diff --git a/mlir/lib/Analysis/Utils.cpp b/mlir/lib/Analysis/Utils.cpp
--- a/mlir/lib/Analysis/Utils.cpp
+++ b/mlir/lib/Analysis/Utils.cpp
@@ -207,7 +207,8 @@
 
     // Check if src and dst loop bounds are the same. If not, we can guarantee
     // that the slice is not maximal.
-    if (srcLbResult != dstLbResult || srcUbResult != dstUbResult)
+    if (srcLbResult != dstLbResult || srcUbResult != dstUbResult ||
+        srcLoop.getStep() != dstLoop.getStep())
       return false;
   }
 
diff --git a/mlir/test/Transforms/loop-fusion-4.mlir b/mlir/test/Transforms/loop-fusion-4.mlir
--- a/mlir/test/Transforms/loop-fusion-4.mlir
+++ b/mlir/test/Transforms/loop-fusion-4.mlir
@@ -109,3 +109,26 @@
 // SIBLING-MAXIMAL-NEXT:             affine.for %[[idx_1:.*]] = 0 to 64 {
 // SIBLING-MAXIMAL-NEXT:               %[[result_1:.*]] = affine.for %[[idx_2:.*]] = 0 to 32 iter_args(%[[iter_0:.*]] = %[[cst_1]]) -> (f32) {
 // SIBLING-MAXIMAL-NEXT:                 %[[result_0:.*]] = affine.for %[[idx_3:.*]] = 0 to 64 iter_args(%[[iter_1:.*]] = %[[cst_0]]) -> (f32) {
+
+// -----
+
+// Expects fusion of producer into consumer at depth 1 and source loop to not
+// be removed due to difference in loop steps.
+// PRODUCER-CONSUMER-LABEL: func @check_src_dst_step
+func @check_src_dst_step(%m : memref<100xf32>,
+                         %src: memref<100xf32>,
+                         %out: memref<100xf32>) {
+  affine.for %i0 = 0 to 100 {
+    %r1 = affine.load %src[%i0]: memref<100xf32>
+    affine.store %r1, %m[%i0] : memref<100xf32>
+  }
+  affine.for %i2 = 0 to 100 step 2 {
+    %r2 = affine.load %m[%i2] : memref<100xf32>
+    affine.store %r2, %out[%i2] : memref<100xf32>
+  }
+  return
+}
+
+// PRODUCER-CONSUMER: affine.for
+// PRODUCER-CONSUMER: affine.for
+// PRODUCER-CONSUMER: return