vendor/llvm/llvm-trunk-r300422

8 files changed, 404 insertions, 56 deletions

diff --git a/test/Transforms/LoopUnswitch/AMDGPU/divergent-unswitch.ll b/test/Transforms/LoopUnswitch/AMDGPU/divergent-unswitch.ll
new file mode 100644
index 000000000000..1f106bd894a8
--- /dev/null
+++ b/test/Transforms/LoopUnswitch/AMDGPU/divergent-unswitch.ll
@@ -0,0 +1,85 @@
+; RUN: opt -mtriple=amdgcn-- -O3 -S %s | FileCheck %s
+
+; Check that loop unswitch happened and condition hoisted out of the loop.
+; Condition is uniform so all targets should perform unswitching.
+
+; CHECK-LABEL: {{^}}define amdgpu_kernel void @uniform_unswitch
+; CHECK: entry:
+; CHECK-NEXT: [[LOOP_COND:%[a-z0-9]+]] = icmp
+; CHECK-NEXT: [[IF_COND:%[a-z0-9]+]] = icmp eq i32 %x, 123456
+; CHECK-NEXT: and i1 [[LOOP_COND]], [[IF_COND]]
+; CHECK-NEXT: br i1
+
+define amdgpu_kernel void @uniform_unswitch(i32 * nocapture %out, i32 %n, i32 %x) {
+entry:
+  %cmp6 = icmp sgt i32 %n, 0
+  br i1 %cmp6, label %for.body.lr.ph, label %for.cond.cleanup
+
+for.body.lr.ph:                                   ; preds = %entry
+  %cmp1 = icmp eq i32 %x, 123456
+  br label %for.body
+
+for.cond.cleanup.loopexit:                        ; preds = %for.inc
+  br label %for.cond.cleanup
+
+for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
+  ret void
+
+for.body:                                         ; preds = %for.inc, %for.body.lr.ph
+  %i.07 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
+  br i1 %cmp1, label %if.then, label %for.inc
+
+if.then:                                          ; preds = %for.body
+  %arrayidx = getelementptr inbounds i32, i32 * %out, i32 %i.07
+  store i32 %i.07, i32 * %arrayidx, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body, %if.then
+  %inc = add nuw nsw i32 %i.07, 1
+  %exitcond = icmp eq i32 %inc, %n
+  br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
+}
+
+; Check that loop unswitch does not happen if condition is divergent.
+
+; CHECK-LABEL: {{^}}define amdgpu_kernel void @divergent_unswitch
+; CHECK: entry:
+; CHECK: icmp
+; CHECK: [[IF_COND:%[a-z0-9]+]] = icmp {{.*}} 567890
+; CHECK: br label
+; CHECK: br i1 [[IF_COND]]
+
+define amdgpu_kernel void @divergent_unswitch(i32 * nocapture %out, i32 %n) {
+entry:
+  %cmp9 = icmp sgt i32 %n, 0
+  br i1 %cmp9, label %for.body.lr.ph, label %for.cond.cleanup
+
+for.body.lr.ph:                                   ; preds = %entry
+  %call = tail call i32 @llvm.amdgcn.workitem.id.x() #0
+  %cmp2 = icmp eq i32 %call, 567890
+  br label %for.body
+
+for.cond.cleanup.loopexit:                        ; preds = %for.inc
+  br label %for.cond.cleanup
+
+for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
+  ret void
+
+for.body:                                         ; preds = %for.inc, %for.body.lr.ph
+  %i.010 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
+  br i1 %cmp2, label %if.then, label %for.inc
+
+if.then:                                          ; preds = %for.body
+  %arrayidx = getelementptr inbounds i32, i32 * %out, i32 %i.010
+  store i32 %i.010, i32 * %arrayidx, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body, %if.then
+  %inc = add nuw nsw i32 %i.010, 1
+  %exitcond = icmp eq i32 %inc, %n
+  br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
+}
+
+declare i32 @llvm.amdgcn.workitem.id.x() #0
+
+attributes #0 = { nounwind readnone }
diff --git a/test/Transforms/LoopUnswitch/AMDGPU/lit.local.cfg b/test/Transforms/LoopUnswitch/AMDGPU/lit.local.cfg
new file mode 100644
index 000000000000..2a665f06be72
--- /dev/null
+++ b/test/Transforms/LoopUnswitch/AMDGPU/lit.local.cfg
@@ -0,0 +1,2 @@
+if not 'AMDGPU' in config.root.targets:
+    config.unsupported = True
diff --git a/test/Transforms/LoopUnswitch/basictest.ll b/test/Transforms/LoopUnswitch/basictest.ll
index a02a463764dd..3add848395ae 100644
--- a/test/Transforms/LoopUnswitch/basictest.ll
+++ b/test/Transforms/LoopUnswitch/basictest.ll
@@ -101,6 +101,217 @@ loop_exit:
 ; CHECK: }
 }
 
