Index: llvm/lib/IR/IRBuilder.cpp
===================================================================
--- llvm/lib/IR/IRBuilder.cpp
+++ llvm/lib/IR/IRBuilder.cpp
@@ -94,11 +94,19 @@
 }
 
 Value *IRBuilderBase::CreateStepVector(Type *DstType, const Twine &Name) {
-  if (isa<ScalableVectorType>(DstType))
-    return CreateIntrinsic(Intrinsic::experimental_stepvector, {DstType}, {},
-                           nullptr, Name);
-
   Type *STy = DstType->getScalarType();
+  if (isa<ScalableVectorType>(DstType)) {
+    Type *StepVecType = DstType;
+    if (STy->getScalarSizeInBits() < 8)
+      StepVecType =
+          VectorType::get(getInt8Ty(), cast<ScalableVectorType>(DstType));
+    Value *Res = CreateIntrinsic(Intrinsic::experimental_stepvector,
+                                 {StepVecType}, {}, nullptr, Name);
+    if (StepVecType != DstType)
+      Res = CreateTrunc(Res, DstType);
+    return Res;
+  }
+
   unsigned NumEls = cast<FixedVectorType>(DstType)->getNumElements();
 
   // Create a vector of consecutive numbers from zero to VF.
Index: llvm/unittests/IR/IRBuilderTest.cpp
===================================================================
--- llvm/unittests/IR/IRBuilderTest.cpp
+++ llvm/unittests/IR/IRBuilderTest.cpp
@@ -214,6 +214,25 @@
   EXPECT_EQ(Call->getIntrinsicID(), Intrinsic::experimental_stepvector);
 }
 
+TEST_F(IRBuilderTest, CreateStepVectorI3) {
+  IRBuilder<> Builder(BB);
+
+  // Scalable vectors
+  Type *DstVecTy = VectorType::get(IntegerType::get(Ctx, 3), 2, true);
+  Type *VecI8Ty = VectorType::get(Builder.getInt8Ty(), 2, true);
+  Value *StepVec = Builder.CreateStepVector(DstVecTy);
+  EXPECT_TRUE(isa<TruncInst>(StepVec));
+  TruncInst *Trunc = cast<TruncInst>(StepVec);
+  EXPECT_EQ(Trunc->getDestTy(), DstVecTy);
+  EXPECT_EQ(Trunc->getSrcTy(), VecI8Ty);
+  EXPECT_TRUE(isa<CallInst>(Trunc->getOperand(0)));
+
+  CallInst *Call = cast<CallInst>(Trunc->getOperand(0));
+  FunctionType *FTy = Call->getFunctionType();
+  EXPECT_EQ(FTy->getReturnType(), VecI8Ty);
+  EXPECT_EQ(Call->getIntrinsicID(), Intrinsic::experimental_stepvector);
+}
+
 TEST_F(IRBuilderTest, ConstrainedFP) {
   IRBuilder<> Builder(BB);
   Value *V;