diff --git a/mlir/include/mlir/Dialect/Linalg/IR/LinalgNamedStructuredOps.yaml b/mlir/include/mlir/Dialect/Linalg/IR/LinalgNamedStructuredOps.yaml
--- a/mlir/include/mlir/Dialect/Linalg/IR/LinalgNamedStructuredOps.yaml
+++ b/mlir/include/mlir/Dialect/Linalg/IR/LinalgNamedStructuredOps.yaml
@@ -1907,18 +1907,18 @@
   indexing_maps: !LinalgIndexingMapsConfig
     static_indexing_maps:
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d0, d1 * s2 + d3 * s4, d2 * s6 + d4 * s8, d5)>
+      -> (d0, d1 * s2 + d4 * s4, d2 * s6 + d5 * s8, d3)>
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d3, d4)>
+      -> (d4, d5)>
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d0, d1, d2, d5)>
+      -> (d0, d1, d2, d3)>
   iterator_types:
   - parallel
   - parallel
   - parallel
+  - parallel
   - reduction
   - reduction
-  - parallel
   assignments:
   - !ScalarAssign
     arg: O
@@ -1978,18 +1978,18 @@
   indexing_maps: !LinalgIndexingMapsConfig
     static_indexing_maps:
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d0, d1 * s2 + d3 * s4, d2 * s6 + d4 * s8, d5)>
+      -> (d0, d1 * s2 + d4 * s4, d2 * s6 + d5 * s8, d3)>
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d3, d4)>
+      -> (d4, d5)>
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d0, d1, d2, d5)>
+      -> (d0, d1, d2, d3)>
   iterator_types:
   - parallel
   - parallel
   - parallel
+  - parallel
   - reduction
   - reduction
-  - parallel
   assignments:
   - !ScalarAssign
     arg: O
@@ -2049,18 +2049,18 @@
   indexing_maps: !LinalgIndexingMapsConfig
     static_indexing_maps:
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d0, d1 * s2 + d3 * s4, d2 * s6 + d4 * s8, d5)>
+      -> (d0, d1 * s2 + d4 * s4, d2 * s6 + d5 * s8, d3)>
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d3, d4)>
+      -> (d4, d5)>
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d0, d1, d2, d5)>
+      -> (d0, d1, d2, d3)>
   iterator_types:
   - parallel
   - parallel
   - parallel
+  - parallel
   - reduction
   - reduction
-  - parallel
   assignments:
   - !ScalarAssign
     arg: O
@@ -2191,18 +2191,18 @@
   indexing_maps: !LinalgIndexingMapsConfig
     static_indexing_maps:
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d0, d1 * s2 + d3 * s4, d2 * s6 + d4 * s8, d5)>
+      -> (d0, d1 * s2 + d4 * s4, d2 * s6 + d5 * s8, d3)>
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d3, d4)>
+      -> (d4, d5)>
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d0, d1, d2, d5)>
+      -> (d0, d1, d2, d3)>
   iterator_types:
   - parallel
   - parallel
   - parallel
+  - parallel
   - reduction
   - reduction
-  - parallel
   assignments:
   - !ScalarAssign
     arg: O
@@ -2262,18 +2262,18 @@
   indexing_maps: !LinalgIndexingMapsConfig
     static_indexing_maps:
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d0, d1 * s2 + d3 * s4, d2 * s6 + d4 * s8, d5)>
+      -> (d0, d1 * s2 + d4 * s4, d2 * s6 + d5 * s8, d3)>
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d3, d4)>
+      -> (d4, d5)>
     - affine_map<(d0, d1, d2, d3, d4, d5)[s0, s1, s2, s3, s4, s5, s6, s7, s8, s9]
-      -> (d0, d1, d2, d5)>
+      -> (d0, d1, d2, d3)>
   iterator_types:
   - parallel
