Update LLVM sources to r73879.vendor/llvm/llvm-r73879

15 files changed, 390 insertions, 14 deletions

diff --git a/test/CodeGen/X86/2009-06-15-not-a-tail-call.ll b/test/CodeGen/X86/2009-06-15-not-a-tail-call.ll
new file mode 100644
index 000000000000..095e6a103621
--- /dev/null
+++ b/test/CodeGen/X86/2009-06-15-not-a-tail-call.ll
@@ -0,0 +1,14 @@
+; RUN: llvm-as < %s | llc -march=x86 -tailcallopt | not grep TAILCALL 
+
+; Bug 4396. This tail call can NOT be optimized.
+
+declare fastcc i8* @_D3gcx2GC12mallocNoSyncMFmkZPv() nounwind
+
+define fastcc i8* @_D3gcx2GC12callocNoSyncMFmkZPv() nounwind {
+entry:
+	%tmp6 = tail call fastcc i8* @_D3gcx2GC12mallocNoSyncMFmkZPv()		; <i8*> [#uses=2]
+	%tmp9 = tail call i8* @memset(i8* %tmp6, i32 0, i64 2)		; <i8*> [#uses=0]
+	ret i8* %tmp6
+}
+
+declare i8* @memset(i8*, i32, i64)
diff --git a/test/CodeGen/X86/2009-06-18-movlp-shuffle-register.ll b/test/CodeGen/X86/2009-06-18-movlp-shuffle-register.ll
new file mode 100644
index 000000000000..d6ff5b6803e3
--- /dev/null
+++ b/test/CodeGen/X86/2009-06-18-movlp-shuffle-register.ll
@@ -0,0 +1,9 @@
+; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse,-sse2
+; PR2484
+
+define <4 x float> @f4523(<4 x float> %a,<4 x float> %b) nounwind {
+entry:
+%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 4,i32
+5,i32 2,i32 3>
+ret <4 x float> %shuffle
+}
diff --git a/test/CodeGen/X86/fmul-zero.ll b/test/CodeGen/X86/fmul-zero.ll
index 8f705a4d242f..73aa713de52e 100644
--- a/test/CodeGen/X86/fmul-zero.ll
+++ b/test/CodeGen/X86/fmul-zero.ll
@@ -3,7 +3,7 @@
 
 define void @test14(<4 x float>*) nounwind {
         load <4 x float>* %0, align 1
-        mul <4 x float> %2, zeroinitializer
+        fmul <4 x float> %2, zeroinitializer
         store <4 x float> %3, <4 x float>* %0, align 1
         ret void
 }
diff --git a/test/CodeGen/X86/inline-asm-fpstack2.ll b/test/CodeGen/X86/inline-asm-fpstack2.ll
new file mode 100644
index 000000000000..968561826b5c
--- /dev/null
+++ b/test/CodeGen/X86/inline-asm-fpstack2.ll
@@ -0,0 +1,10 @@
+; RUN: llvm-as < %s | llc -march=x86 > %t
+; RUN: grep {fld	%%st(0)} %t
+; PR4185
+
+define void @test() {
+return:
+	call void asm sideeffect "fistpl $0", "{st}"(double 1.000000e+06)
+	call void asm sideeffect "fistpl $0", "{st}"(double 1.000000e+06)
+	ret void
+}
diff --git a/test/CodeGen/X86/iv-users-in-other-loops.ll b/test/CodeGen/X86/iv-users-in-other-loops.ll
index 2208b2d2e0e3..a48f0616291f 100644
--- a/test/CodeGen/X86/iv-users-in-other-loops.ll
+++ b/test/CodeGen/X86/iv-users-in-other-loops.ll
@@ -1,11 +1,11 @@
 ; RUN: llvm-as < %s | llc -march=x86-64 -f -o %t
 ; RUN: grep inc %t | count 1
 ; RUN: grep dec %t | count 2
-; RUN: grep addq %t | count 8
-; RUN: grep addb %t | count 2
-; RUN: grep leaq %t | count 12
-; RUN: grep leal %t | count 2
-; RUN: grep movq %t | count 4
+; RUN: grep addq %t | count 13
+; RUN: not grep addb %t
+; RUN: grep leaq %t | count 8
+; RUN: grep leal %t | count 4
+; RUN: grep movq %t | count 5
 
 ; IV users in each of the loops from other loops shouldn't cause LSR
 ; to insert new induction variables. Previously it would create a
diff --git a/test/CodeGen/X86/optimize-smax.ll b/test/CodeGen/X86/optimize-max-0.ll
index 0c3be31e293f..90c14565e9a6 100644
--- a/test/CodeGen/X86/optimize-smax.ll
+++ b/test/CodeGen/X86/optimize-max-0.ll
@@ -1,7 +1,7 @@
 ; RUN: llvm-as < %s | llc -march=x86 | not grep cmov
 
-; LSR should be able to eliminate the smax computations by
-; making the loops use slt comparisons instead of ne comparisons.
