Populate cadence cpu ops (#7165)

Summary:
quantized ops in CPU flow are not fully migrated. Adding them all in this PR
- quantized_linear_per_tensor_out


Test Plan: python3 -m examples.cadence.operators.quantized_linear_op

Reviewed By: hsharma35, mcremon-meta

Differential Revision: D66726864

Pulled By: zonglinpeng

Author: Zonglin Peng

backends/cadence/aot/functions.yaml

@@ -183,3 +183,18 @@
   kernels:
     - arg_meta: null
       kernel_name: impl::reference::quantized_matmul_out
+
+- func: cadence::quantized_linear.per_tensor_out(Tensor src, Tensor weight, Tensor bias, SymInt src_zero_point, SymInt weight_zero_point, SymInt out_multiplier, SymInt out_shift, SymInt out_zero_point, Tensor? offset, *, Tensor(a!) out) -> Tensor(a!)
+  kernels:
+    - arg_meta: null
+      kernel_name: impl::reference::quantized_linear_per_tensor_out
+
+- func: cadence::im2row.out(Tensor input, int[2] kernel_size, int[2] dilation, int[2] padding, int[2] stride, Tensor in_zero_point, bool channel_last=False, *, Tensor(a!) out) -> Tensor(a!)
+  kernels:
+    - arg_meta: null
+      kernel_name: impl::reference::im2row_out
+
+- func: cadence::quantized_conv.per_tensor_out(Tensor input, Tensor weight, Tensor bias, int[] stride, SymInt[] padding, int[] dilation, int groups, int input_zero_point, int weight_zero_point, float bias_scale, float out_scale, int out_zero_point, int out_multiplier, int out_shift, bool channel_last=False, *, Tensor(a!) out) -> Tensor(a!)
+  kernels:
+    - arg_meta: null
+      kernel_name: impl::reference::quantized_conv_per_tensor_out

backends/cadence/reference/operators/CMakeLists.txt

@@ -55,6 +55,7 @@ set(_aten_ops__srcs
     "${EXECUTORCH_ROOT}/kernels/portable/cpu/op_expand_copy.cpp"
     "${EXECUTORCH_ROOT}/kernels/portable/cpu/op_gelu.cpp"
     "${EXECUTORCH_ROOT}/kernels/portable/cpu/op_empty.cpp"
+    "${EXECUTORCH_ROOT}/kernels/portable/cpu/util/dtype_util.cpp"
 )
 add_library(aten_ops_cadence ${_aten_ops__srcs})
 target_link_libraries(aten_ops_cadence PUBLIC executorch)
@@ -72,12 +73,13 @@ target_include_directories(
 add_library(
   custom_ops
   "quantized_linear_out.cpp"
-  "quantized_conv_out.cpp"
   "quantized_relu_out.cpp"
   "quantized_layer_norm.cpp"
   "quantize_per_tensor.cpp"
   "dequantize_per_tensor.cpp"
   "quantized_matmul_out.cpp"
+  "im2row_out.cpp"
+  "convolution_out.cpp"
 )
 target_include_directories(
   custom_ops PUBLIC ${ROOT_DIR}/.. ${CMAKE_BINARY_DIR}