vendor/llvm/llvm-release_370-r246257

8 files changed, 241 insertions, 12 deletions

diff --git a/test/Transforms/GVN/pr24397.ll b/test/Transforms/GVN/pr24397.ll
new file mode 100644
index 000000000000..db43964e2e4c
--- /dev/null
+++ b/test/Transforms/GVN/pr24397.ll
@@ -0,0 +1,18 @@
+; RUN: opt -basicaa -gvn -disable-output < %s
+
+target triple = "x86_64-unknown-linux-gnu"
+
+define i64 @foo(i64** %arrayidx) {
+entry:
+  %p = load i64*, i64** %arrayidx, align 8
+  %cmpnull = icmp eq i64* %p, null
+  br label %BB2
+
+entry2:                                           ; No predecessors!
+  br label %BB2
+
+BB2:                                              ; preds = %entry2, %entry
+  %bc = bitcast i64** %arrayidx to i64*
+  %load = load i64, i64* %bc, align 8
+  ret i64 %load
+}
diff --git a/test/Transforms/InstCombine/pr24354.ll b/test/Transforms/InstCombine/pr24354.ll
new file mode 100644
index 000000000000..3b36fd1b74e3
--- /dev/null
+++ b/test/Transforms/InstCombine/pr24354.ll
@@ -0,0 +1,33 @@
+; RUN: opt -instcombine -S < %s | FileCheck %s
+
+; This used to crash opt
+
+@c = common global i32 0, align 4
+@b = common global i32 0, align 4
+@a = common global i16 0, align 2
+@d = common global i32 0, align 4
+
+define void @fn3() {
+; CHECK: @fn3
+bb:
+  %tmp = load i32, i32* @c, align 4
+  %tmp1 = icmp eq i32 %tmp, 0
+  br i1 %tmp1, label %bb2, label %bb6
+
+bb2:                                              ; preds = %bb
+  %tmp3 = load i32, i32* @b, align 4
+  %tmp.i = add nsw i32 255, %tmp3
+  %tmp5 = icmp ugt i32 %tmp.i, 254
+  br label %bb6
+
+bb6:                                              ; preds = %bb, %bb2
+  %tmp7 = phi i1 [ true, %bb ], [ %tmp5, %bb2 ]
+  %tmp8 = zext i1 %tmp7 to i32
+  %tmp10 = icmp eq i32 %tmp8, 0
+  %tmp12 = load i16, i16* @a, align 2
+  %tmp14 = icmp ne i16 %tmp12, 0
+  %tmp16 = select i1 %tmp10, i1 false, i1 %tmp14
+  %tmp17 = zext i1 %tmp16 to i32
+  store i32 %tmp17, i32* @d, align 4
+  ret void
+}
diff --git a/test/Transforms/InstCombine/vector-casts.ll b/test/Transforms/InstCombine/vector-casts.ll
index 727eb4ebb4c8..af18b4cfbdd1 100644
--- a/test/Transforms/InstCombine/vector-casts.ll
+++ b/test/Transforms/InstCombine/vector-casts.ll
@@ -150,3 +150,14 @@ entry:
   ret <4 x float> undef
 }
 
