Samsung Exynos AI LiteCore - Samsung Backend in test suite of ExecuTorch (pytorch#22583)

### Summary

Release notes: TestSuite

The Samsung Exynos backend in TestSuite of ExecuTorch can be verfied and
it was passed Testsuite for E9955/E9965 SoCs.



### Test plan
pytest -c /dev/nul backends/test/suite/operators/test_add.py -m
backend_samsung -vs --html=./report/add_report.html
pytest -c /dev/nul backends/test/suite/models/ -m backend_samsung
--html=./report/samsung_models.html

cc @SS-JIA @digantdesai @kimishpatel

---------

Signed-off-by: Jiseong Oh <jiseong.oh@samsung.com>
Signed-off-by: jiseong.oh <jiseong.oh@samsung.com>
Co-authored-by: Guochao Yang <guochao.yang@samsung.com>
Co-authored-by: Jingya Zhang <jingya.zhang@samsung.com>

Author: 3 people

backends/samsung/_passes/remove_useless_ops.py

@@ -15,7 +15,6 @@ class RemoveUselessOpPass(ExportPass):
     USELESS_OP_SET = {
         exir_ops.edge.aten._to_copy.default,
         exir_ops.edge.aten.clone.default,
-        exir_ops.edge.aten.clone.default,
         exir_ops.edge.aten.alias.default,
         exir_ops.edge.aten.lift_fresh_copy.default,
         exir_ops.edge.dim_order_ops._to_dim_order_copy.default,

backends/samsung/_passes/replace_scalar_ops.py

@@ -38,9 +38,16 @@ def call_operator(
         if op not in self._ops_with_scalar:
             return super().call_operator(op, args, kwargs, meta)
 
+        # For pow operation, convert int scalar to float32 tensor
+        # because the PowVisitor requires both inputs to be float32
+        if op == exir_ops.edge.aten.pow.Tensor_Scalar and isinstance(args[1], int):
+            args1 = torch.tensor(float(args[1]), dtype=torch.float32)
+        else:
+            args1 = torch.tensor(args[1])
+
         return super().call_operator(
             op=self._ops_with_scalar.get(op, op),
-            args=(args[0], torch.tensor(args[1])),
+            args=(args[0], args1),
             kwargs=kwargs,
             meta=meta,
         )

backends/samsung/builders/__init__.py

@@ -18,6 +18,7 @@
     op_dequantize,
     op_div,
     op_embedding,
+    op_exp,
     op_expand_copy,
     op_gelu,
     op_getitem,
@@ -48,6 +49,7 @@
     op_select,
     op_sigmoid,
     op_sin,
+    op_skip,
     op_slice_copy,
     op_softmax,
     op_split_with_sizes_copy,
@@ -77,6 +79,7 @@
     op_dequantize,
     op_div,
     op_embedding,
+    op_exp,
     op_expand_copy,
     op_gelu,
     op_getitem,
@@ -107,6 +110,7 @@
     op_select,
     op_sigmoid,
     op_sin,
+    op_skip,
     op_slice_copy,
     op_softmax,
     op_split_with_sizes_copy,

backends/samsung/builders/node_visitor.py

@@ -31,7 +31,7 @@ def __init__(self, exported_program: ExportedProgram) -> None:
     def exported_program(self) -> ExportedProgram:
         return self._exported_program
 
-    def define_node(self, node: torch.fx.Node, enn_graph: EnnGraph):
+    def define_node(self, node: torch.fx.Node, enn_graph: EnnGraph) -> bool:
         raise NotImplementedError("NodeVisitor must be extended!")
 
     def define_tensor(
@@ -58,7 +58,9 @@ def define_tensor(
         if is_param_node(self.exported_program, node):
             if swap_nc_for_weights:
                 tensor = torch.swapdims(tensor, 0, 1)
-            const_data = tensor.contiguous().detach().numpy()
+            if not isinstance(tensor, torch._subclasses.fake_tensor.FakeTensor):
+                # .numpy() is not supported for tensor subclasses if the tensor is a fake tensor.
+                const_data = tensor.contiguous().detach().numpy()
 
         dims = [1] if len(tensor.size()) == 0 else list(tensor.size())
 

backends/samsung/builders/op_add.py

@@ -4,6 +4,7 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+import logging
 from typing import Dict
 
 import torch
@@ -26,16 +27,22 @@ def define_node(
         node: torch.fx.Node,
         enn_graph: EnnGraph,
         vals_to_ids: Dict[torch.Tensor, int],
-    ) -> None:
+    ) -> bool:
         input1 = node.args[0]
         input_id_1 = self.define_tensor(input1, enn_graph, vals_to_ids)
         params = {}
         self._update_params_qdtype(node, params)
         input2 = node.args[1]
         input_id_2 = self.define_tensor(input2, enn_graph, vals_to_ids)
+        alpha = node.kwargs.get("alpha", 1.0)
+        if alpha != 1.0:
+            logging.warning("Currently, only alpha 1 for add is supported.")
+            return False
 
         output_id = self.define_tensor(node, enn_graph, vals_to_ids)
 
         enn_graph.define_op(
             node.name, "ELTSUM", [input_id_1, input_id_2], [output_id], params
         )
+
+        return True

backends/samsung/builders/op_avg_pool2d.py

@@ -26,7 +26,7 @@ def define_node(
         node: torch.fx.Node,
         enn_graph: EnnGraph,
         vals_to_ids: Dict[torch.Tensor, int],
-    ) -> None:
+    ) -> bool:
         input = node.args[0]
         input_id = self.define_tensor(input, enn_graph, vals_to_ids)
 
