diff --git a/clang/lib/CodeGen/CGExprScalar.cpp b/clang/lib/CodeGen/CGExprScalar.cpp
--- a/clang/lib/CodeGen/CGExprScalar.cpp
+++ b/clang/lib/CodeGen/CGExprScalar.cpp
@@ -4785,11 +4785,8 @@
   // vector to get a vec4, then a bitcast if the target type is different.
   if (NumElementsSrc == 3 && NumElementsDst != 3) {
     Src = ConvertVec3AndVec4(Builder, CGF, Src, 4);
-
-    if (!CGF.CGM.getCodeGenOpts().PreserveVec3Type) {
-      Src = createCastsForTypeOfSameSize(Builder, CGF.CGM.getDataLayout(), Src,
-                                         DstTy);
-    }
+    Src = createCastsForTypeOfSameSize(Builder, CGF.CGM.getDataLayout(), Src,
+                                       DstTy);
 
     Src->setName("astype");
     return Src;
diff --git a/clang/test/CodeGenOpenCL/preserve_vec3.cl b/clang/test/CodeGenOpenCL/preserve_vec3.cl
--- a/clang/test/CodeGenOpenCL/preserve_vec3.cl
+++ b/clang/test/CodeGenOpenCL/preserve_vec3.cl
@@ -1,5 +1,8 @@
 // RUN: %clang_cc1 %s -emit-llvm -o - -triple spir-unknown-unknown -fpreserve-vec3-type | FileCheck %s
 
+typedef char char3 __attribute__((ext_vector_type(3)));
+typedef short short3 __attribute__((ext_vector_type(3)));
+typedef double double2 __attribute__((ext_vector_type(2)));
 typedef float float3 __attribute__((ext_vector_type(3)));
 typedef float float4 __attribute__((ext_vector_type(4)));
 
@@ -25,3 +28,28 @@
   // CHECK: store <4 x float> %[[ASTYPE]], <4 x float> addrspace(1)* %b, align 16
   *b = __builtin_astype(*a, float4);
 }
+
+void kernel float3_to_double2(global float3 *a, global double2 *b) {
+  // CHECK-LABEL: spir_kernel void @float3_to_double2
+  // CHECK: %[[LOAD_A:.*]] = load <3 x float>, <3 x float> addrspace(1)* %a, align 16
+  // CHECK: %[[ASTYPE:.*]] = shufflevector <3 x float> %[[LOAD_A]], <3 x float> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 undef>
+  // CHECK: %[[OUT_BC:.*]] = bitcast <2 x double> addrspace(1)* %b to <4 x float> addrspace(1)*
+  // CHECK: store <4 x float> %[[ASTYPE]], <4 x float> addrspace(1)* %[[OUT_BC]], align 16
+  *b = __builtin_astype(*a, double2);
+}
+
+void from_char3(char3 a, global int *out) {
+  // CHECK-LABEL: void @from_char3
+  // CHECK: %[[ASTYPE:.*]] = shufflevector <3 x i8> %a, <3 x i8> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 undef>
+  // CHECK: %[[OUT_BC:.*]] = bitcast i32 addrspace(1)* %out to <4 x i8> addrspace(1)*
+  // CHECK: store <4 x i8> %[[ASTYPE]], <4 x i8> addrspace(1)* %[[OUT_BC]]
+  *out = __builtin_astype(a, int);
+}
+
+void from_short3(short3 a, global long *out) {
+  // CHECK-LABEL: void @from_short3
+  // CHECK: %[[ASTYPE:.*]] = shufflevector <3 x i16> %a, <3 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 undef>
+  // CHECK: %[[OUT_BC:.*]] = bitcast i64 addrspace(1)* %out to <4 x i16> addrspace(1)*
+  // CHECK: store <4 x i16> %[[ASTYPE]], <4 x i16> addrspace(1)* %[[OUT_BC]]
+  *out = __builtin_astype(a, long);
+}