+; LSR should be able to eliminate the max computations by
+; making the loops use slt/ult comparisons instead of ne comparisons.
 
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
 target triple = "i386-apple-darwin9"
@@ -231,6 +231,231 @@ return:		; preds = %bb20
 	ret void
 }
 
+define void @bar(i8* %r, i32 %s, i32 %w, i32 %x, i8* %j, i32 %d) nounwind {
+entry:
+	%0 = mul i32 %x, %w		; <i32> [#uses=2]
+	%1 = mul i32 %x, %w		; <i32> [#uses=1]
+	%2 = udiv i32 %1, 4		; <i32> [#uses=1]
+	%.sum2 = add i32 %2, %0		; <i32> [#uses=2]
+	%cond = icmp eq i32 %d, 1		; <i1> [#uses=1]
+	br i1 %cond, label %bb29, label %bb10.preheader
+
+bb10.preheader:		; preds = %entry
+	%3 = icmp ne i32 %x, 0		; <i1> [#uses=1]
+	br i1 %3, label %bb.nph9, label %bb18.loopexit
+
+bb.nph7:		; preds = %bb7.preheader
+	%4 = mul i32 %y.08, %w		; <i32> [#uses=1]
+	%5 = mul i32 %y.08, %s		; <i32> [#uses=1]
+	%6 = add i32 %5, 1		; <i32> [#uses=1]
+	%tmp8 = icmp ugt i32 1, %w		; <i1> [#uses=1]
+	%smax9 = select i1 %tmp8, i32 1, i32 %w		; <i32> [#uses=1]
+	br label %bb6
+
+bb6:		; preds = %bb7, %bb.nph7
+	%x.06 = phi i32 [ 0, %bb.nph7 ], [ %indvar.next7, %bb7 ]		; <i32> [#uses=3]
+	%7 = add i32 %x.06, %4		; <i32> [#uses=1]
+	%8 = shl i32 %x.06, 1		; <i32> [#uses=1]
+	%9 = add i32 %6, %8		; <i32> [#uses=1]
+	%10 = getelementptr i8* %r, i32 %9		; <i8*> [#uses=1]
+	%11 = load i8* %10, align 1		; <i8> [#uses=1]
+	%12 = getelementptr i8* %j, i32 %7		; <i8*> [#uses=1]
+	store i8 %11, i8* %12, align 1
+	br label %bb7
+
+bb7:		; preds = %bb6
+	%indvar.next7 = add i32 %x.06, 1		; <i32> [#uses=2]
+	%exitcond10 = icmp ne i32 %indvar.next7, %smax9		; <i1> [#uses=1]
+	br i1 %exitcond10, label %bb6, label %bb7.bb9_crit_edge
+
+bb7.bb9_crit_edge:		; preds = %bb7
+	br label %bb9
+
+bb9:		; preds = %bb7.preheader, %bb7.bb9_crit_edge
+	br label %bb10
+
+bb10:		; preds = %bb9
+	%indvar.next11 = add i32 %y.08, 1		; <i32> [#uses=2]
+	%exitcond12 = icmp ne i32 %indvar.next11, %x		; <i1> [#uses=1]
+	br i1 %exitcond12, label %bb7.preheader, label %bb10.bb18.loopexit_crit_edge
+
+bb10.bb18.loopexit_crit_edge:		; preds = %bb10
+	br label %bb10.bb18.loopexit_crit_edge.split
+
+bb10.bb18.loopexit_crit_edge.split:		; preds = %bb.nph9, %bb10.bb18.loopexit_crit_edge
