[x86] Implement a faster vector population count based on the PSHUFB

[oota-llvm.git] / test / CodeGen / X86 / 2007-01-08-InstrSched.ll

diff --git a/test/CodeGen/X86/2007-01-08-InstrSched.ll b/test/CodeGen/X86/2007-01-08-InstrSched.ll
index 3b365f35cb22104c2585338478802744490e79c9..4ec703921e29fab62cd34a63a6265de463978cbc 100644 (file)
--- a/test/CodeGen/X86/2007-01-08-InstrSched.ll
+++ b/test/CodeGen/X86/2007-01-08-InstrSched.ll
@@ -1,8 +1,7 @@
 ; PR1075
-; RUN: llvm-as < %s | llc -mtriple=x86_64-apple-darwin | \
-; RUN:   %prcontext {mulss     LCPI1_3} 1 | grep mulss | count 1
+; RUN: llc < %s -mcpu=generic -mtriple=x86_64-apple-darwin -O3 | FileCheck %s
 
-define float @foo(float %x) {
+define float @foo(float %x) nounwind {
     %tmp1 = fmul float %x, 3.000000e+00
     %tmp3 = fmul float %x, 5.000000e+00
     %tmp5 = fmul float %x, 7.000000e+00
@@ -11,4 +10,13 @@ define float @foo(float %x) {
     %tmp12 = fadd float %tmp10, %tmp5
     %tmp14 = fadd float %tmp12, %tmp7
     ret float %tmp14
+
+; CHECK: mulss
+; CHECK: mulss
+; CHECK: mulss
+; CHECK: mulss
+; CHECK: addss
+; CHECK: addss
+; CHECK: addss
+; CHECK: ret
 }