@@ -52,10 +52,6 @@ def define_node(
         params["explicit_padding"] = explicit_padding
         self._update_params_qdtype(node, params)
 
-        if len(node.args) > 4:
-            ceil_mode = cast(bool, node.args[4])
-            assert not ceil_mode, "Not support ceil_mode = True."
-
         if len(node.args) > 5:
             params["count_include_pad"] = cast(bool, node.args[5])
         else:
@@ -68,3 +64,5 @@ def define_node(
             ), "Not supported divisor_override which is not equal to pooling region."
         output_id = self.define_tensor(node, enn_graph, vals_to_ids)
         enn_graph.define_op(node.name, "AVGPOOL2D", [input_id], [output_id], params)
+
+        return True

backends/samsung/builders/op_batch_norm.py

@@ -25,7 +25,16 @@ def define_node(
         node: torch.fx.Node,
         enn_graph: EnnGraph,
         vals_to_ids: Dict[torch.Tensor, int],
-    ) -> None:
+    ) -> bool:
+        index_zero_getitems = []
+        for user in node.users.keys():
+            if user.target.__name__ != "getitem":
+                continue
+            if user.args[1] == 0:
+                index_zero_getitems.append(user)
+            elif len(user.users) > 0:
+                return False
+
         all_input_tensors = []
         input = node.args[0]
         input_id = self.define_tensor(input, enn_graph, vals_to_ids)
@@ -51,6 +60,11 @@ def define_node(
 
         output_id = self.define_tensor(node, enn_graph, vals_to_ids, output_idx=0)
 
+        for getitem in index_zero_getitems:
+            vals_to_ids[getitem] = output_id
+
         enn_graph.define_op(
             node.name, "BatchNormalization", all_input_tensors, [output_id], params
         )
+
+        return True

backends/samsung/builders/op_bmm.py

@@ -26,7 +26,7 @@ def define_node(
         node: torch.fx.Node,
         enn_graph: EnnGraph,
         vals_to_ids: Dict[torch.Tensor, int],
-    ) -> None:
+    ) -> bool:
         input1 = node.args[0]
         input_id_1 = self.define_tensor(input1, enn_graph, vals_to_ids)
 
@@ -41,3 +41,5 @@ def define_node(
         enn_graph.define_op(
             node.name, "BATCH_MATMUL", [input_id_1, input_id_2], [output_id], params
         )
+
+        return True

backends/samsung/builders/op_cat.py

@@ -28,7 +28,7 @@ def define_node(
         node: torch.fx.Node,
         enn_graph: EnnGraph,
         vals_to_ids: Dict[torch.Tensor, int],
-    ) -> None:
+    ) -> bool:
         tensors = cast(List[torch.fx.Node], node.args[0])
         input_tensor_ids = []
         constant_idx = None
@@ -48,3 +48,5 @@ def define_node(
 
         output_id = self.define_tensor(node, enn_graph, vals_to_ids)
         enn_graph.define_op(node.name, "CONCAT", input_tensor_ids, [output_id], params)
+
+        return True

backends/samsung/builders/op_clamp.py

@@ -4,13 +4,15 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
+import logging
 from typing import cast, Dict
 
 import torch
 from executorch.backends.samsung.builders.node_visitor import (
     NodeVisitor,
     register_node_visitor,
 )
+from executorch.backends.samsung.builders.utils import get_tensor
 from executorch.backends.samsung.serialization.enn_graph_schema import EnnGraph
 
 
@@ -26,9 +28,13 @@ def define_node(
         node: torch.fx.Node,
         enn_graph: EnnGraph,
         vals_to_ids: Dict[torch.Tensor, int],
-    ) -> None:
+    ) -> bool:
         input = node.args[0]
         input_id = self.define_tensor(input, enn_graph, vals_to_ids)
+        input_tensor = get_tensor(self.exported_program, input)
+        if input_tensor.dtype == torch.int64:
+            logging.warning("Currently, int64 clip is unsupported!")
+            return False
 
         # The default value of lower bound and upper bound
         output_min = torch.finfo(torch.float32).min
@@ -45,3 +51,5 @@ def define_node(
         output_id = self.define_tensor(node, enn_graph, vals_to_ids)
 
         enn_graph.define_op(node.name, "CLIP", [input_id], [output_id], params)
+
+        return True