+	br label %bb18.loopexit
+
+bb.nph9:		; preds = %bb10.preheader
+	%13 = icmp ugt i32 %w, 0		; <i1> [#uses=1]
+	br i1 %13, label %bb.nph9.split, label %bb10.bb18.loopexit_crit_edge.split
+
+bb.nph9.split:		; preds = %bb.nph9
+	br label %bb7.preheader
+
+bb7.preheader:		; preds = %bb.nph9.split, %bb10
+	%y.08 = phi i32 [ 0, %bb.nph9.split ], [ %indvar.next11, %bb10 ]		; <i32> [#uses=3]
+	br i1 true, label %bb.nph7, label %bb9
+
+bb.nph5:		; preds = %bb18.loopexit
+	%14 = udiv i32 %w, 2		; <i32> [#uses=1]
+	%15 = icmp ult i32 %w, 2		; <i1> [#uses=1]
+	%16 = udiv i32 %x, 2		; <i32> [#uses=2]
+	br i1 %15, label %bb18.bb20_crit_edge.split, label %bb.nph5.split
+
+bb.nph5.split:		; preds = %bb.nph5
+	%tmp2 = icmp ugt i32 1, %16		; <i1> [#uses=1]
+	%smax3 = select i1 %tmp2, i32 1, i32 %16		; <i32> [#uses=1]
+	br label %bb13
+
+bb13:		; preds = %bb18, %bb.nph5.split
+	%y.14 = phi i32 [ 0, %bb.nph5.split ], [ %indvar.next1, %bb18 ]		; <i32> [#uses=4]
+	%17 = mul i32 %14, %y.14		; <i32> [#uses=2]
+	%18 = shl i32 %y.14, 1		; <i32> [#uses=1]
+	%19 = urem i32 %y.14, 2		; <i32> [#uses=1]
+	%20 = add i32 %19, %18		; <i32> [#uses=1]
+	%21 = mul i32 %20, %s		; <i32> [#uses=2]
+	br i1 true, label %bb.nph3, label %bb17
+
+bb.nph3:		; preds = %bb13
+	%22 = add i32 %17, %0		; <i32> [#uses=1]
+	%23 = add i32 %17, %.sum2		; <i32> [#uses=1]
+	%24 = udiv i32 %w, 2		; <i32> [#uses=2]
+	%tmp = icmp ugt i32 1, %24		; <i1> [#uses=1]
+	%smax = select i1 %tmp, i32 1, i32 %24		; <i32> [#uses=1]
+	br label %bb14
+
+bb14:		; preds = %bb15, %bb.nph3
+	%x.12 = phi i32 [ 0, %bb.nph3 ], [ %indvar.next, %bb15 ]		; <i32> [#uses=5]
+	%25 = shl i32 %x.12, 2		; <i32> [#uses=1]
+	%26 = add i32 %25, %21		; <i32> [#uses=1]
+	%27 = getelementptr i8* %r, i32 %26		; <i8*> [#uses=1]
+	%28 = load i8* %27, align 1		; <i8> [#uses=1]
+	%.sum = add i32 %22, %x.12		; <i32> [#uses=1]
+	%29 = getelementptr i8* %j, i32 %.sum		; <i8*> [#uses=1]
+	store i8 %28, i8* %29, align 1
+	%30 = shl i32 %x.12, 2		; <i32> [#uses=1]
+	%31 = or i32 %30, 2		; <i32> [#uses=1]
+	%32 = add i32 %31, %21		; <i32> [#uses=1]
+	%33 = getelementptr i8* %r, i32 %32		; <i8*> [#uses=1]
+	%34 = load i8* %33, align 1		; <i8> [#uses=1]
+	%.sum6 = add i32 %23, %x.12		; <i32> [#uses=1]