+; Make sure we unswitch %a == 0 out of the loop.
+;
+; CHECK: define void @and_i2_as_switch_input(i2
+; CHECK: entry:
+; This is an indication that the loop has been unswitched.
+; CHECK: icmp eq i2 %a, 0
+; CHECK: br
+; There should be no more unswitching after the 1st unswitch.
+; CHECK-NOT: icmp eq
+; CHECK: ret
+define void @and_i2_as_switch_input(i2 %a) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i2 [ 0, %entry ], [ %inc, %for.inc ]
+  %and = and i2 %a, %i
+  %and1 = and i2 %and, %i
+  switch i2 %and1, label %sw.default [
+    i2 0, label %sw.bb
+    i2 1, label %sw.bb1
+  ]
+
+sw.bb:
+  br label %sw.epilog
+
+sw.bb1:
+  br label %sw.epilog
+
+sw.default:
+  br label %sw.epilog
+
+sw.epilog:
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i2 %i, 1
+  %cmp = icmp slt i2 %inc, 3 
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
+
+; Make sure we unswitch %a == !0 out of the loop.
+;
+; CHECK: define void @or_i2_as_switch_input(i2
+; CHECK: entry:
+; This is an indication that the loop has been unswitched.
+; CHECK: icmp eq i2 %a, -1
+; CHECK: br
+; There should be no more unswitching after the 1st unswitch.
+; CHECK-NOT: icmp eq
+; CHECK: ret
+define void @or_i2_as_switch_input(i2 %a) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i2 [ 0, %entry ], [ %inc, %for.inc ]
+  %or = or i2 %a, %i
+  %or1 = or i2 %or, %i
+  switch i2 %or1, label %sw.default [
+    i2 2, label %sw.bb
+    i2 3, label %sw.bb1
+  ]
+
+sw.bb:
+  br label %sw.epilog
+
+sw.bb1:
+  br label %sw.epilog
+
+sw.default:
+  br label %sw.epilog
+
+sw.epilog:
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i2 %i, 1
+  %cmp = icmp slt i2 %inc, 3 
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
+
+; Make sure we unswitch %a == !0 out of the loop. Even we do not
+; have it as a case value. Unswitching it out allows us to simplify
+; the or operator chain.
+;
+; CHECK: define void @or_i2_as_switch_input_unswitch_default(i2
+; CHECK: entry:
+; This is an indication that the loop has been unswitched.
+; CHECK: icmp eq i2 %a, -1
+; CHECK: br
+; There should be no more unswitching after the 1st unswitch.
+; CHECK-NOT: icmp eq
+; CHECK: ret
+define void @or_i2_as_switch_input_unswitch_default(i2 %a) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i2 [ 0, %entry ], [ %inc, %for.inc ]
+  %or = or i2 %a, %i
+  %or1 = or i2 %or, %i
+  switch i2 %or1, label %sw.default [
+    i2 1, label %sw.bb
+    i2 2, label %sw.bb1
+  ]
+
+sw.bb:
+  br label %sw.epilog
+
+sw.bb1:
+  br label %sw.epilog
+
+sw.default:
+  br label %sw.epilog
+
+sw.epilog:
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i2 %i, 1
+  %cmp = icmp slt i2 %inc, 3 
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
+
+; Make sure we don't unswitch, as we can not find an input value %a
+; that will effectively unswitch 0 or 3 out of the loop.
+;
+; CHECK: define void @and_or_i2_as_switch_input(i2
+; CHECK: entry:
+; This is an indication that the loop has NOT been unswitched.
+; CHECK-NOT: icmp
+; CHECK: br
+define void @and_or_i2_as_switch_input(i2 %a) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i2 [ 0, %entry ], [ %inc, %for.inc ]
+  %and = and i2 %a, %i 
+  %or = or i2 %and, %i
+  switch i2 %or, label %sw.default [
+    i2 0, label %sw.bb
+    i2 3, label %sw.bb1
+  ]
+
+sw.bb:
+  br label %sw.epilog
+
+sw.bb1:
+  br label %sw.epilog
+
+sw.default:
+  br label %sw.epilog
+
+sw.epilog:
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i2 %i, 1
+  %cmp = icmp slt i2 %inc, 3 
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
+
+; Make sure we don't unswitch, as we can not find an input value %a
+; that will effectively unswitch true/false out of the loop.
+;
+; CHECK: define void @and_or_i1_as_branch_input(i1
+; CHECK: entry:
+; This is an indication that the loop has NOT been unswitched.
+; CHECK-NOT: icmp
+; CHECK: br
+define void @and_or_i1_as_branch_input(i1 %a) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i1 [ 0, %entry ], [ %inc, %for.inc ]
+  %and = and i1 %a, %i 
+  %or = or i1 %and, %i
+  br i1 %or, label %sw.bb, label %sw.bb1
+
+sw.bb:
+  br label %sw.epilog
+
+sw.bb1:
+  br label %sw.epilog
+
+sw.epilog:
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i1 %i, 1
+  %cmp = icmp slt i1 %inc, 1 
+  br i1 %cmp, label %for.body, label %for.end
+
+for.end:
+  ret void
+}
 
