4 files changed, 429 insertions, 0 deletions
diff --git a/llvm/test/Transforms/GVN/PRE/2017-10-16-LoadPRECrash.ll b/llvm/test/Transforms/GVN/PRE/2017-10-16-LoadPRECrash.ll
index 5fbb0fcc511..14f65a4a24a 100644
--- a/llvm/test/Transforms/GVN/PRE/2017-10-16-LoadPRECrash.ll
+++ b/llvm/test/Transforms/GVN/PRE/2017-10-16-LoadPRECrash.ll
@@ -17,6 +17,13 @@ declare i64* @getaddr_i64(i64 addrspace(100)*) #0
 define hidden void @wrapon_fn173() {
 
 ; CHECK-LABEL: @wrapon_fn173
+; CHECK:       entry:
+; CHECK-NEXT:    call %ArrayImpl* @getaddr_ArrayImpl(%ArrayImpl addrspace(100)* undef)
+; CHECK-NEXT:    %.pre = load i64 addrspace(100)*, i64 addrspace(100)** null, align 8
+; CHECK-NEXT:    br label %loop
+; CHECK:       loop:
+; CHECK-NEXT:    call i64* @getaddr_i64(i64 addrspace(100)* %.pre)
+; CHECK-NEXT:    br label %loop
 
 entry:
   %0 = call %ArrayImpl* @getaddr_ArrayImpl(%ArrayImpl addrspace(100)* undef)
diff --git a/llvm/test/Transforms/GVN/PRE/pre-load-guards.ll b/llvm/test/Transforms/GVN/PRE/pre-load-guards.ll
new file mode 100644
index 00000000000..eeb3ef649d9
--- /dev/null
+++ b/llvm/test/Transforms/GVN/PRE/pre-load-guards.ll
@@ -0,0 +1,146 @@
+; RUN: opt < %s -basicaa -gvn -enable-load-pre -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"
+
+declare void @llvm.experimental.guard(i1, ...)
+
+; This is a motivating example on why we prohibit hoisting through guards.
+; In the bottom block, we check that the index is within bounds and only access
+; the element in this case and deoptimize otherwise. If we hoist the load to a
+; place above the guard, it will may lead to out-of-bound array access.
+define i32 @test_motivation(i32* %p, i32* %q, i1 %C, i32 %index, i32 %len) {
+; CHECK-LABEL: @test_motivation(
+block1:
+  %el1 = getelementptr inbounds i32, i32* %q, i32 %index
+  %el2 = getelementptr inbounds i32, i32* %p, i32 %index
+	br i1 %C, label %block2, label %block3
+
+block2:
+
+; CHECK:        block2:
+; CHECK-NEXT:     br
+; CHECK-NOT:      load
+; CHECK-NOT:      sge
+; CHECK-NOT:      slt
+; CHECK-NOT:      and
+  br label %block4
+
+block3:
+  store i32 0, i32* %el1
+  br label %block4
+
+block4:
+
+; CHECK:        block4:
+; CHECK:          %cond1 = icmp sge i32 %index, 0
+; CHECK-NEXT:     %cond2 = icmp slt i32 %index, %len
+; CHECK-NEXT:     %in.bounds = and i1 %cond1, %cond2
+; CHECK:          call void (i1, ...) @llvm.experimental.guard(i1 %in.bounds)
+; CHECK-NEXT:     %PRE = load i32, i32* %P2
+; CHECK:          ret i32 %PRE
+
+  %P2 = phi i32* [%el2, %block3], [%el1, %block2]
+  %cond1 = icmp sge i32 %index, 0
+  %cond2 = icmp slt i32 %index, %len
+  %in.bounds = and i1 %cond1, %cond2
+  call void (i1, ...) @llvm.experimental.guard(i1 %in.bounds) [ "deopt"() ]
+  %PRE = load i32, i32* %P2
+  ret i32 %PRE
+}
+
+; Guard in load's block that is above the load should prohibit the PRE.
+define i32 @test_guard_01(i32* %p, i32* %q, i1 %C, i1 %G) {
+; CHECK-LABEL: @test_guard_01(
+block1:
+	br i1 %C, label %block2, label %block3
+
+block2:
+
+; CHECK:        block2:
+; CHECK-NEXT:     br
+; CHECK-NOT:      load
+
+ br label %block4
+
+block3:
+  store i32 0, i32* %p
+  br label %block4
+
+block4:
+
+; CHECK:        block4:
+; CHECK:          call void (i1, ...) @llvm.experimental.guard(i1 %G)
+; CHECK-NEXT:     load
+; CHECK:          ret i32
+
+  %P2 = phi i32* [%p, %block3], [%q, %block2]
+  call void (i1, ...) @llvm.experimental.guard(i1 %G) [ "deopt"() ]
+  %PRE = load i32, i32* %P2
+  ret i32 %PRE
+}
+
+; Guard in load's block that is below the load should not prohibit the PRE.
