Index: mlir/lib/Dialect/Affine/IR/AffineOps.cpp
===================================================================
--- mlir/lib/Dialect/Affine/IR/AffineOps.cpp
+++ mlir/lib/Dialect/Affine/IR/AffineOps.cpp
@@ -1816,7 +1816,10 @@
   if (!ivArg || !ivArg.getOwner())
     return AffineForOp();
   auto *containingInst = ivArg.getOwner()->getParent()->getParentOp();
-  return dyn_cast<AffineForOp>(containingInst);
+  if (auto forOp = dyn_cast<AffineForOp>(containingInst))
+    // Check to make sure `val` is the induction variable, not an iter_arg.
+    return forOp.getInductionVar() == val ? forOp : AffineForOp();
+  return AffineForOp();
 }
 
 /// Extracts the induction variables from a list of AffineForOps and returns
Index: mlir/lib/Dialect/Affine/Transforms/SuperVectorize.cpp
===================================================================
--- mlir/lib/Dialect/Affine/Transforms/SuperVectorize.cpp
+++ mlir/lib/Dialect/Affine/Transforms/SuperVectorize.cpp
@@ -253,7 +253,8 @@
 ///           transfer read and write operations.
 ///         * Scalar constant operations/operands are converted to vector
 ///           constant operations (splat).
-///         * Uniform operands (only operands defined outside of the loop nest,
+///         * Uniform operands (only induction variables of loops not mapped to
+///           a vector dimension, or operands defined outside of the loop nest
 ///           for now) are broadcasted to a vector.
 ///           TODO: Support more uniform cases.
 ///         * Affine for operations with 'iter_args' are vectorized by
@@ -1062,10 +1063,16 @@
 
 /// Returns true if the provided value is vector uniform given the vectorization
 /// strategy.
-// TODO: For now, only values that are invariants to all the loops in the
-// vectorization strategy are considered vector uniforms.
+// TODO: For now, only values that are induction variables of loops not in
+// `loopToVectorDim` or invariants to all the loops in the vectorization
+// strategy are considered vector uniforms.
 static bool isUniformDefinition(Value value,
                                 const VectorizationStrategy *strategy) {
+  AffineForOp forOp = getForInductionVarOwner(value);
+  if (forOp &&
+      strategy->loopToVectorDim.find(forOp) == strategy->loopToVectorDim.end())
+    return true;
+
   for (auto loopToDim : strategy->loopToVectorDim) {
     auto loop = cast<AffineForOp>(loopToDim.first);
     if (!loop.isDefinedOutsideOfLoop(value))
@@ -1079,11 +1086,13 @@
 static Operation *vectorizeUniform(Value uniformVal,
                                    VectorizationState &state) {
   OpBuilder::InsertionGuard guard(state.builder);
-  state.builder.setInsertionPointAfterValue(uniformVal);
+  auto uniformScalarRepl =
+      state.valueScalarReplacement.lookupOrDefault(uniformVal);
+  state.builder.setInsertionPointAfterValue(uniformScalarRepl);
 
   auto vectorTy = getVectorType(uniformVal.getType(), state.strategy);
   auto bcastOp = state.builder.create<BroadcastOp>(uniformVal.getLoc(),
-                                                   vectorTy, uniformVal);
+                                                   vectorTy, uniformScalarRepl);
   state.registerValueVectorReplacement(uniformVal, bcastOp);
   return bcastOp;
 }
Index: mlir/test/Dialect/Affine/SuperVectorize/vectorize_1d.mlir
===================================================================
--- mlir/test/Dialect/Affine/SuperVectorize/vectorize_1d.mlir
+++ mlir/test/Dialect/Affine/SuperVectorize/vectorize_1d.mlir
@@ -165,6 +165,56 @@
 
 // -----
 
+// CHECK-LABEL: func @vec_block_arg
+func @vec_block_arg(%A : memref<32x512xi32>) {
+  // CHECK:      affine.for %[[IV0:[arg0-9]+]] = 0 to 512 step 128 {
+  // CHECK-NEXT:   affine.for %[[IV1:[arg0-9]+]] = 0 to 32 {
+  // CHECK-NEXT:     %[[BROADCAST:.*]] = vector.broadcast %[[IV1]] : index to vector<128xindex>
+  // CHECK-NEXT:     %[[CAST:.*]] = index_cast %[[BROADCAST]] : vector<128xindex> to vector<128xi32>
+  // CHECK-NEXT:     vector.transfer_write %[[CAST]], {{.*}}[%[[IV1]], %[[IV0]]] : vector<128xi32>, memref<32x512xi32>
+  affine.for %i = 0 to 512 {  // vectorized
+    affine.for %j = 0 to 32 {
+      %idx = std.index_cast %j : index to i32
+      affine.store %idx, %A[%j, %i] : memref<32x512xi32>
+    }
+  }
+  return
+}
+
+// -----
+
+// CHECK-DAG: #[[$map0:map[0-9]+]] = affine_map<(d0, d1, d2) -> (d0 * 2 + d1 - 1)>
+// CHECK-DAG: #[[$map1:map[0-9]+]] = affine_map<(d0, d1, d2) -> (d2)>
+// CHECK-LABEL: func @vec_block_arg_2
+func @vec_block_arg_2(%A : memref<?x512xindex>) {
+  %c0 = constant 0 : index
+  %N = memref.dim %A, %c0 : memref<?x512xindex>
+  // CHECK:      affine.for %[[IV0:[arg0-9]+]] = 0 to %{{.*}} {
+  // CHECK-NEXT:   %[[BROADCAST1:.*]] = vector.broadcast %[[IV0]] : index to vector<128xindex>
+  // CHECK-NEXT:   affine.for %[[IV1:[arg0-9]+]] = 0 to 512 step 128 {
+  // CHECK-NOT:      vector.broadcast %[[IV1]]
+  // CHECK:          affine.for %[[IV2:[arg0-9]+]] = 0 to 2 {
+  // CHECK-NEXT:       %[[BROADCAST2:.*]] = vector.broadcast %[[IV2]] : index to vector<128xindex>
+  // CHECK-NEXT:       %[[INDEX1:.*]] = affine.apply #[[$map0]](%[[IV0]], %[[IV2]], %[[IV1]])
+  // CHECK-NEXT:       %[[INDEX2:.*]] = affine.apply #[[$map1]](%[[IV0]], %[[IV2]], %[[IV1]])
+  // CHECK:            %[[LOAD:.*]] = vector.transfer_read %{{.*}}[%[[INDEX1]], %[[INDEX2]]], %{{.*}} : memref<?x512xindex>, vector<128xindex>
+  // CHECK-NEXT:       muli %[[BROADCAST1]], %[[LOAD]] : vector<128xindex>
+  // CHECK-NEXT:       addi %{{.*}}, %[[BROADCAST2]] : vector<128xindex>
+  // CHECK:          }
+  affine.for %i0 = 0 to %N {
+    affine.for %i1 = 0 to 512 { // vectorized
+      affine.for %i2 = 0 to 2 {
+        %0 = affine.load %A[%i0 * 2 + %i2 - 1, %i1] : memref<?x512xindex>
+        %mul = muli %i0, %0 : index
+        %add = addi %mul, %i2 : index
+      }
+    }  
+  }  
+  return
+}
+
+// -----
+
 // CHECK-LABEL: func @vec_rejected_1
 func @vec_rejected_1(%A : memref<?x?xf32>, %B : memref<?x?x?xf32>) {
 // CHECK-DAG: %[[C0:.*]] = constant 0 : index