Index: mlir/include/mlir/Dialect/Linalg/IR/LinalgNamedStructuredOps.yaml
===================================================================
--- mlir/include/mlir/Dialect/Linalg/IR/LinalgNamedStructuredOps.yaml
+++ mlir/include/mlir/Dialect/Linalg/IR/LinalgNamedStructuredOps.yaml
@@ -1643,6 +1643,107 @@
                 operands:
                 - !ScalarExpression
                   scalar_arg: K
+
+--- !LinalgOpConfig
+metadata: !LinalgOpMetadata
+  name: conv_2d_gnchw_gfchw
+  cpp_class_name: Conv2DNgchwFgchwOp
+  doc: |-
+    Performs 2-D convolution.
+
+    Layout:
+      * Input: NGCHW.
+      * Kernel: FGCHW.
+
+    Numeric casting is performed on the operands to the inner multiply, promoting
+    them to the same data type as the accumulator/output.
+  implements:
+  - LinalgConvolutionOpInterface
+structured_op: !LinalgStructuredOpConfig
+  args:
+  - !LinalgOperandDefConfig
+    name: I
+    kind: input_tensor
+    type_var: T1
+    shape_map: affine_map<()[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11] -> (s0,
+      s1, s2, s3 * s4 + s5 * s6, s7 * s8 + s9 * s10)>
+  - !LinalgOperandDefConfig
+    name: K
+    kind: input_tensor
+    type_var: T2
+    shape_map: affine_map<()[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11] -> (s11,
+      s1, s5, s9)>
+  - !LinalgOperandDefConfig
+    name: O
+    kind: output_tensor
+    type_var: U
+    shape_map: affine_map<()[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9, s10. s11] -> (s0,
+      s11, s3, s7)>
+  - !LinalgOperandDefConfig
+    name: strides
+    kind: index_attr
+    index_attr_map: affine_map<()[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11] ->
+      (s4, s8)>
+    default_indices:
+    - 1
+    - 1
+  - !LinalgOperandDefConfig
+    name: dilations
+    kind: index_attr
+    index_attr_map: affine_map<()[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9, s10. s11] ->
+      (s6, s10)>
+    default_indices:
+    - 1
+    - 1
+  indexing_maps: !LinalgIndexingMapsConfig
+    static_indexing_maps:
+    - affine_map<(d0, d1, d2, d3, d4, d5, d6, d7)[s0, s1, s2, s3, s4, s5, s6, s7, s8,
+      s9, s10, s11] -> (d0, d2, d5, d3 * s4 + d6 * s6, d4 * s8 + d7 * s10)>
+    - affine_map<(d0, d1, d2, d3, d4, d5, d6, d7)[s0, s1, s2, s3, s4, s5, s6, s7, s8,
+      s9, s10, s11] -> (d1, d2, d5, d6, d7)>
+    - affine_map<(d0, d1, d2, d3, d4, d5, d6, d7)[s0, s1, s2, s3, s4, s5, s6, s7, s8,
+      s9, s10, s11] -> (d0, d1, d3, d4)>
+  iterator_types:
+  - parallel
+  - parallel
+  - parallel
+  - parallel
+  - parallel
+  - reduction
+  - reduction
+  - reduction
+  - reduction
+  assignments:
+  - !ScalarAssign
+    arg: O
+    value: !ScalarExpression
+      scalar_fn:
+        kind: binary
+        fn_name: add
+        operands:
+        - !ScalarExpression
+          scalar_arg: O
+        - !ScalarExpression
+          scalar_fn:
+            kind: binary
+            fn_name: mul
+            operands:
+            - !ScalarExpression
+              scalar_fn:
+                kind: type
+                fn_name: cast_signed
+                type_var: U
+                operands:
+                - !ScalarExpression
+                  scalar_arg: I
+            - !ScalarExpression
+              scalar_fn:
+                kind: type
+                fn_name: cast_signed
+                type_var: U
+                operands:
+                - !ScalarExpression
+                  scalar_arg: K
 --- !LinalgOpConfig
 metadata: !LinalgOpMetadata
   name: conv_3d_ndhwc_dhwcf
Index: mlir/python/mlir/dialects/linalg/opdsl/ops/core_named_ops.py
===================================================================
--- mlir/python/mlir/dialects/linalg/opdsl/ops/core_named_ops.py
+++ mlir/python/mlir/dialects/linalg/opdsl/ops/core_named_ops.py
@@ -298,7 +298,7 @@
                                     S.OW * S.SW + S.KW * S.DW, S.C),
                         K=TensorDef(T2, S.KH, S.KW, S.C, S.F),
                         IZp=ScalarDef(I32),
-                        KZp=ScalarDef(I32),
+                        KgZp=ScalarDef(I32),
                         O=TensorDef(U, S.N, S.OH, S.OW, S.F, output=True),
                         strides=IndexAttrDef(S.SH, S.SW, default=[1, 1]),
                         dilations=IndexAttrDef(S.DH, S.DW, default=[1, 1])):
@@ -343,6 +343,28 @@
       U, I[D.n, D.c, D.oh * S.SH + D.kh * S.DH, D.ow * S.SW +
            D.kw * S.DW]) * TypeFn.cast_signed(U, K[D.f, D.c, D.kh, D.kw])
 
+@linalg_structured_op
+def conv_group_2d_ngchw_fgchw(I=TensorDef(T1, S.N, G, S.CG, S.OH * S.SH + S.KH * S.DH,
+                                  S.OW * S.SW + S.KW * S.DW),
+                      K=TensorDef(T2, S.FG, G, S.C, S.KH, S.KW),
+                      O=TensorDef(U, S.N, S.F, S.OH, S.OW, output=True),
+                      strides=IndexAttrDef(S.SH, S.SW, default=[1, 1]),
+                      dilations=IndexAttrDef(S.DH, S.DW, default=[1, 1])):
+  """Performs Grouped 2-D convolution.
+
+  Layout:
+    * Input: NGCHW.
+    * Kernel: FGCHW.
+
+  Numeric casting is performed on the operands to the inner multiply, promoting
+  them to the same data type as the accumulator/output.
+  """
+  implements(ConvolutionOpInterface)
+  domain(D.n, D.fg, D.oh, D.ow, D.cg, D.c, D.kh, D.kw, D.g)
+  O[D.n, D.fg, D.oh, D.ow] += TypeFn.cast_signed(
+      U, I[D.n, D.g, D.cg, D.oh * S.SH + D.kh * S.DH, D.ow * S.SW +
+           D.kw * S.DW]) * TypeFn.cast_signed(U, K[D.fg, D.g, D.c, D.kh, D.kw])
+
 
 @linalg_structured_op
 def conv_3d_ndhwc_dhwcf(I=TensorDef(T1, S.N, S.OD * S.SD + S.KD * S.DD,