 declare void @incf() noreturn
 declare void @decf() noreturn
diff --git a/test/Transforms/LoopUnswitch/cold-loop.ll b/test/Transforms/LoopUnswitch/cold-loop.ll
deleted file mode 100644
index 1fbc08038bbd..000000000000
--- a/test/Transforms/LoopUnswitch/cold-loop.ll
+++ /dev/null
@@ -1,52 +0,0 @@
-; RUN: opt < %s -loop-unswitch -loop-unswitch-with-block-frequency -S 2>&1 | FileCheck %s
-
-;; trivial condition should be unswithed regardless of coldness.
-define i32 @test1(i1 %cond1, i1 %cond2) !prof !1 {
-  br i1 %cond1, label %loop_begin, label %loop_exit, !prof !0
-
-loop_begin:
-; CHECK: br i1 true, label %continue, label %loop_exit.loopexit
-  br i1 %cond2, label %continue, label %loop_exit  ; trivial condition
-
-continue:
-  call void @some_func1() noreturn nounwind
-  br label %loop_begin
-
-loop_exit:
-  ret i32 0
-}
-
-;; cold non-trivial condition should not be unswitched.
-define i32 @test2(i32* %var, i1 %cond1, i1 %cond2) !prof !1 {
-  br i1 %cond1, label %loop_begin, label %loop_exit, !prof !0
-
-loop_begin:
-  store i32 1, i32* %var
-; CHECK: br i1 %cond2, label %continue1, label %continue2
-  br i1 %cond2, label %continue1, label %continue2  ; non-trivial condition
-
-continue1:
-  call void @some_func1() noreturn nounwind
-  br label %joint
-
-continue2:
-  call void @some_func2() noreturn nounwind
-  br label %joint
-
-joint:
-;; unswitching will duplicate these calls.
-  call void @some_func3() noreturn nounwind
-  call void @some_func4() noreturn nounwind
-  br label %loop_begin
-
-loop_exit:
-  ret i32 0
-}
-
-declare void @some_func1() noreturn
-declare void @some_func2() noreturn
-declare void @some_func3() noreturn
-declare void @some_func4() noreturn
-
-!0 = !{!"branch_weights", i32 1, i32 100000000}
-!1 = !{!"function_entry_count", i64 100}
diff --git a/test/Transforms/LoopUnswitch/copy-metadata.ll b/test/Transforms/LoopUnswitch/copy-metadata.ll
index 2a634c25a23d..3302bce9a6e5 100644
--- a/test/Transforms/LoopUnswitch/copy-metadata.ll
+++ b/test/Transforms/LoopUnswitch/copy-metadata.ll
@@ -3,11 +3,11 @@
 ; This test checks if unswitched condition preserve make.implicit metadata.
 
 define i32 @test(i1 %cond) {
-; CHECK: br i1 %cond, label %..split_crit_edge, label %.loop_exit.split_crit_edge, !make.implicit !0
+; CHECK-LABEL: @test(
+; CHECK:  br i1 %cond, label %..split_crit_edge, label %.loop_exit.split_crit_edge, !make.implicit !0
   br label %loop_begin
 
 loop_begin:
-; CHECK: br i1 true, label %continue, label %loop_exit, !make.implicit !0
   br i1 %cond, label %continue, label %loop_exit, !make.implicit !0
 
 continue:
diff --git a/test/Transforms/LoopUnswitch/crash.ll b/test/Transforms/LoopUnswitch/crash.ll
index 101fb7a2c2ce..b273a123c39c 100644
--- a/test/Transforms/LoopUnswitch/crash.ll
+++ b/test/Transforms/LoopUnswitch/crash.ll
@@ -30,7 +30,7 @@ return:		; preds = %return.loopexit, %list_Length.exit9
 	ret void
 }
 