+	%35 = getelementptr i8* %j, i32 %.sum6		; <i8*> [#uses=1]
+	store i8 %34, i8* %35, align 1
+	br label %bb15
+
+bb15:		; preds = %bb14
+	%indvar.next = add i32 %x.12, 1		; <i32> [#uses=2]
+	%exitcond = icmp ne i32 %indvar.next, %smax		; <i1> [#uses=1]
+	br i1 %exitcond, label %bb14, label %bb15.bb17_crit_edge
+
+bb15.bb17_crit_edge:		; preds = %bb15
+	br label %bb17
+
+bb17:		; preds = %bb15.bb17_crit_edge, %bb13
+	br label %bb18
+
+bb18.loopexit:		; preds = %bb10.bb18.loopexit_crit_edge.split, %bb10.preheader
+	%36 = icmp ult i32 %x, 2		; <i1> [#uses=1]
+	br i1 %36, label %bb20, label %bb.nph5
+
+bb18:		; preds = %bb17
+	%indvar.next1 = add i32 %y.14, 1		; <i32> [#uses=2]
+	%exitcond4 = icmp ne i32 %indvar.next1, %smax3		; <i1> [#uses=1]
+	br i1 %exitcond4, label %bb13, label %bb18.bb20_crit_edge
+
+bb18.bb20_crit_edge:		; preds = %bb18
+	br label %bb18.bb20_crit_edge.split
+
+bb18.bb20_crit_edge.split:		; preds = %bb18.bb20_crit_edge, %bb.nph5
+	br label %bb20
+
+bb20:		; preds = %bb18.bb20_crit_edge.split, %bb18.loopexit
+	switch i32 %d, label %return [
+		i32 3, label %bb22
+		i32 1, label %bb29
+	]
+
+bb22:		; preds = %bb20
+	%37 = mul i32 %x, %w		; <i32> [#uses=1]
+	%38 = udiv i32 %37, 4		; <i32> [#uses=1]
+	%.sum3 = add i32 %38, %.sum2		; <i32> [#uses=2]
+	%39 = add i32 %x, 15		; <i32> [#uses=1]
+	%40 = and i32 %39, -16		; <i32> [#uses=1]
+	%41 = add i32 %w, 15		; <i32> [#uses=1]
+	%42 = and i32 %41, -16		; <i32> [#uses=1]
+	%43 = mul i32 %40, %s		; <i32> [#uses=1]
+	%44 = icmp ugt i32 %x, 0		; <i1> [#uses=1]
+	br i1 %44, label %bb.nph, label %bb26
+
+bb.nph:		; preds = %bb22
+	br label %bb23
+
+bb23:		; preds = %bb24, %bb.nph
+	%y.21 = phi i32 [ 0, %bb.nph ], [ %indvar.next5, %bb24 ]		; <i32> [#uses=3]
+	%45 = mul i32 %y.21, %42		; <i32> [#uses=1]
+	%.sum1 = add i32 %45, %43		; <i32> [#uses=1]
+	%46 = getelementptr i8* %r, i32 %.sum1		; <i8*> [#uses=1]
+	%47 = mul i32 %y.21, %w		; <i32> [#uses=1]
+	%.sum5 = add i32 %47, %.sum3		; <i32> [#uses=1]
+	%48 = getelementptr i8* %j, i32 %.sum5		; <i8*> [#uses=1]
+	tail call void @llvm.memcpy.i32(i8* %48, i8* %46, i32 %w, i32 1)
+	br label %bb24
+
+bb24:		; preds = %bb23
+	%indvar.next5 = add i32 %y.21, 1		; <i32> [#uses=2]
+	%exitcond6 = icmp ne i32 %indvar.next5, %x		; <i1> [#uses=1]
