Fix sse2.psrl.w and sse2.psrl.q definitions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@45772 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 38 insertions, 4 deletions

diff --git a/include/llvm/IntrinsicsX86.td b/include/llvm/IntrinsicsX86.td
index 5405902..28a4472 100644
--- a/include/llvm/IntrinsicsX86.td
+++ b/include/llvm/IntrinsicsX86.td
@@ -329,13 +329,13 @@ let TargetPrefix = "x86" in {  // All intrinsics start with "llvm.x86.".
                          llvm_i32_ty], [IntrNoMem]>;
   def int_x86_sse2_psrl_w : GCCBuiltin<"__builtin_ia32_psrlw128">,
               Intrinsic<[llvm_v8i16_ty, llvm_v8i16_ty,
-                         llvm_v4i32_ty], [IntrNoMem]>;
+                         llvm_v8i16_ty], [IntrNoMem]>;
   def int_x86_sse2_psrl_d : GCCBuiltin<"__builtin_ia32_psrld128">,
               Intrinsic<[llvm_v4i32_ty, llvm_v4i32_ty,
                          llvm_v4i32_ty], [IntrNoMem]>;
   def int_x86_sse2_psrl_q : GCCBuiltin<"__builtin_ia32_psrlq128">,
               Intrinsic<[llvm_v2i64_ty, llvm_v2i64_ty,
-                         llvm_v4i32_ty], [IntrNoMem]>;
+                         llvm_v2i64_ty], [IntrNoMem]>;
   def int_x86_sse2_psrl_dq : GCCBuiltin<"__builtin_ia32_psrldqi128">,
               Intrinsic<[llvm_v2i64_ty, llvm_v2i64_ty,
                          llvm_i32_ty], [IntrNoMem]>;
diff --git a/test/CodeGen/X86/2007-05-17-ShuffleISelBug.ll b/test/CodeGen/X86/2007-05-17-ShuffleISelBug.ll
index 33ff755..64ccef3 100644
--- a/test/CodeGen/X86/2007-05-17-ShuffleISelBug.ll
+++ b/test/CodeGen/X86/2007-05-17-ShuffleISelBug.ll
@@ -3,7 +3,7 @@
 
 declare <8 x i16> @llvm.x86.sse2.packuswb.128(<8 x i16>, <8 x i16>)
 
-declare <8 x i16> @llvm.x86.sse2.psrl.w(<8 x i16>, <4 x i32>)
+declare <8 x i16> @llvm.x86.sse2.psrl.w(<8 x i16>, <8 x i16>)
 
 define fastcc void @test(i32* %src, i32 %sbpr, i32* %dst, i32 %dbpr, i32 %w, i32 %h, i32 %dstalpha, i32 %mask) {
 	%tmp633 = shufflevector <8 x i16> zeroinitializer, <8 x i16> undef, <8 x i32> < i32 4, i32 4, i32 5, i32 5, i32 6, i32 6, i32 7, i32 7 >
@@ -12,7 +12,7 @@ define fastcc void @test(i32* %src, i32 %sbpr, i32* %dst, i32 %dbpr, i32 %w, i32
 	%tmp777 = add <4 x i32> %tmp776, shufflevector (<4 x i32> < i32 65537, i32 0, i32 0, i32 0 >, <4 x i32> < i32 65537, i32 0, i32 0, i32 0 >, <4 x i32> zeroinitializer)
 	%tmp805 = add <4 x i32> %tmp777, zeroinitializer
 	%tmp832 = bitcast <4 x i32> %tmp805 to <8 x i16>
-	%tmp838 = tail call <8 x i16> @llvm.x86.sse2.psrl.w( <8 x i16> %tmp832, <4 x i32> < i32 8, i32 undef, i32 undef, i32 undef > )
+	%tmp838 = tail call <8 x i16> @llvm.x86.sse2.psrl.w( <8 x i16> %tmp832, <8 x i16> < i16 8, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef > )
 	%tmp1020 = tail call <8 x i16> @llvm.x86.sse2.packuswb.128( <8 x i16> zeroinitializer, <8 x i16> %tmp838 )
 	%tmp1030 = bitcast <8 x i16> %tmp1020 to <4 x i32>
 	%tmp1033 = add <4 x i32> zeroinitializer, %tmp1030
diff --git a/test/CodeGen/X86/vec_shift.ll b/test/CodeGen/X86/vec_shift.ll
new file mode 100644
index 0000000..9c595bc
--- /dev/null
+++ b/test/CodeGen/X86/vec_shift.ll
@@ -0,0 +1,34 @@
+; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep psllw
+; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep psrlq
+; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep psraw
+
+define <2 x i64> @t1(<2 x i64> %b1, <2 x i64> %c) nounwind  {
+entry:
+	%tmp6 = bitcast <2 x i64> %c to <8 x i16>		; <<8 x i16>> [#uses=1]
+	%tmp8 = bitcast <2 x i64> %b1 to <8 x i16>		; <<8 x i16>> [#uses=1]
+	%tmp9 = tail call <8 x i16> @llvm.x86.sse2.psll.w( <8 x i16> %tmp8, <8 x i16> %tmp6 ) nounwind readnone 		; <<8 x i16>> [#uses=1]
+	%tmp10 = bitcast <8 x i16> %tmp9 to <2 x i64>		; <<2 x i64>> [#uses=1]
+	ret <2 x i64> %tmp10
+}
+
+define <2 x i64> @t3(<2 x i64> %b1, i32 %c) nounwind  {
+entry:
+	%tmp2 = bitcast <2 x i64> %b1 to <8 x i16>		; <<8 x i16>> [#uses=1]
+	%tmp4 = insertelement <4 x i32> undef, i32 %c, i32 0		; <<4 x i32>> [#uses=1]
+	%tmp8 = bitcast <4 x i32> %tmp4 to <8 x i16>		; <<8 x i16>> [#uses=1]
+	%tmp9 = tail call <8 x i16> @llvm.x86.sse2.psra.w( <8 x i16> %tmp2, <8 x i16> %tmp8 )		; <<8 x i16>> [#uses=1]
+	%tmp11 = bitcast <8 x i16> %tmp9 to <2 x i64>		; <<2 x i64>> [#uses=1]
+	ret <2 x i64> %tmp11
+}
+
+declare <8 x i16> @llvm.x86.sse2.psra.w(<8 x i16>, <8 x i16>) nounwind readnone 
+
+define <2 x i64> @t2(<2 x i64> %b1, <2 x i64> %c) nounwind  {
+entry:
+	%tmp9 = tail call <2 x i64> @llvm.x86.sse2.psrl.q( <2 x i64> %b1, <2 x i64> %c ) nounwind readnone 		; <<2 x i64>> [#uses=1]
+	ret <2 x i64> %tmp9
+}
+
+declare <2 x i64> @llvm.x86.sse2.psrl.q(<2 x i64>, <2 x i64>) nounwind readnone 
+
+declare <8 x i16> @llvm.x86.sse2.psll.w(<8 x i16>, <8 x i16>) nounwind readnone