[static op generation] tril_triu (#54033)

* [phi] autogen code tril_triu

* [phi][api]fix tril_triu_grad args

* [fluid] clean cmake; [phi] fix infer_meta

paddle/fluid/operators/unity_build_rule.cmake

@@ -288,7 +288,6 @@ register_unity_group(
   transpose_op.cc
   mkldnn/transpose_mkldnn_op.cc
   tree_conv_op.cc
-  tril_triu_op.cc
   unbind_op.cc
   unfold_op.cc)
 register_unity_group(

paddle/phi/api/yaml/op_compat.yaml

@@ -2390,6 +2390,13 @@
   outputs :
     out : Out
 
+- op : tril_triu
+  backward : tril_triu_grad
+  inputs :
+    {x: X}
+  outputs :
+    {out : Out}
+
 - op : trilinear_interp (trilinear_interp_v2)
   backward : trilinear_interp_grad (trilinear_interp_v2_grad)
   inputs :

paddle/phi/api/yaml/static_backward.yaml

@@ -65,6 +65,16 @@
     func : softmax_grad
   composite : softmax_grad(out, out_grad, axis, x_grad)
 
+- backward_op : tril_triu_grad
+  forward : tril_triu (Tensor x, int diagonal = 0, bool lower = false)  -> Tensor(out)
+  args : (Tensor out_grad, int diagonal, bool lower)
+  output : Tensor(x_grad)
+  infer_meta :
+      func : UnchangedInferMeta
+      param : [out_grad]
+  kernel:
+    func : tril_triu_grad
+
 - backward_op: unpool_grad
   forward: unpool (Tensor x, Tensor indices, int[] ksize, str unpooling_type, int[] strides = {1,1}, int[] paddings ={0,0} ,IntArray output_size = {0,0}, str data_format="NCHW") -> Tensor(out)
   args: (Tensor x, Tensor indices, Tensor out, Tensor out_grad, int[] ksize, int[] strides, int[] paddings, IntArray output_size, str data_format)

paddle/phi/api/yaml/static_ops.yaml

@@ -356,6 +356,15 @@
     param : [rows, cols, offset, dtype]
     data_type : dtype
 
+- op : tril_triu
+  args : (Tensor x, int diagonal = 0, bool lower = false)
+  output : Tensor(out)
+  infer_meta :
+    func : TrilTriuInferMeta
+  kernel :
+    func : tril_triu
+  backward : tril_triu_grad
+
 - op : triu_indices
   args : (int row = 0, int col = 0, int offset = 0, DataType dtype = DataType::INT64)
   output : Tensor(out)