+	br i1 %exitcond6, label %bb23, label %bb24.bb26_crit_edge
+
+bb24.bb26_crit_edge:		; preds = %bb24
+	br label %bb26
+
+bb26:		; preds = %bb24.bb26_crit_edge, %bb22
+	%49 = mul i32 %x, %w		; <i32> [#uses=1]
+	%.sum4 = add i32 %.sum3, %49		; <i32> [#uses=1]
+	%50 = getelementptr i8* %j, i32 %.sum4		; <i8*> [#uses=1]
+	%51 = mul i32 %x, %w		; <i32> [#uses=1]
+	%52 = udiv i32 %51, 2		; <i32> [#uses=1]
+	tail call void @llvm.memset.i32(i8* %50, i8 -128, i32 %52, i32 1)
+	ret void
+
+bb29:		; preds = %bb20, %entry
+	%53 = add i32 %w, 15		; <i32> [#uses=1]
+	%54 = and i32 %53, -16		; <i32> [#uses=1]
+	%55 = icmp ugt i32 %x, 0		; <i1> [#uses=1]
+	br i1 %55, label %bb.nph11, label %bb33
+
+bb.nph11:		; preds = %bb29
+	br label %bb30
+
+bb30:		; preds = %bb31, %bb.nph11
+	%y.310 = phi i32 [ 0, %bb.nph11 ], [ %indvar.next13, %bb31 ]		; <i32> [#uses=3]
+	%56 = mul i32 %y.310, %54		; <i32> [#uses=1]
+	%57 = getelementptr i8* %r, i32 %56		; <i8*> [#uses=1]
+	%58 = mul i32 %y.310, %w		; <i32> [#uses=1]
+	%59 = getelementptr i8* %j, i32 %58		; <i8*> [#uses=1]
+	tail call void @llvm.memcpy.i32(i8* %59, i8* %57, i32 %w, i32 1)
+	br label %bb31
+
+bb31:		; preds = %bb30
+	%indvar.next13 = add i32 %y.310, 1		; <i32> [#uses=2]
+	%exitcond14 = icmp ne i32 %indvar.next13, %x		; <i1> [#uses=1]
+	br i1 %exitcond14, label %bb30, label %bb31.bb33_crit_edge
+
+bb31.bb33_crit_edge:		; preds = %bb31
+	br label %bb33
+
+bb33:		; preds = %bb31.bb33_crit_edge, %bb29
+	%60 = mul i32 %x, %w		; <i32> [#uses=1]
+	%61 = getelementptr i8* %j, i32 %60		; <i8*> [#uses=1]
+	%62 = mul i32 %x, %w		; <i32> [#uses=1]
+	%63 = udiv i32 %62, 2		; <i32> [#uses=1]
+	tail call void @llvm.memset.i32(i8* %61, i8 -128, i32 %63, i32 1)
+	ret void
+
+return:		; preds = %bb20
+	ret void
+}
+
 declare void @llvm.memcpy.i32(i8*, i8*, i32, i32) nounwind
 
 declare void @llvm.memset.i32(i8*, i8, i32, i32) nounwind
diff --git a/test/CodeGen/X86/optimize-max-1.ll b/test/CodeGen/X86/optimize-max-1.ll
new file mode 100644
index 000000000000..084e1818f5dd
--- /dev/null
+++ b/test/CodeGen/X86/optimize-max-1.ll
@@ -0,0 +1,78 @@
+; RUN: llvm-as < %s | llc -march=x86-64 | not grep cmov
+
+; LSR should be able to eliminate both smax and umax expressions
+; in loop trip counts.
