5 files changed, 338 insertions, 2 deletions
diff --git a/test/Transforms/GlobalOpt/atexit.ll b/test/Transforms/GlobalOpt/atexit.ll
new file mode 100644
index 0000000000..dbcd0d7b00
--- /dev/null
+++ b/test/Transforms/GlobalOpt/atexit.ll
@@ -0,0 +1,6 @@
+; RUN: opt < %s -globalopt -S | FileCheck %s
+
+; CHECK: ModuleID
+define internal hidden i32 @__cxa_atexit(void (i8*)* nocapture %func, i8* nocapture %arg, i8* nocapture %dso_handle) nounwind readnone optsize noimplicitfloat {
+  unreachable
+}
diff --git a/test/Transforms/LoopVectorize/hoist-loads.ll b/test/Transforms/LoopVectorize/hoist-loads.ll
new file mode 100644
index 0000000000..fad17350cd
--- /dev/null
+++ b/test/Transforms/LoopVectorize/hoist-loads.ll
@@ -0,0 +1,69 @@
+; RUN: opt -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 -S < %s | FileCheck %s
+
+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"
+
+@A = common global [1024 x float] zeroinitializer, align 16
+@B = common global [1024 x float] zeroinitializer, align 16
+
+; Make sure we can vectorize in the presence of hoistable conditional loads.
+; CHECK: hoist_cond_load
+; CHECK: load <2 x float>
+
+define void @hoist_cond_load() {
+entry:
+  br label %for.body
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %if.end9 ]
+  %arrayidx = getelementptr inbounds [1024 x float]* @A, i64 0, i64 %indvars.iv
+  %arrayidx2 = getelementptr inbounds [1024 x float]* @B, i64 0, i64 %indvars.iv
+  %0 = load float* %arrayidx2, align 4
+  %cmp3 = fcmp oeq float %0, 0.000000e+00
+  br i1 %cmp3, label %if.end9, label %if.else
+
+if.else:
+  %1 = load float* %arrayidx, align 4
+  br label %if.end9
+
+if.end9:
+  %tmp.0 = phi float [ %1, %if.else ], [ 0.000000e+00, %for.body ]
+  store float %tmp.0, float* %arrayidx, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp ne i32 %lftr.wideiv, 1024
+  br i1 %exitcond, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
+
+; However, we can't hoist loads whose address we have not seen unconditionally
+; accessed.
+; CHECK:     dont_hoist_cond_load
+; CHECK-NOT: load <2 x float>
+
+define void @dont_hoist_cond_load() {
+entry:
+  br label %for.body
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %if.end9 ]
+  %arrayidx = getelementptr inbounds [1024 x float]* @A, i64 0, i64 %indvars.iv
+  %arrayidx2 = getelementptr inbounds [1024 x float]* @B, i64 0, i64 %indvars.iv
+  %0 = load float* %arrayidx2, align 4
+  %cmp3 = fcmp oeq float %0, 0.000000e+00
+  br i1 %cmp3, label %if.end9, label %if.else
+
+if.else:
+  %1 = load float* %arrayidx, align 4
+  br label %if.end9
+
+if.end9:
+  %tmp.0 = phi float [ %1, %if.else ], [ 0.000000e+00, %for.body ]
+  store float %tmp.0, float* %arrayidx2, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp ne i32 %lftr.wideiv, 1024
+  br i1 %exitcond, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
diff --git a/test/Transforms/LoopVectorize/induction.ll b/test/Transforms/LoopVectorize/induction.ll
new file mode 100644
index 0000000000..48bb438a86
--- /dev/null
+++ b/test/Transforms/LoopVectorize/induction.ll
@@ -0,0 +1,30 @@
+; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=2 -S | FileCheck %s
+
+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"
+
+; Make sure that we can handle multiple integer induction variables.
