_util.cc DEPS ddim place paddle_memory device_context)
+endif ()
 
 cc_test(tensor_test SRCS tensor_test.cc DEPS tensor)
 cc_test(tensor_util_test SRCS tensor_util_test.cc DEPS tensor)

paddle/framework/tensor_util.cc

+/* Copyright (c) 2016 PaddlePaddle 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 "paddle/framework/tensor_util.h"
+
+namespace paddle {
+namespace framework {
+template <typename Predicate, typename DevCtx>
+struct AnyDTypeVisitor {
+  Predicate predicate_;
+  const Tensor& tensor_;
+  const DevCtx& ctx_;
+  Tensor* out_;
+
+  AnyDTypeVisitor(Predicate predicate, const Tensor& tensor, const DevCtx& ctx,
+                  Tensor* out)
+      : predicate_(predicate), tensor_(tensor), ctx_(ctx), out_(out) {}
+
+  template <typename T>
+  void operator()() const {
+    auto t = EigenVector<T>::Flatten(tensor_);
+    auto o = EigenScalar<bool>::From(*out_);
+    o.device(*ctx_.eigen_device()) = predicate_(t).any();
+  }
+};
+
+template <typename Predicate, typename DevCtx>
+inline void AnyImpl(Predicate predicate, const framework::Tensor& tensor,
+                    const DevCtx& ctx, framework::Tensor* out) {
+  VisitDataType(ToDataType(tensor.type()), AnyDTypeVisitor<Predicate, DevCtx>(
+                                               predicate, tensor, ctx, out));
+}
+
+template <typename Predicate>
+struct AnyVisitor : public boost::static_visitor<bool> {
+  const framework::Tensor& tensor_;
+  Predicate predicate_;
+
+  AnyVisitor(const framework::Tensor& tensor, Predicate predicate)
+      : tensor_(tensor), predicate_(std::move(predicate)) {}
+
+  template <typename Place>
+  bool operator()(const Place& place) const {
+    framework::Tensor out;
+    out.Resize({1});
+    out.mutable_data<bool>(place);
+    auto* ctx = platform::DeviceContextPool::Instance().GetByPlace(place);
+    AnyImpl(predicate_, tensor_, *ctx, &out);
+    return this->GetResult(out, place);
+  }
+
+  bool GetResult(const framework::Tensor& out,
+                 const platform::CUDAPlace& gpu) const {
+    platform::CPUPlace cpu;
+    framework::Tensor tmp;
+    tmp.Resize({1});
+    tmp.mutable_data<bool>(cpu);
+    platform::DeviceContextPool::Instance().Get(gpu)->Wait();
+    CopyFrom(out, cpu, &tmp);
+    platform::DeviceContextPool::Instance().Get(gpu)->Wait();
+    return GetResult(tmp, cpu);
+  }
+
+  bool GetResult(const framework::Tensor& out,
+                 const platform::CPUPlace& cpu) const {
+    return *out.data<bool>();
+  }
+};
+
+template <typename Predicate>
+inline bool Any(const framework::Tensor& tensor, Predicate predicate) {
+  AnyVisitor<Predicate> visitor(tensor, predicate);
+  auto place = tensor.place();
+  return platform::VisitPlace(place, visitor);
+}
+
+struct HasNANPredicate {
+  template <typename T>
+  auto operator()(const T& eigen_vec) const
+      -> decltype(std::declval<T>().isnan()) {
+    return eigen_vec.isnan();
+  }
+};
+
+bool HasNAN(const framework::Tensor& tensor) {
+  HasNANPredicate predicate;
+  return Any(tensor, predicate);
+}
+
+struct HasInfPredicate {
+  template <typename T>
+  auto operator()(const T& eigen_vec) const
+      -> decltype(std::declval<T>().isinf()) {
+    return eigen_vec.isinf();
+  }
+};
+
+bool HasInf(const framework::Tensor& tensor) {
+  HasInfPredicate predicate;
+  return Any(tensor, predicate);
+}
+
+}  // namespace framework
+}  // namespace paddle

paddle/framework/tensor_util.cu

+./tensor_util.cc
\ No newline at end of file

paddle/framework/tensor_util.h

@@ -208,100 +208,8 @@ inline void CopyToVector(const Tensor& src, std::vector<T>* dst) {
                src_ptr, size);
 }
 
-template <typename Predicate, typename DevCtx>
-struct AnyDTypeVisitor {
-  Predicate predicate_;
-  const Tensor& tensor_;
-  const DevCtx& ctx_;
-  Tensor* out_;
-
-  AnyDTypeVisitor(Predicate predicate, const Tensor& tensor, const DevCtx& ctx,
-                  Tensor* out)
-      : predicate_(predicate), tensor_(tensor), ctx_(ctx), out_(out) {}
-
-  template <typename T>
-  void operator()() const {
-    auto t = EigenVector<T>::Flatten(tensor_);
-    auto o = EigenScalar<bool>::From(*out_);
-    o.device(*ctx_.eigen_device()) = predicate_(t).any();
-  }
-};
-
-template <typename Predicate, typename DevCtx>
-inline void AnyImpl(Predicate predicate, const framework::Tensor& tensor,
-                    const DevCtx& ctx, framework::Tensor* out) {
-  VisitDataType(ToDataType(tensor.type()), AnyDTypeVisitor<Predicate, DevCtx>(
-                                               predicate, tensor, ctx, out));
-}
-
-template <typename Predicate>
-struct AnyVisitor : public boost::static_visitor<bool> {
-  const framework::Tensor& tensor_;
-  Predicate predicate_;
-
-  AnyVisitor(const framework::Tensor& tensor, Predicate predicate)
-      : tensor_(tensor), predicate_(std::move(predicate)) {}
-
-  template <typename Place>
-  bool operator()(const Place& place) const {
-    framework::Tensor out;
-    out.Resize({1});
-    out.mutable_data<bool>(place);
-    auto* ctx = platform::DeviceContextPool::Instance().GetByPlace(place);
-    AnyImpl(predicate_, tensor_, *ctx, &out);
-    return this->GetResult(out, place);
-  }
-
-  bool GetResult(const framework::Tensor& out,
-                 const platform::CUDAPlace& gpu) const {
-    platform::CPUPlace cpu;
-    framework::Tensor tmp;
-    tmp.Resize({1});
-    tmp.mutable_data<bool>(cpu);
-    platform::DeviceContextPool::Instance().Get(gpu)->Wait();
-    CopyFrom(out, cpu, &tmp);
-    platform::DeviceContextPool::Instance().Get(gpu)->Wait();
-    return GetResult(tmp, cpu);
-  }
-
-  bool GetResult(const framework::Tensor& out,
-                 const platform::CPUPlace& cpu) const {
-    return *out.data<bool>();
-  }
-};
-
-template <typename Predicate>
-inline bool Any(const framework::Tensor& tensor, Predicate predicate) {
-  AnyVisitor<Predicate> visitor(tensor, predicate);
-  auto place = tensor.place();
-  return platform::VisitPlace(place, visitor);
-}
-
-struct HasNANPredicate {
-  template <typename T>
-  auto operator()(const T& eigen_vec) const
-      -> decltype(std::declval<T>().isnan()) {
-    return eigen_vec.isnan();
-  }
-};
-
-inline bool HasNAN(const framework::Tensor& tensor) {
-  HasNANPredicate predicate;
-  return Any(tensor, predicate);
-}
-
-struct HasInfPredicate {
-  template <typename T>
-  auto operator()(const T& eigen_vec) const
-      -> decltype(std::declval<T>().isinf()) {
-    return eigen_vec.isinf();
-  }
-};
-
-inline bool HasInf(const framework::Tensor& tensor) {
-  HasInfPredicate predicate;
-  return Any(tensor, predicate);
-}
+extern bool HasNAN(const framework::Tensor& tensor);
+extern bool HasInf(const framework::Tensor& tensor);
 
 }  // namespace framework
 }  // namespace paddle