+
+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"
+
+define void @fs(double* nocapture %p, i64 %n) nounwind {
+entry:
+	%tmp = icmp slt i64 %n, 1		; <i1> [#uses=1]
+	%smax = select i1 %tmp, i64 1, i64 %n		; <i64> [#uses=1]
+	br label %bb
+
+bb:		; preds = %bb, %entry
+	%i.0 = phi i64 [ 0, %entry ], [ %0, %bb ]		; <i64> [#uses=2]
+	%scevgep = getelementptr double* %p, i64 %i.0		; <double*> [#uses=1]
+	store double 0.000000e+00, double* %scevgep, align 8
+	%0 = add i64 %i.0, 1		; <i64> [#uses=2]
+	%exitcond = icmp eq i64 %0, %smax		; <i1> [#uses=1]
+	br i1 %exitcond, label %return, label %bb
+
+return:		; preds = %bb
+	ret void
+}
+
+define void @bs(double* nocapture %p, i64 %n) nounwind {
+entry:
+	%tmp = icmp sge i64 %n, 1		; <i1> [#uses=1]
+	%smax = select i1 %tmp, i64 %n, i64 1		; <i64> [#uses=1]
+	br label %bb
+
+bb:		; preds = %bb, %entry
+	%i.0 = phi i64 [ 0, %entry ], [ %0, %bb ]		; <i64> [#uses=2]
+	%scevgep = getelementptr double* %p, i64 %i.0		; <double*> [#uses=1]
+	store double 0.000000e+00, double* %scevgep, align 8
+	%0 = add i64 %i.0, 1		; <i64> [#uses=2]
+	%exitcond = icmp eq i64 %0, %smax		; <i1> [#uses=1]
+	br i1 %exitcond, label %return, label %bb
+
+return:		; preds = %bb
+	ret void
+}
+
+define void @fu(double* nocapture %p, i64 %n) nounwind {
+entry:
+	%tmp = icmp eq i64 %n, 0		; <i1> [#uses=1]
+	%umax = select i1 %tmp, i64 1, i64 %n		; <i64> [#uses=1]
+	br label %bb
+
+bb:		; preds = %bb, %entry
+	%i.0 = phi i64 [ 0, %entry ], [ %0, %bb ]		; <i64> [#uses=2]
+	%scevgep = getelementptr double* %p, i64 %i.0		; <double*> [#uses=1]
+	store double 0.000000e+00, double* %scevgep, align 8
+	%0 = add i64 %i.0, 1		; <i64> [#uses=2]
+	%exitcond = icmp eq i64 %0, %umax		; <i1> [#uses=1]
+	br i1 %exitcond, label %return, label %bb
+
+return:		; preds = %bb
+	ret void
+}
+
+define void @bu(double* nocapture %p, i64 %n) nounwind {
+entry:
+	%tmp = icmp ne i64 %n, 0		; <i1> [#uses=1]
+	%umax = select i1 %tmp, i64 %n, i64 1		; <i64> [#uses=1]
+	br label %bb
+
+bb:		; preds = %bb, %entry
+	%i.0 = phi i64 [ 0, %entry ], [ %0, %bb ]		; <i64> [#uses=2]
+	%scevgep = getelementptr double* %p, i64 %i.0		; <double*> [#uses=1]
+	store double 0.000000e+00, double* %scevgep, align 8
+	%0 = add i64 %i.0, 1		; <i64> [#uses=2]
+	%exitcond = icmp eq i64 %0, %umax		; <i1> [#uses=1]
+	br i1 %exitcond, label %return, label %bb
+
+return:		; preds = %bb
+	ret void
+}
diff --git a/test/CodeGen/X86/optimize-max-2.ll b/test/CodeGen/X86/optimize-max-2.ll
new file mode 100644
index 000000000000..effc3fc737d9
--- /dev/null
+++ b/test/CodeGen/X86/optimize-max-2.ll
@@ -0,0 +1,30 @@
+; RUN: llvm-as < %s | llc -march=x86-64 > %t
+; RUN: grep cmov %t | count 2
+; RUN: grep jne %t | count 1
+
+; LSR's OptimizeMax function shouldn't try to eliminate this max, because
+; it has three operands.