+; CHECK: multi_int_induction
+; CHECK: vector.body:
+; CHECK:  %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+; CHECK:  %normalized.idx = sub i64 %index, 0
+; CHECK:  %[[VAR:.*]] = trunc i64 %normalized.idx to i32
+; CHECK:  %offset.idx = add i32 190, %[[VAR]]
+define void @multi_int_induction(i32* %A, i32 %N) {
+for.body.lr.ph:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
+  %count.09 = phi i32 [ 190, %for.body.lr.ph ], [ %inc, %for.body ]
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %indvars.iv
+  store i32 %count.09, i32* %arrayidx2, align 4
+  %inc = add nsw i32 %count.09, 1
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp ne i32 %lftr.wideiv, %N
+  br i1 %exitcond, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
+
diff --git a/test/Transforms/ObjCARC/allocas.ll b/test/Transforms/ObjCARC/allocas.ll
new file mode 100644
index 0000000000..eabd54deb7
--- /dev/null
+++ b/test/Transforms/ObjCARC/allocas.ll
@@ -0,0 +1,203 @@
+; RUN: opt -objc-arc -S < %s | FileCheck %s
+
+declare i8* @objc_retain(i8*)
+declare i8* @objc_retainAutoreleasedReturnValue(i8*)
+declare void @objc_release(i8*)
+declare i8* @objc_autorelease(i8*)
+declare i8* @objc_autoreleaseReturnValue(i8*)
+declare void @objc_autoreleasePoolPop(i8*)
+declare i8* @objc_autoreleasePoolPush()
+declare i8* @objc_retainBlock(i8*)
+
+declare i8* @objc_retainedObject(i8*)
+declare i8* @objc_unretainedObject(i8*)
+declare i8* @objc_unretainedPointer(i8*)
+
+declare void @use_pointer(i8*)
+declare void @callee()
+declare void @callee_fnptr(void ()*)
+declare void @invokee()
+declare i8* @returner()
+declare void @bar(i32 ()*)
+declare void @use_alloca(i8**)
+
+declare void @llvm.dbg.value(metadata, i64, metadata)
+
+declare i8* @objc_msgSend(i8*, i8*, ...)
+
+
+; In the presense of allocas, unconditionally remove retain/release pairs only
+; if they are known safe in both directions. This prevents matching up an inner
+; retain with the boundary guarding release in the following situation:
+; 
+; %A = alloca
+; retain(%x)
+; retain(%x) <--- Inner Retain
+; store %x, %A
+; %y = load %A
+; ... DO STUFF ...
+; release(%y)
+; release(%x) <--- Guarding Release
+;
+; rdar://13750319
+
+; CHECK: define void @test1a(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_release(i8* %y)
+; CHECK: @objc_release(i8* %x)
+; CHECK: ret void
+; CHECK: }
+define void @test1a(i8* %x) {
+entry:
+  %A = alloca i8*
+  tail call i8* @objc_retain(i8* %x)
+  tail call i8* @objc_retain(i8* %x)
+  store i8* %x, i8** %A, align 8
+  %y = load i8** %A
+  call void @use_alloca(i8** %A)
+  call void @objc_release(i8* %y), !clang.imprecise_release !0
+  call void @use_pointer(i8* %x)
+  call void @objc_release(i8* %x), !clang.imprecise_release !0
+  ret void
+}
+
+; CHECK: define void @test1b(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_release(i8* %y)
+; CHECK: @objc_release(i8* %x)
+; CHECK: ret void
+; CHECK: }
+define void @test1b(i8* %x) {
+entry:
+  %A = alloca i8*
+  %gep = getelementptr i8** %A, i32 0
+  tail call i8* @objc_retain(i8* %x)
+  tail call i8* @objc_retain(i8* %x)
+  store i8* %x, i8** %gep, align 8
+  %y = load i8** %A
+  call void @use_alloca(i8** %A)
+  call void @objc_release(i8* %y), !clang.imprecise_release !0
+  call void @use_pointer(i8* %x)
+  call void @objc_release(i8* %x), !clang.imprecise_release !0
+  ret void
+}
+
+
+; CHECK: define void @test1c(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_release(i8* %y)
+; CHECK: @objc_release(i8* %x)
+; CHECK: ret void
+; CHECK: }
+define void @test1c(i8* %x) {
+entry:
+  %A = alloca i8*, i32 3
+  %gep = getelementptr i8** %A, i32 2
+  tail call i8* @objc_retain(i8* %x)
+  tail call i8* @objc_retain(i8* %x)
+  store i8* %x, i8** %gep, align 8
+  %y = load i8** %gep
+  call void @use_alloca(i8** %A)
+  call void @objc_release(i8* %y), !clang.imprecise_release !0
+  call void @use_pointer(i8* %x)
+  call void @objc_release(i8* %x), !clang.imprecise_release !0
+  ret void
+}
+
+
+; CHECK: define void @test1d(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_release(i8* %y)
+; CHECK: @objc_release(i8* %x)
+; CHECK: ret void
+; CHECK: }
+define void @test1d(i8* %x) {