   - parallel
   - parallel
+  - parallel
   - reduction
   - reduction
-  - parallel
   assignments:
   - !ScalarAssign
     arg: O
@@ -2336,21 +2336,21 @@
   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, s12, s13] -> (d0, d1 * s2 + d4 * s4, d2 * s6 + d5 * s8, d3
-      * s10 + d6 * s12, d7)>
+      s8, s9, s10, s11, s12, s13] -> (d0, d1 * s2 + d5 * s4, d2 * s6 + d6 * s8, d3
+      * s10 + d7 * s12, d4)>
     - affine_map<(d0, d1, d2, d3, d4, d5, d6, d7)[s0, s1, s2, s3, s4, s5, s6, s7,
-      s8, s9, s10, s11, s12, s13] -> (d4, d5, d6)>
+      s8, s9, s10, s11, s12, s13] -> (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, s12, s13] -> (d0, d1, d2, d3, d7)>
+      s8, s9, s10, s11, s12, s13] -> (d0, d1, d2, d3, d4)>
   iterator_types:
   - parallel
   - parallel
   - parallel
   - parallel
+  - parallel
   - reduction
   - reduction
   - reduction
-  - parallel
   assignments:
   - !ScalarAssign
     arg: O
@@ -2413,21 +2413,21 @@
   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, s12, s13] -> (d0, d1 * s2 + d4 * s4, d2 * s6 + d5 * s8, d3
-      * s10 + d6 * s12, d7)>
+      s8, s9, s10, s11, s12, s13] -> (d0, d1 * s2 + d5 * s4, d2 * s6 + d6 * s8, d3
+      * s10 + d7 * s12, d4)>
     - affine_map<(d0, d1, d2, d3, d4, d5, d6, d7)[s0, s1, s2, s3, s4, s5, s6, s7,
-      s8, s9, s10, s11, s12, s13] -> (d4, d5, d6)>
+      s8, s9, s10, s11, s12, s13] -> (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, s12, s13] -> (d0, d1, d2, d3, d7)>
+      s8, s9, s10, s11, s12, s13] -> (d0, d1, d2, d3, d4)>
   iterator_types:
   - parallel
   - parallel
   - parallel
   - parallel
+  - parallel
   - reduction
   - reduction
   - reduction
-  - parallel
   assignments:
   - !ScalarAssign
     arg: O
@@ -2490,21 +2490,21 @@
   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, s12, s13] -> (d0, d1 * s2 + d4 * s4, d2 * s6 + d5 * s8, d3
-      * s10 + d6 * s12, d7)>
+      s8, s9, s10, s11, s12, s13] -> (d0, d1 * s2 + d5 * s4, d2 * s6 + d6 * s8, d3
+      * s10 + d7 * s12, d4)>
     - affine_map<(d0, d1, d2, d3, d4, d5, d6, d7)[s0, s1, s2, s3, s4, s5, s6, s7,
-      s8, s9, s10, s11, s12, s13] -> (d4, d5, d6)>
+      s8, s9, s10, s11, s12, s13] -> (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, s12, s13] -> (d0, d1, d2, d3, d7)>
+      s8, s9, s10, s11, s12, s13] -> (d0, d1, d2, d3, d4)>
   iterator_types:
   - parallel
   - parallel
   - parallel
   - parallel
+  - parallel
   - reduction
   - reduction
   - reduction
-  - parallel
   assignments:
   - !ScalarAssign
     arg: O
diff --git a/mlir/python/mlir/dialects/linalg/opdsl/ops/core_named_ops.py b/mlir/python/mlir/dialects/linalg/opdsl/ops/core_named_ops.py
--- a/mlir/python/mlir/dialects/linalg/opdsl/ops/core_named_ops.py
+++ b/mlir/python/mlir/dialects/linalg/opdsl/ops/core_named_ops.py
@@ -459,7 +459,7 @@
   data type as the accumulator/output.
   """
   implements(ConvolutionOpInterface)
-  domain(D.n, D.oh, D.ow, D.kh, D.kw, D.c)
+  domain(D.n, D.oh, D.ow, D.c, D.kh, D.kw)
   O[D.n, D.oh, D.ow, D.c] += TypeFn.cast(
       U, I[D.n, D.oh * S.SH + D.kh * S.DH, D.ow * S.SW + D.kw * S.DW, D.c])
 
@@ -478,7 +478,7 @@
   data type as the accumulator/output.