+
+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"
+
+define void @foo(double* nocapture %p, i64 %x, i64 %y) nounwind {
+entry:
+	%tmp = icmp eq i64 %y, 0		; <i1> [#uses=1]
+	%umax = select i1 %tmp, i64 1, i64 %y		; <i64> [#uses=2]
+	%tmp8 = icmp ugt i64 %umax, %x		; <i1> [#uses=1]
+	%umax9 = select i1 %tmp8, i64 %umax, i64 %x		; <i64> [#uses=1]
+	br label %bb4
+
+bb4:		; preds = %bb4, %entry
+	%i.07 = phi i64 [ 0, %entry ], [ %2, %bb4 ]		; <i64> [#uses=2]
+	%scevgep = getelementptr double* %p, i64 %i.07		; <double*> [#uses=2]
+	%0 = load double* %scevgep, align 8		; <double> [#uses=1]
+	%1 = fmul double %0, 2.000000e+00		; <double> [#uses=1]
+	store double %1, double* %scevgep, align 8
+	%2 = add i64 %i.07, 1		; <i64> [#uses=2]
+	%exitcond = icmp eq i64 %2, %umax9		; <i1> [#uses=1]
+	br i1 %exitcond, label %return, label %bb4
+
+return:		; preds = %bb4
+	ret void
+}
diff --git a/test/CodeGen/X86/pic_jumptable.ll b/test/CodeGen/X86/pic_jumptable.ll
index 1731feb58e91..229865bb71b9 100644
--- a/test/CodeGen/X86/pic_jumptable.ll
+++ b/test/CodeGen/X86/pic_jumptable.ll
@@ -1,6 +1,8 @@
 ; RUN: llvm-as < %s | llc -relocation-model=pic -mtriple=i386-linux-gnu -asm-verbose=false | not grep -F .text
 ; RUN: llvm-as < %s | llc -relocation-model=pic -mtriple=i686-apple-darwin -asm-verbose=false | not grep lea
 ; RUN: llvm-as < %s | llc -relocation-model=pic -mtriple=i686-apple-darwin -asm-verbose=false | grep add | count 2
+; RUN: llvm-as < %s | llc                       -mtriple=x86_64-apple-darwin | not grep 'lJTI'
+; rdar://6971437
 
 declare void @_Z3bari(i32)
 
diff --git a/test/CodeGen/X86/tls1-pic.ll b/test/CodeGen/X86/tls1-pic.ll
index a73e75ba8068..e43bf7ce66e6 100644
--- a/test/CodeGen/X86/tls1-pic.ll
+++ b/test/CodeGen/X86/tls1-pic.ll
@@ -1,5 +1,5 @@
 ; RUN: llvm-as < %s | llc -march=x86 -mtriple=i386-linux-gnu -relocation-model=pic > %t
-; RUN: grep {leal	i@TLSGD(,%ebx,1), %eax} %t
+; RUN: grep {leal	i@TLSGD(,%ebx), %eax} %t
 ; RUN: grep {call	___tls_get_addr@PLT} %t
 ; RUN: llvm-as < %s | llc -march=x86-64 -mtriple=x86_64-linux-gnu -relocation-model=pic > %t2
 ; RUN: grep {leaq	i@TLSGD(%rip), %rdi} %t2
diff --git a/test/CodeGen/X86/tls1.ll b/test/CodeGen/X86/tls1.ll
index 5155dfd4a118..85ff360a5508 100644
--- a/test/CodeGen/X86/tls1.ll
+++ b/test/CodeGen/X86/tls1.ll
@@ -5,7 +5,7 @@
 
 @i = thread_local global i32 15
 
-define i32 @f() {
