Index: include/clang/Driver/CC1Options.td
===================================================================
--- include/clang/Driver/CC1Options.td
+++ include/clang/Driver/CC1Options.td
@@ -657,6 +657,9 @@
 def finclude_default_header : Flag<["-"], "finclude-default-header">,
   HelpText<"Include the default header file for OpenCL">;
 
+def preserve_vec3_type : Flag<["-"], "preserve-vec3-type">,
+  HelpText<"Preserve 3-component vector type operations">;
+
 // FIXME: Remove these entirely once functionality/tests have been excised.
 def fobjc_gc_only : Flag<["-"], "fobjc-gc-only">, Group<f_Group>,
   HelpText<"Use GC exclusively for Objective-C related memory management">;
Index: include/clang/Frontend/CodeGenOptions.def
===================================================================
--- include/clang/Frontend/CodeGenOptions.def
+++ include/clang/Frontend/CodeGenOptions.def
@@ -265,6 +265,9 @@
 /// Whether emit extra debug info for sample pgo profile collection.
 CODEGENOPT(DebugInfoForProfiling, 1, 0)
 
+/// Whether 3-component vector type is preserved.
+CODEGENOPT(PreserveVec3Type, 1, 0)
+
 #undef CODEGENOPT
 #undef ENUM_CODEGENOPT
 #undef VALUE_CODEGENOPT
Index: lib/CodeGen/CGExpr.cpp
===================================================================
--- lib/CodeGen/CGExpr.cpp
+++ lib/CodeGen/CGExpr.cpp
@@ -1368,26 +1368,28 @@
                                                QualType TBAABaseType,
                                                uint64_t TBAAOffset,
                                                bool isNontemporal) {
-  // For better performance, handle vector loads differently.
-  if (Ty->isVectorType()) {
-    const llvm::Type *EltTy = Addr.getElementType();
-
-    const auto *VTy = cast<llvm::VectorType>(EltTy);
-
-    // Handle vectors of size 3 like size 4 for better performance.
-    if (VTy->getNumElements() == 3) {
-
-      // Bitcast to vec4 type.
-      llvm::VectorType *vec4Ty = llvm::VectorType::get(VTy->getElementType(),
-                                                         4);
-      Address Cast = Builder.CreateElementBitCast(Addr, vec4Ty, "castToVec4");
-      // Now load value.
-      llvm::Value *V = Builder.CreateLoad(Cast, Volatile, "loadVec4");
-
-      // Shuffle vector to get vec3.
-      V = Builder.CreateShuffleVector(V, llvm::UndefValue::get(vec4Ty),
-                                      {0, 1, 2}, "extractVec");
-      return EmitFromMemory(V, Ty);
+  if (!CGM.getCodeGenOpts().PreserveVec3Type) {
+    // For better performance, handle vector loads differently.
+    if (Ty->isVectorType()) {
+      const llvm::Type *EltTy = Addr.getElementType();
+
+      const auto *VTy = cast<llvm::VectorType>(EltTy);
+
+      // Handle vectors of size 3 like size 4 for better performance.
+      if (VTy->getNumElements() == 3) {
+
+        // Bitcast to vec4 type.
+        llvm::VectorType *vec4Ty =
+            llvm::VectorType::get(VTy->getElementType(), 4);
+        Address Cast = Builder.CreateElementBitCast(Addr, vec4Ty, "castToVec4");
+        // Now load value.
+        llvm::Value *V = Builder.CreateLoad(Cast, Volatile, "loadVec4");
+
+        // Shuffle vector to get vec3.
+        V = Builder.CreateShuffleVector(V, llvm::UndefValue::get(vec4Ty),
+                                        {0, 1, 2}, "extractVec");
+        return EmitFromMemory(V, Ty);
+      }
     }
   }
 
@@ -1456,23 +1458,24 @@
                                         bool isNontemporal) {
 
   // Handle vectors differently to get better performance.
-  if (Ty->isVectorType()) {
-    llvm::Type *SrcTy = Value->getType();
-    auto *VecTy = cast<llvm::VectorType>(SrcTy);
-    // Handle vec3 special.
-    if (VecTy->getNumElements() == 3) {
-      // Our source is a vec3, do a shuffle vector to make it a vec4.
-      llvm::Constant *Mask[] = {Builder.getInt32(0), Builder.getInt32(1),
-                                Builder.getInt32(2),
-                                llvm::UndefValue::get(Builder.getInt32Ty())};
-      llvm::Value *MaskV = llvm::ConstantVector::get(Mask);
-      Value = Builder.CreateShuffleVector(Value,
-                                          llvm::UndefValue::get(VecTy),
-                                          MaskV, "extractVec");
-      SrcTy = llvm::VectorType::get(VecTy->getElementType(), 4);
-    }
-    if (Addr.getElementType() != SrcTy) {
-      Addr = Builder.CreateElementBitCast(Addr, SrcTy, "storetmp");
+  if (!CGM.getCodeGenOpts().PreserveVec3Type) {
+    if (Ty->isVectorType()) {
+      llvm::Type *SrcTy = Value->getType();
+      auto *VecTy = cast<llvm::VectorType>(SrcTy);
+      // Handle vec3 special.
+      if (VecTy->getNumElements() == 3) {
+        // Our source is a vec3, do a shuffle vector to make it a vec4.
+        llvm::Constant *Mask[] = {Builder.getInt32(0), Builder.getInt32(1),
+                                  Builder.getInt32(2),
+                                  llvm::UndefValue::get(Builder.getInt32Ty())};
+        llvm::Value *MaskV = llvm::ConstantVector::get(Mask);
+        Value = Builder.CreateShuffleVector(Value, llvm::UndefValue::get(VecTy),
+                                            MaskV, "extractVec");
+        SrcTy = llvm::VectorType::get(VecTy->getElementType(), 4);
+      }
+      if (Addr.getElementType() != SrcTy) {
+        Addr = Builder.CreateElementBitCast(Addr, SrcTy, "storetmp");
+      }
     }
   }
 
Index: lib/Frontend/CompilerInvocation.cpp
===================================================================
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -713,6 +713,7 @@
     }
   }
 
+  Opts.PreserveVec3Type = Args.hasArg(OPT_preserve_vec3_type);
   Opts.InstrumentFunctions = Args.hasArg(OPT_finstrument_functions);
   Opts.XRayInstrumentFunctions = Args.hasArg(OPT_fxray_instrument);
   Opts.XRayInstructionThreshold =
Index: test/CodeGenOpenCL/preserve_vec3.cl
===================================================================
--- /dev/null
+++ test/CodeGenOpenCL/preserve_vec3.cl
@@ -0,0 +1,10 @@
+// RUN: %clang_cc1 %s -emit-llvm -o - -triple spir-unknown-unknown -preserve-vec3-type  | FileCheck %s
+
+typedef float float3 __attribute__((ext_vector_type(3)));
+typedef float float4 __attribute__((ext_vector_type(4)));
+
+void kernel foo(global float3 *a, global float3 *b) {
+  // CHECK: %[[LOAD_A:.*]] = load <3 x float>, <3 x float> addrspace(1)* %a
+  // CHECK: store <3 x float> %[[LOAD_A]], <3 x float> addrspace(1)* %b
+  *b = *a;
+}