R600: Fix R600ControlFlowFinalizer not considering VTX_READ 128 bit dst reg

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

diff --git a/test/CodeGen/X86/StackColoring.ll b/test/CodeGen/X86/StackColoring.ll
index 6ef3b3cd023223d4da6b71ca9fe38e1612658d7c..6c0f00d17d5acaa19a0cdebf09d09192079e25d3 100644 (file)
--- a/test/CodeGen/X86/StackColoring.ll
+++ b/test/CodeGen/X86/StackColoring.ll
@@ -7,7 +7,6 @@ target triple = "x86_64-apple-macosx10.8.0"
 ;YESCOLOR: subq  $136, %rsp
 ;NOCOLOR: subq  $264, %rsp
 
-
 define i32 @myCall_w2(i32 %in) {
 entry:
   %a = alloca [17 x i8*], align 8
@@ -325,11 +324,109 @@ entry:
   ret void
 }
 
+
+;YESCOLOR: subq  $272, %rsp
+;NOCOLOR: subq  $272, %rsp
+define i32 @myCall_end_before_begin(i32 %in, i1 %d) {
+entry:
+  %a = alloca [17 x i8*], align 8
+  %a2 = alloca [16 x i8*], align 8
+  %b = bitcast [17 x i8*]* %a to i8*
+  %b2 = bitcast [16 x i8*]* %a2 to i8*
+  %t1 = call i32 @foo(i32 %in, i8* %b)
+  %t2 = call i32 @foo(i32 %in, i8* %b)
+  call void @llvm.lifetime.end(i64 -1, i8* %b)
+  call void @llvm.lifetime.start(i64 -1, i8* %b)
+  br i1 %d, label %bb2, label %bb3
+bb2:
+  call void @llvm.lifetime.start(i64 -1, i8* %b2)
+  %t3 = call i32 @foo(i32 %in, i8* %b2)
+  %t4 = call i32 @foo(i32 %in, i8* %b2)
+  %t5 = add i32 %t1, %t2
+  %t6 = add i32 %t3, %t4
+  %t7 = add i32 %t5, %t6
+  ret i32 %t7
+bb3:
+  ret i32 0
+}
+
+
+; Regression test for PR15707.  %buf1 and %buf2 should not be merged
+; in this test case.
+;YESCOLOR: myCall_pr15707
+;YESCOLOR: subq $200008, %rsp
+;NOCOLOR: myCall_pr15707
+;NOCOLOR: subq $200008, %rsp
+define void @myCall_pr15707() {
+  %buf1 = alloca i8, i32 100000, align 16
+  %buf2 = alloca i8, i32 100000, align 16
+
+  call void @llvm.lifetime.start(i64 -1, i8* %buf1)
+  call void @llvm.lifetime.end(i64 -1, i8* %buf1)
+
+  call void @llvm.lifetime.start(i64 -1, i8* %buf1)
+  call void @llvm.lifetime.start(i64 -1, i8* %buf2)
+  %result1 = call i32 @foo(i32 0, i8* %buf1)
+  %result2 = call i32 @foo(i32 0, i8* %buf2)
+  ret void
+}
+
+
+; Check that we don't assert and crash even when there are allocas
+; outside the declared lifetime regions.
+;YESCOLOR: bad_range
+;NOCOLOR:  bad_range
+define void @bad_range() nounwind ssp {
+entry:
+  %A.i1 = alloca [100 x i32], align 4
+  %B.i2 = alloca [100 x i32], align 4
+  %A.i = alloca [100 x i32], align 4
+  %B.i = alloca [100 x i32], align 4
+  %0 = bitcast [100 x i32]* %A.i to i8*
+  call void @llvm.lifetime.start(i64 -1, i8* %0) nounwind
+  %1 = bitcast [100 x i32]* %B.i to i8*
+  call void @llvm.lifetime.start(i64 -1, i8* %1) nounwind
+  call void @bar([100 x i32]* %A.i, [100 x i32]* %B.i) nounwind
+  call void @llvm.lifetime.end(i64 -1, i8* %0) nounwind
+  call void @llvm.lifetime.end(i64 -1, i8* %1) nounwind
+  br label %block2
+
+block2:
+  ; I am used outside the marked lifetime.
+  call void @bar([100 x i32]* %A.i, [100 x i32]* %B.i) nounwind
+  ret void
+}
+
+
+; Check that we don't assert and crash even when there are usages
+; of allocas which do not read or write outside the declared lifetime regions.
+;YESCOLOR: shady_range
+;NOCOLOR:  shady_range
+
+%struct.Klass = type { i32, i32 }
+
+define i32 @shady_range(i32 %argc, i8** nocapture %argv) uwtable {
+  %a.i = alloca [4 x %struct.Klass], align 16
+  %b.i = alloca [4 x %struct.Klass], align 16
+  %a8 = bitcast [4 x %struct.Klass]* %a.i to i8*
+  %b8 = bitcast [4 x %struct.Klass]* %b.i to i8*
+  ; I am used outside the lifetime zone below:
+  %z2 = getelementptr inbounds [4 x %struct.Klass]* %a.i, i64 0, i64 0, i32 0
+  call void @llvm.lifetime.start(i64 -1, i8* %a8)
+  call void @llvm.lifetime.start(i64 -1, i8* %b8)
+  %z3 = load i32* %z2, align 16
+  %r = call i32 @foo(i32 %z3, i8* %a8)
+  %r2 = call i32 @foo(i32 %z3, i8* %b8)
+  call void @llvm.lifetime.end(i64 -1, i8* %a8)
+  call void @llvm.lifetime.end(i64 -1, i8* %b8)
+  ret i32 9
+}
+
 declare void @bar([100 x i32]* , [100 x i32]*) nounwind
 
 declare void @llvm.lifetime.start(i64, i8* nocapture) nounwind
 
 declare void @llvm.lifetime.end(i64, i8* nocapture) nounwind
 
- declare i32 @foo(i32, i8*)
+declare i32 @foo(i32, i8*)