Use movups to lower memcpy and memset even if it's not fast (like corei7).
The theory is it's still faster than a pair of movq / a quad of movl. This
will probably hurt older chips like P4 but should run faster on current
and future Intel processors. rdar://8817010
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122955 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/X86/memcpy.ll b/test/CodeGen/X86/memcpy.ll
index 72342cb..4af93ad 100644
--- a/test/CodeGen/X86/memcpy.ll
+++ b/test/CodeGen/X86/memcpy.ll
@@ -37,26 +37,34 @@
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void
; LINUX: test3:
-; LINUX: memcpy
+; LINUX-NOT: memcpy
+; LINUX: movups
+; LINUX: movups
+; LINUX: movups
+; LINUX: movups
+; LINUX: movups
+; LINUX: movups
+; LINUX: movups
+; LINUX: movups
; DARWIN: test3:
; DARWIN-NOT: memcpy
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
-; DARWIN: movq
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
+; DARWIN: movups
}
; Large constant memcpy's should be inlined when not optimizing for size.