+define i32 @test_guard_02(i32* %p, i32* %q, i1 %C, i1 %G) {
+; CHECK-LABEL: @test_guard_02(
+block1:
+	br i1 %C, label %block2, label %block3
+
+block2:
+
+; CHECK:        block2:
+; CHECK-NEXT:     load i32, i32* %q
+
+ br label %block4
+
+block3:
+  store i32 0, i32* %p
+  br label %block4
+
+block4:
+
+; CHECK:        block4:
+; CHECK-NEXT:     phi i32 [
+; CHECK-NEXT:     phi i32* [
+; CHECK-NEXT:     call void (i1, ...) @llvm.experimental.guard(i1 %G)
+; CHECK-NOT:      load
+; CHECK:          ret i32
+
+  %P2 = phi i32* [%p, %block3], [%q, %block2]
+  %PRE = load i32, i32* %P2
+  call void (i1, ...) @llvm.experimental.guard(i1 %G) [ "deopt"() ]
+  ret i32 %PRE
+}
+
+; Guard above the load's block should prevent PRE from hoisting through it.
+define i32 @test_guard_03(i32* %p, i32* %q, i1 %C, i1 %G) {
+; CHECK-LABEL: @test_guard_03(
+block1:
+	br i1 %C, label %block2, label %block3
+
+block2:
+
+; CHECK:        block2:
+; CHECK-NEXT:     br
+; CHECK-NOT:      load
+
+ br label %block4
+
+block3:
+  store i32 0, i32* %p
+  br label %block4
+
+block4:
+
+; CHECK:        block4:
+; CHECK-NEXT:     phi i32*
+; CHECK-NEXT:     call void (i1, ...) @llvm.experimental.guard(i1 %G)
+; CHECK-NEXT:     load
+; CHECK-NEXT:     ret i32
+
+  %P2 = phi i32* [%p, %block3], [%q, %block2]
+  call void (i1, ...) @llvm.experimental.guard(i1 %G) [ "deopt"() ]
+  br label %block5
+
+block5:
+  %PRE = load i32, i32* %P2
+  ret i32 %PRE
+}
diff --git a/llvm/test/Transforms/GVN/PRE/pre-load-implicit-cf-updates.ll b/llvm/test/Transforms/GVN/PRE/pre-load-implicit-cf-updates.ll
new file mode 100644
index 00000000000..c131e923997
--- /dev/null
+++ b/llvm/test/Transforms/GVN/PRE/pre-load-implicit-cf-updates.ll
@@ -0,0 +1,118 @@
+; RUN: opt -S -gvn -enable-load-pre < %s | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; These tests exercise situations when instructions that were first instructions
+; with implicit control flow get removed. We make sure that after that we don't
+; face crashes and are still able to perform PRE correctly.
+
+declare i32 @foo(i32 %arg) #0
+
+define hidden void @test_01(i32 %x, i32 %y) {
+
+; c2 only throws if c1 throws, so it can be safely removed and then PRE can
+; hoist the load out of loop.
+
+; CHECK-LABEL: @test_01
+; CHECK:       entry:
+; CHECK-NEXT:    %c1 = call i32 @foo(i32 %x)
+; CHECK-NEXT:    %val.pre = load i32, i32* null, align 8
+; CHECK-NEXT:    br label %loop
+; CHECK:       loop:
+; CHECK-NEXT:    %c3 = call i32 @foo(i32 %val.pre)
+; CHECK-NEXT:    br label %loop
+
+entry:
+  %c1 = call i32 @foo(i32 %x)
+  br label %loop
+
+loop:
+  %c2 = call i32 @foo(i32 %x)
+  %val = load i32, i32* null, align 8
+  %c3 = call i32 @foo(i32 %val)
+  br label %loop
+}
+
+define hidden void @test_02(i32 %x, i32 %y) {
+
+; PRE is not allowed because c2 may throw.