+define <8 x i32> @pr24458(<8 x float> %n) {
+; CHECK-LABEL: @pr24458
+  %notequal_b_load_.i = fcmp une <8 x float> %n, zeroinitializer
+  %equal_a_load72_.i = fcmp ueq <8 x float> %n, zeroinitializer
+  %notequal_b_load__to_boolvec.i = sext <8 x i1> %notequal_b_load_.i to <8 x i32>
+  %equal_a_load72__to_boolvec.i = sext <8 x i1> %equal_a_load72_.i to <8 x i32>
+  %wrong = or <8 x i32> %notequal_b_load__to_boolvec.i, %equal_a_load72__to_boolvec.i
+  ret <8 x i32> %wrong
+; CHECK-NEXT: ret <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
+}
+
diff --git a/test/Transforms/InstSimplify/2011-09-05-InsertExtractValue.ll b/test/Transforms/InstSimplify/2011-09-05-InsertExtractValue.ll
index 7e391aba3045..441bc1adca7e 100644
--- a/test/Transforms/InstSimplify/2011-09-05-InsertExtractValue.ll
+++ b/test/Transforms/InstSimplify/2011-09-05-InsertExtractValue.ll
@@ -36,3 +36,13 @@ define i32 @test3(i32 %a, float %b) {
 ; CHECK-LABEL: @test3(
 ; CHECK: ret i32 %a
 }
+
+define i8 @test4(<8 x i8> %V) {
+  %add     = add <8 x i8> %V, bitcast (double 0x319BEB8FD172E36 to <8 x i8>)
+  %extract = extractelement <8 x i8> %add, i32 6
+  ret i8 %extract
+; CHECK-LABEL: @test4(
+; CHECK: %[[add:.*]] = add <8 x i8> %V, bitcast (<1 x double> <double 0x319BEB8FD172E36> to <8 x i8>)
+; CHECK-NEXT: %[[extract:.*]] = extractelement <8 x i8> %[[add]], i32 6
+; CHECK-NEXT: ret i8 %[[extract]]
+}
diff --git a/test/Transforms/SROA/basictest.ll b/test/Transforms/SROA/basictest.ll
index 7c8955b28fa2..ad2794167a5e 100644
--- a/test/Transforms/SROA/basictest.ll
+++ b/test/Transforms/SROA/basictest.ll
@@ -1195,20 +1195,24 @@ entry:
   %a = alloca <{ i1 }>, align 8
   %b = alloca <{ i1 }>, align 8
 ; CHECK:      %[[a:.*]] = alloca i8, align 8
+; CHECK-NEXT: %[[b:.*]] = alloca i8, align 8
 
   %b.i1 = bitcast <{ i1 }>* %b to i1*
   store i1 %x, i1* %b.i1, align 8
   %b.i8 = bitcast <{ i1 }>* %b to i8*
   %foo = load i8, i8* %b.i8, align 1
-; CHECK-NEXT: %[[ext:.*]] = zext i1 %x to i8
-; CHECK-NEXT: store i8 %[[ext]], i8* %[[a]], align 8
-; CHECK-NEXT: {{.*}} = load i8, i8* %[[a]], align 8
+; CHECK-NEXT: %[[b_cast:.*]] = bitcast i8* %[[b]] to i1*
+; CHECK-NEXT: store i1 %x, i1* %[[b_cast]], align 8
+; CHECK-NEXT: {{.*}} = load i8, i8* %[[b]], align 8
 
   %a.i8 = bitcast <{ i1 }>* %a to i8*
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.i8, i8* %b.i8, i32 1, i32 1, i1 false) nounwind
   %bar = load i8, i8* %a.i8, align 1
   %a.i1 = getelementptr inbounds <{ i1 }>, <{ i1 }>* %a, i32 0, i32 0
   %baz = load i1, i1* %a.i1, align 1
+; CHECK-NEXT: %[[copy:.*]] = load i8, i8* %[[b]], align 8
+; CHECK-NEXT: store i8 %[[copy]], i8* %[[a]], align 8
+; CHECK-NEXT: {{.*}} = load i8, i8* %[[a]], align 8
 ; CHECK-NEXT: %[[a_cast:.*]] = bitcast i8* %[[a]] to i1*
 ; CHECK-NEXT: {{.*}} = load i1, i1* %[[a_cast]], align 8
 