+define i32 @f() nounwind {
 entry:
 	%tmp1 = load i32* @i
 	ret i32 %tmp1
diff --git a/test/CodeGen/X86/tls2-pic.ll b/test/CodeGen/X86/tls2-pic.ll
index cdfe97ca0b04..6ab3ee0a69fd 100644
--- a/test/CodeGen/X86/tls2-pic.ll
+++ b/test/CodeGen/X86/tls2-pic.ll
@@ -1,5 +1,5 @@
 ; RUN: llvm-as < %s | llc -march=x86 -mtriple=i386-linux-gnu -relocation-model=pic > %t
-; RUN: grep {leal	i@TLSGD(,%ebx,1), %eax} %t
+; RUN: grep {leal	i@TLSGD(,%ebx), %eax} %t
 ; RUN: grep {call	___tls_get_addr@PLT} %t
 ; RUN: llvm-as < %s | llc -march=x86-64 -mtriple=x86_64-linux-gnu -relocation-model=pic > %t2
 ; RUN: grep {leaq	i@TLSGD(%rip), %rdi} %t2
@@ -7,7 +7,7 @@
 
 @i = thread_local global i32 15
 
-define i32* @f() {
+define i32* @f() nounwind {
 entry:
 	ret i32* @i
 }
diff --git a/test/CodeGen/X86/tls3-pic.ll b/test/CodeGen/X86/tls3-pic.ll
index f62cca218ab0..8e6df29afbf9 100644
--- a/test/CodeGen/X86/tls3-pic.ll
+++ b/test/CodeGen/X86/tls3-pic.ll
@@ -1,5 +1,5 @@
 ; RUN: llvm-as < %s | llc -march=x86 -mtriple=i386-linux-gnu -relocation-model=pic  > %t
-; RUN: grep {leal	i@TLSGD(,%ebx,1), %eax} %t
+; RUN: grep {leal	i@TLSGD(,%ebx), %eax} %t
 ; RUN: grep {call	___tls_get_addr@PLT} %t
 ; RUN: llvm-as < %s | llc -march=x86-64 -mtriple=x86_64-linux-gnu -relocation-model=pic > %t2
 ; RUN: grep {leaq	i@TLSGD(%rip), %rdi} %t2
diff --git a/test/CodeGen/X86/tls4-pic.ll b/test/CodeGen/X86/tls4-pic.ll
index ec3d43591cd3..94de78f7aef7 100644
--- a/test/CodeGen/X86/tls4-pic.ll
+++ b/test/CodeGen/X86/tls4-pic.ll
@@ -1,5 +1,5 @@
 ; RUN: llvm-as < %s | llc -march=x86 -mtriple=i386-linux-gnu -relocation-model=pic > %t
-; RUN: grep {leal	i@TLSGD(,%ebx,1), %eax} %t
+; RUN: grep {leal	i@TLSGD(,%ebx), %eax} %t
 ; RUN: grep {call	___tls_get_addr@PLT} %t
 ; RUN: llvm-as < %s | llc -march=x86-64 -mtriple=x86_64-linux-gnu -relocation-model=pic > %t2
 ; RUN: grep {leaq	i@TLSGD(%rip), %rdi} %t2
diff --git a/test/CodeGen/X86/umul-with-overflow.ll b/test/CodeGen/X86/umul-with-overflow.ll
new file mode 100644
index 000000000000..9e69154f10f9
--- /dev/null
+++ b/test/CodeGen/X86/umul-with-overflow.ll
@@ -0,0 +1,8 @@
+; RUN: llvm-as < %s | llc -march=x86 | grep "\\\\\\\<mul"
+
+declare {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
+define i1 @a(i32 %x) zeroext nounwind {
+  %res = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %x, i32 3)
+  %obil = extractvalue {i32, i1} %res, 1
+  ret i1 %obil
+}