Tidy up this testcase and add test for tailcall optimization

[oota-llvm.git] / test / CodeGen / X86 / sse3.ll

diff --git a/test/CodeGen/X86/sse3.ll b/test/CodeGen/X86/sse3.ll
index 6319cb887afdb010ee9ebccc8c00deab342ea8a8..5550d263389acc91b7d8568ddeb938a93d7ace4f 100644 (file)
--- a/test/CodeGen/X86/sse3.ll
+++ b/test/CodeGen/X86/sse3.ll
@@ -1,6 +1,6 @@
 ; These are tests for SSE3 codegen.  Yonah has SSE3 and earlier but not SSSE3+.
 
-; RUN: llc < %s -march=x86-64 -mcpu=yonah -mtriple=i686-apple-darwin9\
+; RUN: llc < %s -march=x86-64 -mcpu=yonah -mtriple=i686-apple-darwin9 -O3 \
 ; RUN:              | FileCheck %s --check-prefix=X64
 
 ; Test for v8xi16 lowering where we extract the first element of the vector and
@@ -145,7 +145,9 @@ define void @t9(<4 x float>* %r, <2 x i32>* %A) nounwind {
        ret void
 ; X64:         t9:
 ; X64:                 movsd   (%rsi), %xmm0
-; X64:                 movhps  %xmm0, (%rdi)
+; X64:         movaps  (%rdi), %xmm1
+; X64:         movlhps %xmm0, %xmm1
+; X64:         movaps  %xmm1, (%rdi)
 ; X64:                 ret
 }