diff --git a/test/Transforms/SROA/big-endian.ll b/test/Transforms/SROA/big-endian.ll
index b5a04ca8e64a..4de7bfcb898d 100644
--- a/test/Transforms/SROA/big-endian.ll
+++ b/test/Transforms/SROA/big-endian.ll
@@ -112,3 +112,126 @@ entry:
 ; CHECK-NEXT: %[[ret:.*]] = zext i56 %[[insert4]] to i64
 ; CHECK-NEXT: ret i64 %[[ret]]
 }
+
+define i64 @PR14132(i1 %flag) {
+; CHECK-LABEL: @PR14132(
+; Here we form a PHI-node by promoting the pointer alloca first, and then in
+; order to promote the other two allocas, we speculate the load of the
+; now-phi-node-pointer. In doing so we end up loading a 64-bit value from an i8
+; alloca. While this is a bit dubious, we were asserting on trying to
+; rewrite it. The trick is that the code using the value may carefully take
+; steps to only use the not-undef bits, and so we need to at least loosely
+; support this. This test is particularly interesting because how we handle
+; a load of an i64 from an i8 alloca is dependent on endianness.
+entry:
+  %a = alloca i64, align 8
+  %b = alloca i8, align 8
+  %ptr = alloca i64*, align 8
+; CHECK-NOT: alloca
+
+  %ptr.cast = bitcast i64** %ptr to i8**
+  store i64 0, i64* %a
+  store i8 1, i8* %b
+  store i64* %a, i64** %ptr
+  br i1 %flag, label %if.then, label %if.end
+
+if.then:
+  store i8* %b, i8** %ptr.cast
+  br label %if.end
+; CHECK-NOT: store
+; CHECK: %[[ext:.*]] = zext i8 1 to i64
+; CHECK: %[[shift:.*]] = shl i64 %[[ext]], 56
+
+if.end:
+  %tmp = load i64*, i64** %ptr
+  %result = load i64, i64* %tmp
+; CHECK-NOT: load
+; CHECK: %[[result:.*]] = phi i64 [ %[[shift]], %if.then ], [ 0, %entry ]
+
+  ret i64 %result
+; CHECK-NEXT: ret i64 %[[result]]
+}
+
+declare void @f(i64 %x, i32 %y)
+
+define void @test3() {
+; CHECK-LABEL: @test3(
+;
+; This is a test that specifically exercises the big-endian lowering because it
+; ends up splitting a 64-bit integer into two smaller integers and has a number
+; of tricky aspects (the i24 type) that make that hard. Historically, SROA
+; would miscompile this by either dropping a most significant byte or least
+; significant byte due to shrinking the [4,8) slice to an i24, or by failing to
+; move the bytes around correctly.
+;
+; The magical number 34494054408 is used because it has bits set in various
+; bytes so that it is clear if those bytes fail to be propagated.
+;
+; If you're debugging this, rather than using the direct magical numbers, run
+; the IR through '-sroa -instcombine'. With '-instcombine' these will be
+; constant folded, and if the i64 doesn't round-trip correctly, you've found
+; a bug!
+;
+entry:
+  %a = alloca { i32, i24 }, align 4
+; CHECK-NOT: alloca
+
+  %tmp0 = bitcast { i32, i24 }* %a to i64*
+  store i64 34494054408, i64* %tmp0
+  %tmp1 = load i64, i64* %tmp0, align 4
+  %tmp2 = bitcast { i32, i24 }* %a to i32*
+  %tmp3 = load i32, i32* %tmp2, align 4
+; CHECK: %[[HI_EXT:.*]] = zext i32 134316040 to i64
+; CHECK: %[[HI_INPUT:.*]] = and i64 undef, -4294967296
+; CHECK: %[[HI_MERGE:.*]] = or i64 %[[HI_INPUT]], %[[HI_EXT]]
+; CHECK: %[[LO_EXT:.*]] = zext i32 8 to i64
+; CHECK: %[[LO_SHL:.*]] = shl i64 %[[LO_EXT]], 32
+; CHECK: %[[LO_INPUT:.*]] = and i64 %[[HI_MERGE]], 4294967295
+; CHECK: %[[LO_MERGE:.*]] = or i64 %[[LO_INPUT]], %[[LO_SHL]]
+
+  call void @f(i64 %tmp1, i32 %tmp3)
+; CHECK: call void @f(i64 %[[LO_MERGE]], i32 8)
+  ret void
+; CHECK: ret void
+}
+
+define void @test4() {
+; CHECK-LABEL: @test4
+;
+; Much like @test3, this is specifically testing big-endian management of data.
+; Also similarly, it uses constants with particular bits set to help track
+; whether values are corrupted, and can be easily evaluated by running through
+; -instcombine to see that the i64 round-trips.
+;
+entry:
+  %a = alloca { i32, i24 }, align 4
+  %a2 = alloca i64, align 4
+; CHECK-NOT: alloca
+
+  store i64 34494054408, i64* %a2
+  %tmp0 = bitcast { i32, i24 }* %a to i8*
+  %tmp1 = bitcast i64* %a2 to i8*
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp0, i8* %tmp1, i64 8, i32 4, i1 false)
+; CHECK: %[[LO_SHR:.*]] = lshr i64 34494054408, 32
+; CHECK: %[[LO_START:.*]] = trunc i64 %[[LO_SHR]] to i32
+; CHECK: %[[HI_START:.*]] = trunc i64 34494054408 to i32
+
+  %tmp2 = bitcast { i32, i24 }* %a to i64*
+  %tmp3 = load i64, i64* %tmp2, align 4
+  %tmp4 = bitcast { i32, i24 }* %a to i32*
+  %tmp5 = load i32, i32* %tmp4, align 4
+; CHECK: %[[HI_EXT:.*]] = zext i32 %[[HI_START]] to i64
+; CHECK: %[[HI_INPUT:.*]] = and i64 undef, -4294967296
+; CHECK: %[[HI_MERGE:.*]] = or i64 %[[HI_INPUT]], %[[HI_EXT]]
+; CHECK: %[[LO_EXT:.*]] = zext i32 %[[LO_START]] to i64
+; CHECK: %[[LO_SHL:.*]] = shl i64 %[[LO_EXT]], 32
+; CHECK: %[[LO_INPUT:.*]] = and i64 %[[HI_MERGE]], 4294967295
+; CHECK: %[[LO_MERGE:.*]] = or i64 %[[LO_INPUT]], %[[LO_SHL]]
+
+  call void @f(i64 %tmp3, i32 %tmp5)
+; CHECK: call void @f(i64 %[[LO_MERGE]], i32 %[[LO_START]])
+  ret void
+; CHECK: ret void
+}
+
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i32, i1)
diff --git a/test/Transforms/SROA/phi-and-select.ll b/test/Transforms/SROA/phi-and-select.ll
index e97bd66d052a..fb76548b1d18 100644
--- a/test/Transforms/SROA/phi-and-select.ll
+++ b/test/Transforms/SROA/phi-and-select.ll
@@ -438,26 +438,26 @@ define i64 @PR14132(i1 %flag) {
 ; steps to only use the not-undef bits, and so we need to at least loosely
 ; support this..
 entry:
-  %a = alloca i64
-  %b = alloca i8
-  %ptr = alloca i64*
+  %a = alloca i64, align 8
+  %b = alloca i8, align 8
+  %ptr = alloca i64*, align 8
 ; CHECK-NOT: alloca
 
