make 'abcd op 1b11' broadcast support cuda

modules/dnn/perf/perf_layer.cpp

@@ -66,8 +66,13 @@ struct Layer_NaryEltwise : public TestBaseWithParam<tuple<Backend, Target> >
 
         if (!isRef && backendId == DNN_BACKEND_CUDA)
         {
-            if (a_shape != b_shape)
-                throw SkipTestException("The test is skipped because inputs with different shapes are not supported.");
+            if (a_shape.size() != b_shape.size())
+                throw SkipTestException("The test is skipped because inputs with different shape size are not supported.");
+
+            for(int i = 0; i < a_shape.size(); i++)
+                if (a_shape[i] != b_shape[i] && a_shape[i] != 1 && b_shape[i] != 1)
+                    throw SkipTestException("The test is skipped because inputs are not supported.");
+
             if (nary_eltwise_cuda_deny_ops.find(op) != nary_eltwise_cuda_deny_ops.end())
                 throw SkipTestException("The operator '" + op + "' is skipped because is not support with cuda currently.");
         }
@@ -215,6 +220,11 @@ PERF_TEST_P_(Layer_NaryEltwise, NHWC_C)
     test_layer({N, H, W, C}, {1, C}, "sum");
 }
 
+PERF_TEST_P_(Layer_NaryEltwise, NHWC_H)
+{
+    test_layer({N, H, W, C}, {1, H, 1, 1}, "sum");
+}
+
 PERF_TEST_P_(Layer_Slice, YOLOv4_tiny_1)
 {
     const int inputShape[4] = {1, 64, 104, 104};

modules/dnn/src/layers/nary_eltwise_layers.cpp

@@ -673,12 +673,17 @@ public:
     {
         auto context = reinterpret_cast<csl::CSLContext*>(context_);
 
-        auto input_wrapper = inputs[0].dynamicCast<CUDABackendWrapper>();
+        auto input_0_shape = inputs[0].dynamicCast<CUDABackendWrapper>()->getShape();
         for (int i = 1; i < inputs.size(); i++)
         {
-            auto from_wrapper = inputs[i].dynamicCast<CUDABackendWrapper>();
-            if (input_wrapper->getShape() != from_wrapper->getShape())
+            auto input_i_shape = inputs[i].dynamicCast<CUDABackendWrapper>()->getShape();
+            if (input_0_shape.size() != input_i_shape.size())
                 return Ptr<BackendNode>();
+            // check if the shape can be supported by `eltwise_ops.cu`, or return the default BackendNode
+            for (int j = 0; j < input_0_shape.size(); j++)
+                if (input_0_shape[j] != input_i_shape[j] &&
+                    input_0_shape[j] != 1 && input_i_shape[j] != 1)
+                    return Ptr<BackendNode>();
         }
 
         cuda4dnn::EltwiseOpType op_ = cuda4dnn::EltwiseOpType::SUM;