[X86] Improve shift combining

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

diff --git a/test/CodeGen/X86/StackColoring.ll b/test/CodeGen/X86/StackColoring.ll
index f8ae74f292d224b51b7aaee128dba208cea50ec6..634f66ad52dea538b775f772c7f2f894a760e674 100644 (file)
--- a/test/CodeGen/X86/StackColoring.ll
+++ b/test/CodeGen/X86/StackColoring.ll
@@ -1,11 +1,12 @@
-; RUN: llc -mcpu=corei7 -no-stack-coloring=false < %s | FileCheck %s --check-prefix=YESCOLOR
-; RUN: llc -mcpu=corei7 -no-stack-coloring=true  < %s | FileCheck %s --check-prefix=NOCOLOR
+; RUN: llc -mcpu=corei7 -no-stack-coloring=false < %s | FileCheck %s --check-prefix=YESCOLOR --check-prefix=CHECK
+; RUN: llc -mcpu=corei7 -no-stack-coloring=true  < %s | FileCheck %s --check-prefix=NOCOLOR --check-prefix=CHECK
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.8.0"
 
-;YESCOLOR: subq  $136, %rsp
-;NOCOLOR: subq  $264, %rsp
+;CHECK-LABEL: myCall_w2:
+;YESCOLOR: subq  $144, %rsp
+;NOCOLOR: subq  $272, %rsp
 
 define i32 @myCall_w2(i32 %in) {
 entry:
@@ -28,6 +29,7 @@ entry:
 }
 
 
+;CHECK-LABEL: myCall2_no_merge
 ;YESCOLOR: subq  $272, %rsp
 ;NOCOLOR: subq  $272, %rsp
 
@@ -56,6 +58,7 @@ bb3:
   ret i32 0
 }
 
+;CHECK-LABEL: myCall2_w2
 ;YESCOLOR: subq  $144, %rsp
 ;NOCOLOR: subq  $272, %rsp
 
@@ -82,11 +85,10 @@ bb2:
 bb3:
   ret i32 0
 }
-;YESCOLOR: subq  $208, %rsp
-;NOCOLOR: subq  $400, %rsp
-
-
 
+;CHECK-LABEL: myCall_w4:
+;YESCOLOR: subq  $200, %rsp
+;NOCOLOR: subq  $408, %rsp
 
 define i32 @myCall_w4(i32 %in) {
 entry:
@@ -119,6 +121,7 @@ entry:
   ret i32 %t7
 }
 
+;CHECK-LABEL: myCall2_w4:
 ;YESCOLOR: subq  $112, %rsp
 ;NOCOLOR: subq  $400, %rsp
 
@@ -158,6 +161,7 @@ bb3:
 }
 
 
+;CHECK-LABEL: myCall2_noend:
 ;YESCOLOR: subq  $144, %rsp
 ;NOCOLOR: subq  $272, %rsp
 
@@ -185,6 +189,7 @@ bb3:
   ret i32 0
 }
 
+;CHECK-LABEL: myCall2_noend2:
 ;YESCOLOR: subq  $144, %rsp
 ;NOCOLOR: subq  $272, %rsp
 define i32 @myCall2_noend2(i32 %in, i1 %d) {
@@ -211,6 +216,7 @@ bb3:
 }
 
 
+;CHECK-LABEL: myCall2_nostart:
 ;YESCOLOR: subq  $144, %rsp
 ;NOCOLOR: subq  $272, %rsp
 define i32 @myCall2_nostart(i32 %in, i1 %d) {
@@ -236,6 +242,7 @@ bb3:
 }
 
 ; Adopt the test from Transforms/Inline/array_merge.ll'
+;CHECK-LABEL: array_merge:
 ;YESCOLOR: subq  $816, %rsp
 ;NOCOLOR: subq  $1616, %rsp
 define void @array_merge() nounwind ssp {
@@ -261,6 +268,7 @@ entry:
   ret void
 }
 
+;CHECK-LABEL: func_phi_lifetime:
 ;YESCOLOR: subq  $272, %rsp
 ;NOCOLOR: subq  $272, %rsp
 define i32 @func_phi_lifetime(i32 %in, i1 %d) {
@@ -297,8 +305,7 @@ bb3:
 }
 
 
-;YESCOLOR: multi_region_bb
-;NOCOLOR: multi_region_bb
+;CHECK-LABEL: multi_region_bb:
 define void @multi_region_bb() nounwind ssp {
 entry:
   %A.i1 = alloca [100 x i32], align 4
@@ -323,10 +330,9 @@ entry:
   call void @llvm.lifetime.end(i64 -1, i8* %3) nounwind
   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
@@ -350,10 +356,30 @@ bb3:
   ret i32 0
 }
 
+
+; Regression test for PR15707.  %buf1 and %buf2 should not be merged
+; in this test case.
+;CHECK-LABEL: myCall_pr15707:
+;YESCOLOR: subq $200008, %rsp
+;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
+;CHECK-LABEL: bad_range:
 define void @bad_range() nounwind ssp {
 entry:
   %A.i1 = alloca [100 x i32], align 4
@@ -378,8 +404,7 @@ block2:
 
 ; 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
+;CHECK-LABEL: shady_range:
 
 %struct.Klass = type { i32, i32 }
 
@@ -389,10 +414,10 @@ define i32 @shady_range(i32 %argc, i8** nocapture %argv) uwtable {
   %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
+  %z2 = getelementptr inbounds [4 x %struct.Klass], [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
+  %z3 = load i32, 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)
@@ -407,4 +432,3 @@ declare void @llvm.lifetime.start(i64, i8* nocapture) nounwind
 declare void @llvm.lifetime.end(i64, i8* nocapture) nounwind
 
 declare i32 @foo(i32, i8*)
-