diff --git a/mlir/lib/Conversion/StandardToLLVM/StandardToLLVM.cpp b/mlir/lib/Conversion/StandardToLLVM/StandardToLLVM.cpp
--- a/mlir/lib/Conversion/StandardToLLVM/StandardToLLVM.cpp
+++ b/mlir/lib/Conversion/StandardToLLVM/StandardToLLVM.cpp
@@ -1729,6 +1729,7 @@
 using OrOpLowering = VectorConvertToLLVMPattern<OrOp, LLVM::OrOp>;
 using PowFOpLowering = VectorConvertToLLVMPattern<math::PowFOp, LLVM::PowOp>;
 using RemFOpLowering = VectorConvertToLLVMPattern<RemFOp, LLVM::FRemOp>;
+using SIToFPOpLowering = VectorConvertToLLVMPattern<SIToFPOp, LLVM::SIToFPOp>;
 using SelectOpLowering = VectorConvertToLLVMPattern<SelectOp, LLVM::SelectOp>;
 using SignExtendIOpLowering =
     VectorConvertToLLVMPattern<SignExtendIOp, LLVM::SExtOp>;
@@ -3112,11 +3113,6 @@
   }
 };
 
-struct SIToFPLowering
-    : public OneToOneConvertToLLVMPattern<SIToFPOp, LLVM::SIToFPOp> {
-  using Super::Super;
-};
-
 struct UIToFPLowering
     : public OneToOneConvertToLLVMPattern<UIToFPOp, LLVM::UIToFPOp> {
   using Super::Super;
@@ -3922,7 +3918,7 @@
       RemFOpLowering,
       ReturnOpLowering,
       RsqrtOpLowering,
-      SIToFPLowering,
+      SIToFPOpLowering,
       SelectOpLowering,
       ShiftLeftOpLowering,
       SignExtendIOpLowering,
diff --git a/mlir/test/Conversion/StandardToLLVM/convert-nd-vector-to-llvmir.mlir b/mlir/test/Conversion/StandardToLLVM/convert-nd-vector-to-llvmir.mlir
--- a/mlir/test/Conversion/StandardToLLVM/convert-nd-vector-to-llvmir.mlir
+++ b/mlir/test/Conversion/StandardToLLVM/convert-nd-vector-to-llvmir.mlir
@@ -47,3 +47,16 @@
   %0 = zexti %arg0: vector<1x2x3xi32> to vector<1x2x3xi64>
   return
 }
+
+// CHECK-LABEL: @sitofp
+func @sitofp_vector(%arg0 : vector<1x2x3xi32>) -> vector<1x2x3xf32> {
+  // CHECK: llvm.mlir.undef : !llvm.array<1 x array<2 x vector<3xf32>>>
+  // CHECK: llvm.extractvalue %{{.*}}[0, 0] : !llvm.array<1 x array<2 x vector<3xi32>>>
+  // CHECK: llvm.sitofp %{{.*}} : vector<3xi32> to vector<3xf32>
+  // CHECK: llvm.insertvalue %{{.*}}, %{{.*}}[0, 0] : !llvm.array<1 x array<2 x vector<3xf32>>>
+  // CHECK: llvm.extractvalue %{{.*}}[0, 1] : !llvm.array<1 x array<2 x vector<3xi32>>>
+  // CHECK: llvm.sitofp %{{.*}} : vector<3xi32> to vector<3xf32>
+  // CHECK: llvm.insertvalue %{{.*}}, %{{.*}}[0, 1] : !llvm.array<1 x array<2 x vector<3xf32>>>
+  %0 = sitofp %arg0: vector<1x2x3xi32> to vector<1x2x3xf32>
+  return %0 : vector<1x2x3xf32>
+}