   %ptr.cast = bitcast i64** %ptr to i8**
-  store i64 0, i64* %a
-  store i8 1, i8* %b
-  store i64* %a, i64** %ptr
+  store i64 0, i64* %a, align 8
+  store i8 1, i8* %b, align 8
+  store i64* %a, i64** %ptr, align 8
   br i1 %flag, label %if.then, label %if.end
 
 if.then:
-  store i8* %b, i8** %ptr.cast
+  store i8* %b, i8** %ptr.cast, align 8
   br label %if.end
 ; CHECK-NOT: store
 ; CHECK: %[[ext:.*]] = zext i8 1 to i64
 
 if.end:
-  %tmp = load i64*, i64** %ptr
-  %result = load i64, i64* %tmp
+  %tmp = load i64*, i64** %ptr, align 8
+  %result = load i64, i64* %tmp, align 8
 ; CHECK-NOT: load
 ; CHECK: %[[result:.*]] = phi i64 [ %[[ext]], %if.then ], [ 0, %entry ]
 
diff --git a/test/Transforms/Scalarizer/cache-bug.ll b/test/Transforms/Scalarizer/cache-bug.ll
new file mode 100644
index 000000000000..f8c2d100d59a
--- /dev/null
+++ b/test/Transforms/Scalarizer/cache-bug.ll
@@ -0,0 +1,30 @@
+; RUN: opt -scalarizer -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"
+
+
+; Check that vector element 1 is scalarized correctly from a chain of
+; insertelement instructions
+define void @func(i32 %x) {
+; CHECK-LABEL: @func(
+; CHECK-NOT: phi i32 [ %x, %entry ], [ %inc.pos.y, %loop ]
+; CHECK:     phi i32 [ %inc, %entry ], [ %inc.pos.y, %loop ]
+; CHECK:   ret void
+entry:
+  %vecinit = insertelement <2 x i32> <i32 0, i32 0>, i32 %x, i32 1
+  %inc = add i32 %x, 1
+  %0 = insertelement <2 x i32> %vecinit, i32 %inc, i32 1
+  br label %loop
+
+loop:
+  %pos = phi <2 x i32> [ %0, %entry ], [ %new.pos.y, %loop ]
+  %i = phi i32 [ 0, %entry ], [ %new.i, %loop ]
+  %pos.y = extractelement <2 x i32> %pos, i32 1
+  %inc.pos.y = add i32 %pos.y, 1
+  %new.pos.y = insertelement <2 x i32> %pos, i32 %inc.pos.y, i32 1
+  %new.i = add i32 %i, 1
+  %cmp2 = icmp slt i32 %new.i, 1
+  br i1 %cmp2, label %loop, label %exit
+
+exit:
+  ret void
+}