   """
   implements(ConvolutionOpInterface)
-  domain(D.n, D.oh, D.ow, D.kh, D.kw, D.c)
+  domain(D.n, D.oh, D.ow, D.c, D.kh, D.kw)
   O[D.n, D.oh, D.ow, D.c] = ReduceFn.max[D.kh, D.kw](
       TypeFn.cast(
           U, I[D.n, D.oh * S.SH + D.kh * S.DH, D.ow * S.SW + D.kw * S.DW, D.c]))
@@ -498,7 +498,7 @@
   data type as the accumulator/output.
   """
   implements(ConvolutionOpInterface)
-  domain(D.n, D.oh, D.ow, D.kh, D.kw, D.c)
+  domain(D.n, D.oh, D.ow, D.c, D.kh, D.kw)
   O[D.n, D.oh, D.ow, D.c] = ReduceFn.max_unsigned[D.kh, D.kw](
       TypeFn.cast_unsigned(
           U, I[D.n, D.oh * S.SH + D.kh * S.DH, D.ow * S.SW + D.kw * S.DW, D.c]))
@@ -539,7 +539,7 @@
   data type as the accumulator/output.
   """
   implements(ConvolutionOpInterface)
-  domain(D.n, D.oh, D.ow, D.kh, D.kw, D.c)
+  domain(D.n, D.oh, D.ow, D.c, D.kh, D.kw)
   O[D.n, D.oh, D.ow, D.c] = ReduceFn.min[D.kh, D.kw](
       TypeFn.cast(
           U, I[D.n, D.oh * S.SH + D.kh * S.DH, D.ow * S.SW + D.kw * S.DW, D.c]))
@@ -559,7 +559,7 @@
   data type as the accumulator/output.
   """
   implements(ConvolutionOpInterface)
-  domain(D.n, D.oh, D.ow, D.kh, D.kw, D.c)
+  domain(D.n, D.oh, D.ow, D.c, D.kh, D.kw)
   O[D.n, D.oh, D.ow, D.c] = ReduceFn.min_unsigned[D.kh, D.kw](
       TypeFn.cast_unsigned(
           U, I[D.n, D.oh * S.SH + D.kh * S.DH, D.ow * S.SW + D.kw * S.DW, D.c]))
@@ -579,7 +579,7 @@
   data type as the accumulator/output.
   """
   implements(ConvolutionOpInterface)
-  domain(D.n, D.od, D.oh, D.ow, D.kd, D.kh, D.kw, D.c)
+  domain(D.n, D.od, D.oh, D.ow, D.c, D.kd, D.kh, D.kw)
   O[D.n, D.od, D.oh, D.ow, D.c] += TypeFn.cast(
       U, I[D.n, D.od * S.SD + D.kd * S.DD, D.oh * S.SH + D.kh * S.DH,
            D.ow * S.SW + D.kw * S.DW, D.c])
@@ -599,7 +599,7 @@
   data type as the accumulator/output.
   """
   implements(ConvolutionOpInterface)
-  domain(D.n, D.od, D.oh, D.ow, D.kd, D.kh, D.kw, D.c)
+  domain(D.n, D.od, D.oh, D.ow, D.c, D.kd, D.kh, D.kw)
   O[D.n, D.od, D.oh, D.ow, D.c] = ReduceFn.max[D.kd, D.kh, D.kw](
       TypeFn.cast(
           U, I[D.n, D.od * S.SD + D.kd * S.DD, D.oh * S.SH + D.kh * S.DH,
@@ -620,7 +620,7 @@
   data type as the accumulator/output.
   """
   implements(ConvolutionOpInterface)
-  domain(D.n, D.od, D.oh, D.ow, D.kd, D.kh, D.kw, D.c)
+  domain(D.n, D.od, D.oh, D.ow, D.c, D.kd, D.kh, D.kw)
   O[D.n, D.od, D.oh, D.ow, D.c] = ReduceFn.min[D.kd, D.kh, D.kw](
       TypeFn.cast(
           U, I[D.n, D.od * S.SD + D.kd * S.DD, D.oh * S.SH + D.kh * S.DH,