-define void @test2(i32 %x1, i32 %y1, i32 %z1, i32 %r1) nounwind {
+define void @test2() nounwind {
 entry:
   br label %bb.nph
 
diff --git a/test/Transforms/LoopUnswitch/simplify-with-nonvalness.ll b/test/Transforms/LoopUnswitch/simplify-with-nonvalness.ll
new file mode 100644
index 000000000000..d033b083a1b8
--- /dev/null
+++ b/test/Transforms/LoopUnswitch/simplify-with-nonvalness.ll
@@ -0,0 +1,58 @@
+; RUN: opt < %s -loop-unswitch -verify-loop-info -S < %s 2>&1 | FileCheck %s
+
+; There are 1 case and 1 default case in the switch. after we unswitch, we know the
+; %a is definitely not 0 in one of the unswitched loop, make sure we take advantage
+; of that and simplify the branches in the loop.
+;
+; CHECK: define void @simplify_with_nonvalness(
+
+; This is the loop in which we know %a is definitely 0.
+; CHECK: sw.bb.us:
+; CHECK: br i1 true, label %if.then.us, label %if.end.us
+
+; This is the loop in which we do not know what %a is but we know %a is definitely NOT 0.
+; Make sure we use that information to simplify.
+; The icmp eq i32 %a, 0 in one of the unswitched loop is simplified to false.
+; CHECK: sw.bb.split:
+; CHECK: br i1 false, label %if.then, label %if.end
+
+define void @simplify_with_nonvalness(i32 %a) #0 {
+entry:
+  br label %for.cond
+
+for.cond:
+  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
+  %cmp = icmp slt i32 %i.0, 1024
+  br i1 %cmp, label %for.body, label %for.end
+
+for.body:
+  switch i32 %a, label %sw.default [
+    i32 0, label %sw.bb
+  ]
+
+sw.bb:
+  %cmp1 = icmp eq i32 %a, 0
+  br i1 %cmp1, label %if.then, label %if.end
+
+if.then:
+  call void (...) @bar()
+  br label %if.end
+
+if.end:
+  br label %sw.epilog
+
+sw.default:
+  br label %sw.epilog
+
+sw.epilog:
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i32 %i.0, 1
+  br label %for.cond
+
+for.end:
+  ret void
+}
+
+declare void @bar(...) 
diff --git a/test/Transforms/LoopUnswitch/trivial-unswitch.ll b/test/Transforms/LoopUnswitch/trivial-unswitch.ll
index db3328278dae..2def5b6f0334 100644
--- a/test/Transforms/LoopUnswitch/trivial-unswitch.ll
+++ b/test/Transforms/LoopUnswitch/trivial-unswitch.ll
@@ -44,4 +44,48 @@ loop_exit:
   ret i32 0
 }
 
-declare void @some_func() noreturn
\ No newline at end of file
+
+; We will not be able trivially unswitch on the SwitchInst, as its input
+; is a constant. However, since its a constant we should be able to figure
+; out that the switch can be folded into a unconditional branch to %continue.
+; Then we unswitch on the br inst in %continue.
+;
+; CHECK: define i32 @test2(
+; This is an indication that the loop has been unswitched on %cond1.
+; CHECK:  br i1 %cond1, label %..split_crit_edge, label %.loop_exit.split_crit_edge
+
+; CHECK:  ..split_crit_edge:                                ; preds = %0
+; CHECK:    br label %.split
+
+; CHECK:  .split:                                           ; preds = %..split_crit_edge
+; CHECK:    br label %loop_begin
+
+; CHECK:  loop_begin:                                       ; preds = %do_something, %.split
+; CHECK:    switch i32
+
+; CHECK:  continue:                                         ; preds = %loop_begin
+; CHECK:    %var_val = load i32, i32* %var
+; CHECK:    br i1 true, label %do_something, label %loop_exit
+
+define i32 @test2(i32* %var, i1 %cond1) {
+  br label %loop_begin
+
+loop_begin:  
+  switch i32 1, label %continue [
+    i32 0, label %loop_exit
+    i32 1, label %continue
+  ]
+
+continue:
+  %var_val = load i32, i32* %var
+  br i1 %cond1, label %do_something, label %loop_exit
+
+do_something:
+  call void @some_func() noreturn nounwind
+  br label %loop_begin
+
+loop_exit:
+  ret i32 0
+}
+
+declare void @some_func() noreturn