+
+; CHECK-LABEL: @test_02
+; CHECK:       entry:
+; CHECK-NEXT:    %c1 = call i32 @foo(i32 %x)
+; CHECK-NEXT:    br label %loop
+; CHECK:       loop:
+; CHECK-NEXT:    %c2 = call i32 @foo(i32 %y)
+; CHECK-NEXT:    %val = load i32, i32* null, align 8
+; CHECK-NEXT:    %c3 = call i32 @foo(i32 %val)
+; CHECK-NEXT:    br label %loop
+
+entry:
+  %c1 = call i32 @foo(i32 %x)
+  br label %loop
+
+loop:
+  %c2 = call i32 @foo(i32 %y)
+  %val = load i32, i32* null, align 8
+  %c3 = call i32 @foo(i32 %val)
+  br label %loop
+}
+
+define hidden void @test_03(i32 %x, i32 %y) {
+
+; PRE of load is allowed because c2 only throws if c1 throws. c3 should
+; not be eliminated. c4 is eliminated because it only throws if c3 throws.
+
+; CHECK-LABEL: @test_03
+; CHECK:       entry:
+; CHECK-NEXT:    %c1 = call i32 @foo(i32 %x)
+; CHECK-NEXT:    %val.pre = load i32, i32* null, align 8
+; CHECK-NEXT:    br label %loop
+; CHECK:       loop:
+; CHECK-NEXT:    %c3 = call i32 @foo(i32 %y)
+; CHECK-NEXT:    %c5 = call i32 @foo(i32 %val.pre)
+; CHECK-NEXT:    br label %loop
+
+entry:
+  %c1 = call i32 @foo(i32 %x)
+  br label %loop
+
+loop:
+  %c2 = call i32 @foo(i32 %x)
+  %val = load i32, i32* null, align 8
+  %c3 = call i32 @foo(i32 %y)
+  %val2 = load i32, i32* null, align 8
+  %c4 = call i32 @foo(i32 %y)
+  %c5 = call i32 @foo(i32 %val)
+  br label %loop
+}
+
+define hidden void @test_04(i32 %x, i32 %y) {
+
+; PRE is not allowed even after we remove c2 because now c3 prevents us from it.
+
+; CHECK-LABEL: @test_04
+; CHECK:       entry:
+; CHECK-NEXT:    %c1 = call i32 @foo(i32 %x)
+; CHECK-NEXT:    br label %loop
+; CHECK:       loop:
+; CHECK-NEXT:    %c3 = call i32 @foo(i32 %y)
+; CHECK-NEXT:    %val = load i32, i32* null, align 8
+; CHECK-NEXT:    %c5 = call i32 @foo(i32 %val)
+; CHECK-NEXT:    br label %loop
+
+entry:
+  %c1 = call i32 @foo(i32 %x)
+  br label %loop
+
+loop:
+  %c2 = call i32 @foo(i32 %x)
+  %c3 = call i32 @foo(i32 %y)
+  %val = load i32, i32* null, align 8
+  %c4 = call i32 @foo(i32 %y)
+  %c5 = call i32 @foo(i32 %val)
+  br label %loop
+}
+
+attributes #0 = { readnone }
diff --git a/llvm/test/Transforms/GVN/PRE/pre-load.ll b/llvm/test/Transforms/GVN/PRE/pre-load.ll
index ffff2b7f08e..1d050f4b620 100644
--- a/llvm/test/Transforms/GVN/PRE/pre-load.ll
+++ b/llvm/test/Transforms/GVN/PRE/pre-load.ll
@@ -430,3 +430,161 @@ cleanup2:
   call void @g(i32 %NOTPRE)
   cleanupret from %c2 unwind to caller
 }
+
+; Don't PRE load across potentially throwing calls.
+
+define i32 @test13(i32* noalias nocapture readonly %x, i32* noalias nocapture %r, i32 %a) {
+
+; CHECK-LABEL: @test13(
+; CHECK: entry:
+; CHECK-NEXT: icmp eq
+; CHECK-NEXT: br i1
+
+entry:
+  %tobool = icmp eq i32 %a, 0
+  br i1 %tobool, label %if.end, label %if.then
+
+; CHECK: if.then:
+; CHECK-NEXT: load i32
+; CHECK-NEXT: store i32
+
+if.then:
+  %uu = load i32, i32* %x, align 4
+  store i32 %uu, i32* %r, align 4
+  br label %if.end
+
+; CHECK: if.end:
+; CHECK-NEXT: call void @f()
+; CHECK-NEXT: load i32
+
+if.end:
+  call void @f()
+  %vv = load i32, i32* %x, align 4
+  ret i32 %vv
+}
+
+; Same as test13, but now the blocking function is not immediately in load's
+; block.
