Fix return type for X86 mpsadbw instrinsic. The instruction takes in a vector of...

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@143313 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/IntrinsicsX86.td b/include/llvm/IntrinsicsX86.td
index 2bad822abeed045fa391bb649c2cbb32f8ab5944..46e47ab082c42533585ef8617cd92cd6b806255b 100644 (file)
--- a/include/llvm/IntrinsicsX86.td
+++ b/include/llvm/IntrinsicsX86.td
@@ -919,7 +919,7 @@ let TargetPrefix = "x86" in {  // All intrinsics start with "llvm.x86.".
 // Vector sum of absolute differences
 let TargetPrefix = "x86" in {  // All intrinsics start with "llvm.x86.".
   def int_x86_sse41_mpsadbw         : GCCBuiltin<"__builtin_ia32_mpsadbw128">,
-          Intrinsic<[llvm_v16i8_ty], [llvm_v16i8_ty, llvm_v16i8_ty,llvm_i32_ty],
+          Intrinsic<[llvm_v8i16_ty], [llvm_v16i8_ty, llvm_v16i8_ty,llvm_i32_ty],
                     [IntrNoMem, Commutative]>;
 }
 

diff --git a/test/CodeGen/X86/avx-intrinsics-x86.ll b/test/CodeGen/X86/avx-intrinsics-x86.ll
index 5201688686d3b5c5f544b63c05854e86148617cc..0e2a671e4cdbac87c06160d315ce4b45a81d7318 100644 (file)
--- a/test/CodeGen/X86/avx-intrinsics-x86.ll
+++ b/test/CodeGen/X86/avx-intrinsics-x86.ll
@@ -964,12 +964,12 @@ define <2 x i64> @test_x86_sse41_movntdqa(i8* %a0) {
 declare <2 x i64> @llvm.x86.sse41.movntdqa(i8*) nounwind readonly
 
 
-define <16 x i8> @test_x86_sse41_mpsadbw(<16 x i8> %a0, <16 x i8> %a1) {
+define <8 x i16> @test_x86_sse41_mpsadbw(<16 x i8> %a0, <16 x i8> %a1) {
   ; CHECK: vmpsadbw
-  %res = call <16 x i8> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<16 x i8>> [#uses=1]
-  ret <16 x i8> %res
+  %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
 }
-declare <16 x i8> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i32) nounwind readnone
+declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i32) nounwind readnone
 
 
 define <8 x i16> @test_x86_sse41_packusdw(<4 x i32> %a0, <4 x i32> %a1) {