Merge branch 'windows/build' into windows/online

CMakeLists.txt

@@ -130,6 +130,11 @@ if (APPLE OR WIN32)
         "Disable MKL for building on mac and windows" FORCE)
 endif()
 
+if (WIN32)
+    set(WITH_AVX OFF CACHE STRING
+            "Disable AVX when compiling for Windows" FORCE)
+endif()
+
 set(THIRD_PARTY_PATH "${CMAKE_BINARY_DIR}/third_party" CACHE STRING
   "A path setting third party libraries download & build directories.")
 

cmake/operators.cmake

@@ -85,9 +85,7 @@ function(op_library TARGET)
     if (WIN32)
     # remove windows unsupported op, because windows has no nccl, no warpctc such ops.
     foreach(windows_unsupport_op "nccl_op" "gen_nccl_id_op" "warpctc_op"
-#     "hierarchical_sigmoid_op" "cumsum_op"
-#     "crf_decoding_op" "select_op" "lstmp_op" "gru_op" "fusion_gru_op" "lstm_op" "fusion_lstm_op"
-      "fusion_seqconv_eltadd_relu_op" "channel_send_op" "channel_create_op" "channel_close_op" "channel_recv_op")
+            "channel_send_op" "channel_create_op" "channel_close_op" "channel_recv_op")
         if ("${TARGET}" STREQUAL "${windows_unsupport_op}")
           return()
         endif()

cmake/simd.cmake

@@ -70,17 +70,20 @@ int main()
     return 0;
 }" AVX_FOUND)
 
-# Check AVX 2
-set(CMAKE_REQUIRED_FLAGS ${AVX2_FLAG})
-set(AVX2_FOUND_EXITCODE 1 CACHE STRING "Result from TRY_RUN" FORCE)
-CHECK_CXX_SOURCE_RUNS("
-#include <immintrin.h>
-int main()
-{
+# disable AVX2 by default on windows
+if(NOT WIN32)
+    # Check AVX 2
+    set(CMAKE_REQUIRED_FLAGS ${AVX2_FLAG})
+    set(AVX2_FOUND_EXITCODE 1 CACHE STRING "Result from TRY_RUN" FORCE)
+    CHECK_CXX_SOURCE_RUNS("
+    #include <immintrin.h>
+    int main()
+    {
         __m256i a = _mm256_set_epi32 (-1, 2, -3, 4, -1, 2, -3, 4);
         __m256i result = _mm256_abs_epi32 (a);
         return 0;
-}" AVX2_FOUND)
+    }" AVX2_FOUND)
+endif(NOT WIN32)
 
 # Check AVX512F
 set(CMAKE_REQUIRED_FLAGS ${AVX512F_FLAG})

paddle/fluid/operators/CMakeLists.txt

@@ -48,9 +48,9 @@ endif()
 set(COMMON_OP_DEPS "")
 
 set(COMMON_OP_DEPS ${COMMON_OP_DEPS} xxhash selected_rows_functor selected_rows lod_tensor maxouting unpooling pooling lod_rank_table context_project sequence_pooling executor sequence_padding sequence_scale cos_sim_functor memory concat_and_split cross_entropy softmax vol2col im2col sampler)
-set(COMMON_OP_DEPS ${COMMON_OP_DEPS} lstm_compute matrix_bit_code gru_compute activation_functions jit_kernel)
+set(COMMON_OP_DEPS ${COMMON_OP_DEPS} lstm_compute matrix_bit_code sequence2batch gru_compute activation_functions jit_kernel)
 if (NOT WIN32)
-  set(COMMON_OP_DEPS ${COMMON_OP_DEPS} sequence2batch dynload_warpctc)
+  set(COMMON_OP_DEPS ${COMMON_OP_DEPS} dynload_warpctc)
 endif()
 if (WITH_GPU)
   set(COMMON_OP_DEPS ${COMMON_OP_DEPS} depthwise_conv cub)

paddle/fluid/operators/hierarchical_sigmoid_op.h

@@ -111,7 +111,7 @@ class HierarchicalSigmoidGradOpKernel : public framework::OpKernel<T> {
     auto pre_out_mat = EigenMatrix<T>::From(*pre_out);
     auto pre_out_grad_mat = EigenMatrix<T>::From(pre_out_grad);
     auto out_grad_mat = EigenMatrix<T>::From(*out_grad);
-    Eigen::array<int, 2> bcast({{1, static_cast<int>(pre_out_grad.dims()[1])}});
+    Eigen::array<int, 2> bcast{1, static_cast<int>(pre_out_grad.dims()[1])};
 
