Remove type dispatch for quantized_conv1d ops

Differential Revision: D95277804

Pull Request resolved: #17939

Author: mcremon-meta

backends/cadence/aot/BUCK

@@ -154,7 +154,8 @@ fbcode_target(_kind = executorch_generated_lib,
         "//executorch/backends/cadence/generic/operators:op_quantize_per_tensor",
         "//executorch/backends/cadence/generic/operators:op_quantized_add",
         "//executorch/backends/cadence/generic/operators:op_quantized_conv2d",
-        "//executorch/backends/cadence/generic/operators:op_quantized_conv1d",
+        "//executorch/backends/cadence/generic/operators:op_quantized_conv1d_ncl",
+        "//executorch/backends/cadence/generic/operators:op_quantized_conv1d_nlc",
         "//executorch/backends/cadence/generic/operators:op_quantized_fully_connected",
         "//executorch/backends/cadence/generic/operators:op_quantized_layer_norm",
         "//executorch/backends/cadence/generic/operators:op_quantized_linear",

backends/cadence/aot/functions.yaml

@@ -359,6 +359,16 @@
     - arg_meta: null
       kernel_name: impl::generic::quantized_conv2d_nhwc_per_tensor_out
 
+- func: cadence::quantized_conv1d_ncl.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, *, Tensor(a!) out) -> Tensor(a!)
+  kernels:
+    - arg_meta: null
+      kernel_name: impl::generic::quantized_conv1d_ncl_per_tensor_out
+
+- func: cadence::quantized_conv1d_nlc.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, *, Tensor(a!) out) -> Tensor(a!)
+  kernels:
+    - arg_meta: null
+      kernel_name: impl::generic::quantized_conv1d_nlc_per_tensor_out
+
 - func: cadence::quantized_conv2d_nchw_asym8sxsym8s_asym8s.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, *, Tensor(a!) out) -> Tensor(a!)
   kernels:
     - arg_meta: null
@@ -419,26 +429,6 @@
     - arg_meta: null
       kernel_name: impl::generic::quantized_conv2d_nhwc_depthwise_asym8uxsym8u_asym8u_per_tensor_out
 
-- func: cadence::quantized_conv1d_ncl_asym8sxsym8s_asym8s.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, *, Tensor(a!) out) -> Tensor(a!)
-  kernels:
-    - arg_meta: null
-      kernel_name: impl::generic::quantized_conv1d_ncl_asym8sxsym8s_asym8s_per_tensor_out
-
-- func: cadence::quantized_conv1d_ncl_asym8uxsym8u_asym8u.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, *, Tensor(a!) out) -> Tensor(a!)
-  kernels:
-    - arg_meta: null
-      kernel_name: impl::generic::quantized_conv1d_ncl_asym8uxsym8u_asym8u_per_tensor_out
-
-- func: cadence::quantized_conv1d_nlc_asym8sxsym8s_asym8s.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, *, Tensor(a!) out) -> Tensor(a!)
-  kernels:
-    - arg_meta: null
-      kernel_name: impl::generic::quantized_conv1d_nlc_asym8sxsym8s_asym8s_per_tensor_out
-
-- func: cadence::quantized_conv1d_nlc_asym8uxsym8u_asym8u.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, *, Tensor(a!) out) -> Tensor(a!)
-  kernels:
-    - arg_meta: null
-      kernel_name: impl::generic::quantized_conv1d_nlc_asym8uxsym8u_asym8u_per_tensor_out
-
 - func: cadence::quantized_fully_connected.out(Tensor src, Tensor weight, Tensor bias, int src_zero_point, Tensor weight_zero_point, Tensor out_multiplier, Tensor out_shift, int out_zero_point, Tensor? offset, *, Tensor(a!) out) -> Tensor(a!)
   kernels:
     - arg_meta: null

backends/cadence/aot/functions_hifi.yaml

@@ -445,26 +445,6 @@
     - arg_meta: null
       kernel_name: impl::HiFi::quantized_conv2d_nhwc_depthwise_asym8uxsym8u_asym8u_per_tensor_out
 
-- func: cadence::quantized_conv1d_ncl_asym8sxsym8s_asym8s.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, *, Tensor(a!) out) -> Tensor(a!)
-  kernels:
-    - arg_meta: null
-      kernel_name: impl::HiFi::quantized_conv1d_ncl_asym8sxsym8s_asym8s_per_tensor_out
-
-- func: cadence::quantized_conv1d_ncl_asym8uxsym8u_asym8u.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, *, Tensor(a!) out) -> Tensor(a!)
-  kernels:
-    - arg_meta: null
-      kernel_name: impl::HiFi::quantized_conv1d_ncl_asym8uxsym8u_asym8u_per_tensor_out
-
-- func: cadence::quantized_conv1d_nlc_asym8sxsym8s_asym8s.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, *, Tensor(a!) out) -> Tensor(a!)
-  kernels:
-    - arg_meta: null
-      kernel_name: impl::HiFi::quantized_conv1d_nlc_asym8sxsym8s_asym8s_per_tensor_out
-
-- func: cadence::quantized_conv1d_nlc_asym8uxsym8u_asym8u.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, *, Tensor(a!) out) -> Tensor(a!)
-  kernels:
-    - arg_meta: null
-      kernel_name: impl::HiFi::quantized_conv1d_nlc_asym8uxsym8u_asym8u_per_tensor_out
-
 - func: cadence::quantized_layer_norm.out(Tensor input, Tensor in_scale, Tensor in_zero_point, int[] normalized_shape, Tensor weight, Tensor bias, float eps, float output_scale, int output_zero_point, *, Tensor(a!) out) -> Tensor(a!)
   kernels:
     - arg_meta: null
@@ -563,3 +543,13 @@
   kernels:
     - arg_meta: null
       kernel_name: impl::HiFi::quantized_fully_connected_asym8uxasym8u_asym8u_per_tensor_out
+
+- func: cadence::quantized_conv1d_ncl.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, *, Tensor(a!) out) -> Tensor(a!)
+  kernels:
+    - arg_meta: null
+      kernel_name: impl::HiFi::native::quantized_conv1d_ncl_per_tensor_out
+
+- func: cadence::quantized_conv1d_nlc.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, *, Tensor(a!) out) -> Tensor(a!)
+  kernels:
+    - arg_meta: null
+      kernel_name: impl::HiFi::native::quantized_conv1d_nlc_per_tensor_out