Polish atomic pointers

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

diff --git a/test/CodeGen/X86/sandybridge-loads.ll b/test/CodeGen/X86/sandybridge-loads.ll
index d85c32eaa7ec90419c9535ffc4f2e21faa83e12d..2e31154068fc848eb79e5bf502266775118f2f40 100644 (file)
--- a/test/CodeGen/X86/sandybridge-loads.ll
+++ b/test/CodeGen/X86/sandybridge-loads.ll
@@ -1,21 +1,39 @@
 ; RUN: llc -march=x86-64 -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -o - < %s | FileCheck %s
 
-;CHECK: wideloads
+;CHECK-LABEL: wideloads:
 ;CHECK: vmovaps
 ;CHECK: vinsertf128
-;CHECK: vmovups
+;CHECK: vmovaps
 ;CHECK-NOT: vinsertf128
 ;CHECK: ret
 
 define void @wideloads(<8 x float>* %a, <8 x float>* %b, <8 x float>* %c) nounwind uwtable noinline ssp {
-  %v0 = load <8 x float>* %a, align 16  ; <---- unaligned!
-  %v1 = load <8 x float>* %b, align 32  ; <---- aligned!
+  %v0 = load <8 x float>, <8 x float>* %a, align 16  ; <---- unaligned!
+  %v1 = load <8 x float>, <8 x float>* %b, align 32  ; <---- aligned!
   %m0 = fcmp olt <8 x float> %v1, %v0
-  %v2 = load <8 x float>* %c, align 16
+  %v2 = load <8 x float>, <8 x float>* %c, align 32  ; <---- aligned!
   %m1 = fcmp olt <8 x float> %v2, %v0
   %mand = and <8 x i1> %m1, %m0
   %r = zext <8 x i1> %mand to <8 x i32>
-  store <8 x i32> %r, <8 x i32>* undef, align 16
+  store <8 x i32> %r, <8 x i32>* undef, align 32
+  ret void
+}
+
+; CHECK: widestores
+; loads:
+; CHECK: vmovaps
+; CHECK: vmovaps
+; stores:
+; CHECK: vmovaps
+; CHECK: vextractf128
+; CHECK: vmovaps
+;CHECK: ret
+
+define void @widestores(<8 x float>* %a, <8 x float>* %b, <8 x float>* %c) nounwind uwtable noinline ssp {
+  %v0 = load <8 x float>, <8 x float>* %a, align 32
+  %v1 = load <8 x float>, <8 x float>* %b, align 32
+  store <8 x float> %v0, <8 x float>* %b, align 32 ; <--- aligned
+  store <8 x float> %v1, <8 x float>* %a, align 16 ; <--- unaligned
   ret void
 }