     // softrelu derivative
     pre_out_grad_mat.device(place) =

paddle/fluid/operators/math/CMakeLists.txt

@@ -81,4 +81,3 @@ if(WITH_XBYAK)
 endif()
 cc_library(jit_kernel SRCS ${JIT_KERNEL_SRCS} DEPS ${JIT_KERNEL_DEPS})
 cc_test(jit_kernel_test SRCS jit_kernel_test.cc DEPS jit_kernel)
-

paddle/fluid/operators/math/matrix_bit_code.h

@@ -67,7 +67,7 @@ inline constexpr size_t FindLastSet(size_t x) {
              : (std::is_same<size_t, unsigned long>::value  // NOLINT
                     ? (x ? 8 * sizeof(x) - __builtin_clzl(x) : 0)
                     : (x ? 8 * sizeof(x) - __builtin_clzll(x) : 0));
-
+}
 #else
 // windows don't have built-in clz, ctz function
 template <typename T>
@@ -92,7 +92,6 @@ inline int clz(const T& value) {
 
 inline size_t FindLastSet(size_t x) { return sizeof(size_t) * 8 - clz(x); }
 #endif  // !_WIN32
-}
 
 struct SimpleCode {
   SimpleCode(size_t code, size_t num_classes) : c_(code + num_classes) {}

python/paddle/fluid/layers/nn.py

@@ -170,12 +170,6 @@ __all__ = [
     'bilinear_tensor_product',
 ]
 
-# To avoid the api checker complains
-if os.name == 'nt':
-    __all__.remove('dynamic_lstm')
-    __all__.remove('crf_decoding')
-    __all__.remove('roi_pool')
-
 
 def fc(input,
        size,
@@ -349,10 +343,8 @@ def embedding(input,
     return tmp
 
 
-if os.name != 'nt':
-
-    @templatedoc(op_type="lstm")
-    def dynamic_lstm(input,
+@templatedoc(op_type="lstm")
+def dynamic_lstm(input,
                  size,
                  h_0=None,
                  c_0=None,
@@ -969,10 +961,8 @@ def linear_chain_crf(input, label, param_attr=None):
     return log_likelihood
 
 
-if os.name != 'nt':
-
-    @templatedoc()
-    def crf_decoding(input, param_attr, label=None):
+@templatedoc()
+def crf_decoding(input, param_attr, label=None):
     """
     ${comment}
 
@@ -998,11 +988,9 @@ if os.name != 'nt':
         dtype=helper.input_dtype())
     helper.append_op(
         type='crf_decoding',
-            inputs={
-                "Emission": [input],
+        inputs={"Emission": [input],
                 "Transition": transition,
-                "Label": label
-            },
+                "Label": label},
         outputs={"ViterbiPath": [viterbi_path]})
 
     return viterbi_path
@@ -5599,14 +5587,8 @@ def label_smooth(label,
     return smooth_label
 
 
-if os.name != 'nt':
-
-    @templatedoc()
-    def roi_pool(input,
-                 rois,
-                 pooled_height=1,
-                 pooled_width=1,
-                 spatial_scale=1.0):
+@templatedoc()
+def roi_pool(input, rois, pooled_height=1, pooled_width=1, spatial_scale=1.0):
     """
     ${comment}
 

python/paddle/fluid/layers/ops.py

@@ -100,12 +100,12 @@ Examples:
     >>> result = fluid.layers.hard_shrink(x=data, threshold=0.3)
 """
 
-if os.name != 'nt':
-    __all__ += ['cumsum']
+__all__ += ['cumsum']
 
-    _cum_sum_ = generate_layer_fn('cumsum')
+_cum_sum_ = generate_layer_fn('cumsum')
 
-    def cumsum(x, axis=None, exclusive=None, reverse=None):
+
+def cumsum(x, axis=None, exclusive=None, reverse=None):
     locals_var = locals().keys()
     kwargs = dict()
     for name in locals_var:
@@ -114,12 +114,13 @@ if os.name != 'nt':
             kwargs[name] = val
     return _cum_sum_(**kwargs)
 
-    cumsum.__doc__ = _cum_sum_.__doc__ + """
-    Examples:
+
+cumsum.__doc__ = _cum_sum_.__doc__ + """
+Examples:
 
     >>> data = fluid.layers.data(name="input", shape=[32, 784])
     >>> result = fluid.layers.cumsum(data, axis=0)
-    """
+"""
 
 __all__ += ['thresholded_relu']
 

python/paddle/fluid/transpiler/details/checkport.py

@@ -34,6 +34,7 @@ def wait_server_ready(endpoints):
     """
     while True:
         all_ok = True
+        not_ready_endpoints = []
         for ep in endpoints:
             ip_port = ep.split(":")
             with closing(socket.socket(socket.AF_INET,
@@ -42,8 +43,11 @@ def wait_server_ready(endpoints):
                 result = sock.connect_ex((ip_port[0], int(ip_port[1])))
                 if result != 0:
                     all_ok = False
+                    not_ready_endpoints.append(ep)
         if not all_ok:
             sys.stderr.write("pserver not ready, wait 3 sec to retry...\n")
+            sys.stderr.write("not ready endpoints:" + str(not_ready_endpoints) +
+                             "\n")
             sys.stderr.flush()
             time.sleep(3)
         else: