Use movups to lower memcpy and memset even if it's not fast (like corei7).

[oota-llvm.git] / test / CodeGen / X86 / memset-2.ll

diff --git a/test/CodeGen/X86/memset-2.ll b/test/CodeGen/X86/memset-2.ll
index 11f619cd6da4a0a28e11201beddc7781bafc2440..eb5597eb6ff8d21b2fe0244715e0c27c8bc211e1 100644 (file)
--- a/test/CodeGen/X86/memset-2.ll
+++ b/test/CodeGen/X86/memset-2.ll
@@ -5,7 +5,21 @@ declare void @llvm.memset.i32(i8*, i8, i32, i32) nounwind
 define fastcc void @t1() nounwind {
 entry:
 ; CHECK: t1:
-; CHECK: calll _memset
+; CHECK: pxor %xmm0, %xmm0
+; CHECK: movups %xmm0, 160
+; CHECK: movups %xmm0, 144
+; CHECK: movups %xmm0, 128
+; CHECK: movups %xmm0, 112
+; CHECK: movups %xmm0, 96
+; CHECK: movups %xmm0, 80
+; CHECK: movups %xmm0, 64
+; CHECK: movups %xmm0, 48
+; CHECK: movups %xmm0, 32
+; CHECK: movups %xmm0, 16
+; CHECK: movups %xmm0, 0
+; CHECK: movl $0, 184
+; CHECK: movl $0, 180
+; CHECK: movl $0, 176
   call void @llvm.memset.i32( i8* null, i8 0, i32 188, i32 1 ) nounwind
   unreachable
 }
@@ -28,3 +42,12 @@ entry:
 ; CHECK: imull $16843009
 }
 
+define void @t4(i8* nocapture %s, i8 %a) nounwind {
+entry:
+  tail call void @llvm.memset.p0i8.i32(i8* %s, i8 %a, i32 15, i32 1, i1 false)
+  ret void
+; CHECK: t4:
+; CHECK: imull $16843009
+; CHECK-NOT: imul
+; CHECK: ret
+}