diff --git a/include/llvm/IntrinsicsX86.td b/include/llvm/IntrinsicsX86.td
index ed563862c73..2092c810dde 100644
--- a/include/llvm/IntrinsicsX86.td
+++ b/include/llvm/IntrinsicsX86.td
@@ -655,8 +655,8 @@ let TargetPrefix = "x86" in {  // All intrinsics start with "llvm.x86.".
               Intrinsic<[llvm_x86mmx_ty], [llvm_x86mmx_ty,
                          llvm_x86mmx_ty], [IntrNoMem]>;
   def int_x86_ssse3_pmadd_ub_sw_128 : GCCBuiltin<"__builtin_ia32_pmaddubsw128">,
-              Intrinsic<[llvm_v8i16_ty], [llvm_v8i16_ty,
-                         llvm_v8i16_ty], [IntrNoMem]>;
+              Intrinsic<[llvm_v8i16_ty], [llvm_v16i8_ty,
+                         llvm_v16i8_ty], [IntrNoMem]>;
 }
 
 // Packed multiply high with round and scale
diff --git a/test/CodeGen/X86/avx-intrinsics-x86.ll b/test/CodeGen/X86/avx-intrinsics-x86.ll
index 50170f6c2c3..2aad672d2c6 100644
--- a/test/CodeGen/X86/avx-intrinsics-x86.ll
+++ b/test/CodeGen/X86/avx-intrinsics-x86.ll
@@ -1783,12 +1783,12 @@ define <8 x i16> @test_x86_ssse3_phsub_w_128(<8 x i16> %a0, <8 x i16> %a1) {
 declare <8 x i16> @llvm.x86.ssse3.phsub.w.128(<8 x i16>, <8 x i16>) nounwind readnone
 
 
-define <8 x i16> @test_x86_ssse3_pmadd_ub_sw_128(<8 x i16> %a0, <8 x i16> %a1) {
+define <8 x i16> @test_x86_ssse3_pmadd_ub_sw_128(<16 x i8> %a0, <16 x i8> %a1) {
   ; CHECK: vpmaddubsw
-  %res = call <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
+  %res = call <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<16 x i8> %a0, <16 x i8> %a1) ; <<8 x i16>> [#uses=1]
   ret <8 x i16> %res
 }
-declare <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<8 x i16>, <8 x i16>) nounwind readnone
+declare <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<16 x i8>, <16 x i8>) nounwind readnone
 
 
 define <8 x i16> @test_x86_ssse3_pmul_hr_sw_128(<8 x i16> %a0, <8 x i16> %a1) {