+entry:
+  br i1 undef, label %use_allocaA, label %use_allocaB
+
+use_allocaA:
+  %allocaA = alloca i8*
+  br label %exit
+
+use_allocaB:
+  %allocaB = alloca i8*
+  br label %exit
+
+exit:
+  %A = phi i8** [ %allocaA, %use_allocaA ], [ %allocaB, %use_allocaB ]
+  %gep = getelementptr i8** %A, i32 0
+  tail call i8* @objc_retain(i8* %x)
+  tail call i8* @objc_retain(i8* %x)
+  store i8* %x, i8** %gep, align 8
+  %y = load i8** %gep
+  call void @use_alloca(i8** %A)
+  call void @objc_release(i8* %y), !clang.imprecise_release !0
+  call void @use_pointer(i8* %x)
+  call void @objc_release(i8* %x), !clang.imprecise_release !0
+  ret void
+}
+
+; CHECK: define void @test1e(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_release(i8* %y)
+; CHECK: @objc_release(i8* %x)
+; CHECK: ret void
+; CHECK: }
+define void @test1e(i8* %x) {
+entry:
+  br i1 undef, label %use_allocaA, label %use_allocaB
+
+use_allocaA:
+  %allocaA = alloca i8*, i32 4
+  br label %exit
+
+use_allocaB:
+  %allocaB = alloca i8*, i32 4
+  br label %exit
+
+exit:
+  %A = phi i8** [ %allocaA, %use_allocaA ], [ %allocaB, %use_allocaB ]
+  %gep = getelementptr i8** %A, i32 2
+  tail call i8* @objc_retain(i8* %x)
+  tail call i8* @objc_retain(i8* %x)
+  store i8* %x, i8** %gep, align 8
+  %y = load i8** %gep
+  call void @use_alloca(i8** %A)
+  call void @objc_release(i8* %y), !clang.imprecise_release !0
+  call void @use_pointer(i8* %x)
+  call void @objc_release(i8* %x), !clang.imprecise_release !0
+  ret void
+}
+
+; CHECK: define void @test1f(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_retain(i8* %x)
+; CHECK: @objc_release(i8* %y)
+; CHECK: @objc_release(i8* %x)
+; CHECK: ret void
+; CHECK: }
+define void @test1f(i8* %x) {
+entry:
+  %allocaOne = alloca i8*
+  %allocaTwo = alloca i8*
+  %A = select i1 undef, i8** %allocaOne, i8** %allocaTwo
+  tail call i8* @objc_retain(i8* %x)
+  tail call i8* @objc_retain(i8* %x)
+  store i8* %x, i8** %A, align 8
+  %y = load i8** %A
+  call void @use_alloca(i8** %A)
+  call void @objc_release(i8* %y), !clang.imprecise_release !0
+  call void @use_pointer(i8* %x)
+  call void @objc_release(i8* %x), !clang.imprecise_release !0
+  ret void
+}
+
+
+!0 = metadata !{}
+
+declare i32 @__gxx_personality_v0(...)
diff --git a/test/Transforms/SLPVectorizer/X86/diamond.ll b/test/Transforms/SLPVectorizer/X86/diamond.ll
index 49c8712d20..8959b0d9ee 100644
--- a/test/Transforms/SLPVectorizer/X86/diamond.ll
+++ b/test/Transforms/SLPVectorizer/X86/diamond.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
+; RUN: opt < %s -basicaa -slp-vectorizer -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
 
 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"
@@ -74,6 +74,34 @@ entry:
   %add20 = mul i32 %3, %mul238
   %arrayidx21 = getelementptr inbounds i32* %B, i64 3
   store i32 %add20, i32* %arrayidx21, align 4
-  ret i32 %0  ;<--------- This value has multiple users and can't be vectorized.
+  ret i32 %0  ;<--------- This value has multiple users
 }
 
+; In this example we have an external user that is not the first element in the vector.
+; CHECK: @extr_user1
+; CHECK: store <4 x i32>
+; CHECK-NEXT: extractelement <4 x i32>
+; CHECK: ret
+define i32 @extr_user1(i32* noalias nocapture %B, i32* noalias nocapture %A, i32 %n, i32 %m) {
+entry:
+  %0 = load i32* %A, align 4
+  %mul238 = add i32 %m, %n
+  %add = mul i32 %0, %mul238
+  store i32 %add, i32* %B, align 4
+  %arrayidx4 = getelementptr inbounds i32* %A, i64 1
+  %1 = load i32* %arrayidx4, align 4
+  %add8 = mul i32 %1, %mul238
+  %arrayidx9 = getelementptr inbounds i32* %B, i64 1
+  store i32 %add8, i32* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds i32* %A, i64 2
+  %2 = load i32* %arrayidx10, align 4
+  %add14 = mul i32 %2, %mul238
+  %arrayidx15 = getelementptr inbounds i32* %B, i64 2
+  store i32 %add14, i32* %arrayidx15, align 4
+  %arrayidx16 = getelementptr inbounds i32* %A, i64 3
+  %3 = load i32* %arrayidx16, align 4
+  %add20 = mul i32 %3, %mul238
+  %arrayidx21 = getelementptr inbounds i32* %B, i64 3
+  store i32 %add20, i32* %arrayidx21, align 4
+  ret i32 %1  ;<--------- This value has multiple users
+}