+
+define i32 @test14(i32* noalias nocapture readonly %x, i32* noalias nocapture %r, i32 %a) {
+
+; CHECK-LABEL: @test14(
+; CHECK: entry:
+; CHECK-NEXT: icmp eq
+; CHECK-NEXT: br i1
+
+entry:
+  %tobool = icmp eq i32 %a, 0
+  br i1 %tobool, label %if.end, label %if.then
+
+; CHECK: if.then:
+; CHECK-NEXT: load i32
+; CHECK-NEXT: store i32
+
+if.then:
+  %uu = load i32, i32* %x, align 4
+  store i32 %uu, i32* %r, align 4
+  br label %if.end
+
+; CHECK: if.end:
+; CHECK-NEXT: call void @f()
+; CHECK-NEXT: load i32
+
+if.end:
+  call void @f()
+  br label %follow_1
+
+follow_1:
+  br label %follow_2
+
+follow_2:
+  %vv = load i32, i32* %x, align 4
+  ret i32 %vv
+}
+
+; Same as test13, but %x here is dereferenceable. A pointer that is
+; dereferenceable can be loaded from speculatively without a risk of trapping.
+; Since it is OK to speculate, PRE is allowed.
+
+define i32 @test15(i32* noalias nocapture readonly dereferenceable(8) %x, i32* noalias nocapture %r, i32 %a) {
+
+; CHECK-LABEL: @test15
+; CHECK: entry:
+; CHECK-NEXT: icmp eq
+; CHECK-NEXT: br i1
+
+entry:
+  %tobool = icmp eq i32 %a, 0
+  br i1 %tobool, label %if.end, label %if.then
+
+; CHECK: entry.if.end_crit_edge:
+; CHECK-NEXT: %vv.pre = load i32, i32* %x, align 4
+; CHECK-NEXT: br label %if.end
+
+if.then:
+  %uu = load i32, i32* %x, align 4
+  store i32 %uu, i32* %r, align 4
+  br label %if.end
+
+; CHECK: if.then:
+; CHECK-NEXT: %uu = load i32, i32* %x, align 4
+; CHECK-NEXT: store i32 %uu, i32* %r, align 4
+; CHECK-NEXT: br label %if.end
+
+if.end:
+  call void @f()
+  %vv = load i32, i32* %x, align 4
+  ret i32 %vv
+
+; CHECK: if.end:
+; CHECK-NEXT: %vv = phi i32 [ %vv.pre, %entry.if.end_crit_edge ], [ %uu, %if.then ]
+; CHECK-NEXT: call void @f()
+; CHECK-NEXT: ret i32 %vv
+
+}
+
+; Same as test14, but %x here is dereferenceable. A pointer that is
+; dereferenceable can be loaded from speculatively without a risk of trapping.
+; Since it is OK to speculate, PRE is allowed.
+
+define i32 @test16(i32* noalias nocapture readonly dereferenceable(8) %x, i32* noalias nocapture %r, i32 %a) {
+
+; CHECK-LABEL: @test16(
+; CHECK: entry:
+; CHECK-NEXT: icmp eq
+; CHECK-NEXT: br i1
+
+entry:
+  %tobool = icmp eq i32 %a, 0
+  br i1 %tobool, label %if.end, label %if.then
+
+; CHECK: entry.if.end_crit_edge:
+; CHECK-NEXT: %vv.pre = load i32, i32* %x, align 4
+; CHECK-NEXT: br label %if.end
+
+if.then:
+  %uu = load i32, i32* %x, align 4
+  store i32 %uu, i32* %r, align 4
+  br label %if.end
+
+; CHECK: if.then:
+; CHECK-NEXT: %uu = load i32, i32* %x, align 4
+; CHECK-NEXT: store i32 %uu, i32* %r, align 4
+; CHECK-NEXT: br label %if.end
+
+if.end:
+  call void @f()
+  br label %follow_1
+
+; CHECK: if.end:
+; CHECK-NEXT: %vv = phi i32 [ %vv.pre, %entry.if.end_crit_edge ], [ %uu, %if.then ]
+; CHECK-NEXT: call void @f()
+; CHECK-NEXT: ret i32 %vv
+
+follow_1:
+  br label %follow_2
+
+follow_2:
+  %vv = load i32, i32* %x, align 4
+  ret i32 %vv
+}