5 files changed, 172 insertions, 44 deletions
diff --git a/test/Transforms/Inline/AArch64/inline-target-attr.ll b/test/Transforms/Inline/AArch64/inline-target-attr.ll
new file mode 100644
index 000000000000..af87ff6e7404
--- /dev/null
+++ b/test/Transforms/Inline/AArch64/inline-target-attr.ll
@@ -0,0 +1,40 @@
+; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -S -inline | FileCheck %s
+; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -S -passes='cgscc(inline)' | FileCheck %s
+; Check that we only inline when we have compatible target attributes.
+
+define i32 @foo() #0 {
+entry:
+  %call = call i32 (...) @baz()
+  ret i32 %call
+; CHECK-LABEL: foo
+; CHECK: call i32 (...) @baz()
+}
+declare i32 @baz(...) #0
+
+define i32 @bar() #1 {
+entry:
+  %call = call i32 @foo()
+  ret i32 %call
+; CHECK-LABEL: bar
+; CHECK: call i32 (...) @baz()
+}
+
+define i32 @qux() #0 {
+entry:
+  %call = call i32 @bar()
+  ret i32 %call
+; CHECK-LABEL: qux
+; CHECK: call i32 @bar()
+}
+
+define i32 @strict_align() #2 {
+entry:
+  %call = call i32 @foo()
+  ret i32 %call
+; CHECK-LABEL: strict_align
+; CHECK: call i32 (...) @baz()
+}
+
+attributes #0 = { "target-cpu"="generic" "target-features"="+crc,+neon" }
+attributes #1 = { "target-cpu"="generic" "target-features"="+crc,+neon,+crypto" }
+attributes #2 = { "target-cpu"="generic" "target-features"="+crc,+neon,+strict-align" }
diff --git a/test/Transforms/Inline/inline-cold-callsite-pgo.ll b/test/Transforms/Inline/inline-cold-callsite-pgo.ll
new file mode 100644
index 000000000000..26ea8e50eaf1
--- /dev/null
+++ b/test/Transforms/Inline/inline-cold-callsite-pgo.ll
@@ -0,0 +1,54 @@
+; RUN: opt < %s -passes='require<profile-summary>,cgscc(inline)' -inline-threshold=100 -inline-cold-callsite-threshold=0 -S | FileCheck %s
+
+; This tests that a cold callsite gets the inline-cold-callsite-threshold
+; and does not get inlined. Another callsite to an identical callee that
+; is not cold gets inlined because cost is below the inline-threshold.
+
+define i32 @callee1(i32 %x) !prof !21 {
+  %x1 = add i32 %x, 1
+  %x2 = add i32 %x1, 1
+  %x3 = add i32 %x2, 1
+  call void @extern()
+  ret i32 %x3
+}
+
+define i32 @caller(i32 %n) !prof !22 {
+; CHECK-LABEL: @caller(
+  %cond = icmp sle i32 %n, 100
+  br i1 %cond, label %cond_true, label %cond_false, !prof !0
+
+cond_true:
+; CHECK-LABEL: cond_true:
+; CHECK-NOT: call i32 @callee1
+; CHECK: ret i32 %x3.i
+  %i = call i32 @callee1(i32 %n)
+  ret i32 %i
+cond_false:
+; CHECK-LABEL: cond_false:
+; CHECK: call i32 @callee1
+; CHECK: ret i32 %j
+  %j = call i32 @callee1(i32 %n)
+  ret i32 %j
+}
+declare void @extern()
+
+!0 = !{!"branch_weights", i32 200, i32 1}
+
+!llvm.module.flags = !{!1}
+!21 = !{!"function_entry_count", i64 200}
+!22 = !{!"function_entry_count", i64 200}
+
+!1 = !{i32 1, !"ProfileSummary", !2}
+!2 = !{!3, !4, !5, !6, !7, !8, !9, !10}
+!3 = !{!"ProfileFormat", !"InstrProf"}
+!4 = !{!"TotalCount", i64 10000}
+!5 = !{!"MaxCount", i64 1000}
+!6 = !{!"MaxInternalCount", i64 1}
+!7 = !{!"MaxFunctionCount", i64 1000}
+!8 = !{!"NumCounts", i64 3}
+!9 = !{!"NumFunctions", i64 3}
+!10 = !{!"DetailedSummary", !11}
+!11 = !{!12, !13, !14}
+!12 = !{i32 10000, i64 1000, i32 1}
+!13 = !{i32 999000, i64 1000, i32 1}
+!14 = !{i32 999999, i64 1, i32 2}
diff --git a/test/Transforms/Inline/inline-cold-callsite.ll b/test/Transforms/Inline/inline-cold-callsite.ll
index 26ea8e50eaf1..50dd55d62edb 100644
--- a/test/Transforms/Inline/inline-cold-callsite.ll
+++ b/test/Transforms/Inline/inline-cold-callsite.ll
@@ -1,54 +1,47 @@
+
 ; RUN: opt < %s -passes='require<profile-summary>,cgscc(inline)' -inline-threshold=100 -inline-cold-callsite-threshold=0 -S | FileCheck %s
 
 ; This tests that a cold callsite gets the inline-cold-callsite-threshold
 ; and does not get inlined. Another callsite to an identical callee that
 ; is not cold gets inlined because cost is below the inline-threshold.
 
-define i32 @callee1(i32 %x) !prof !21 {
-  %x1 = add i32 %x, 1
-  %x2 = add i32 %x1, 1
-  %x3 = add i32 %x2, 1
+define void @callee() {
+  call void @extern()
   call void @extern()
-  ret i32 %x3
+  ret void
 }
 
-define i32 @caller(i32 %n) !prof !22 {
-; CHECK-LABEL: @caller(
-  %cond = icmp sle i32 %n, 100
-  br i1 %cond, label %cond_true, label %cond_false, !prof !0
-
-cond_true:
-; CHECK-LABEL: cond_true:
-; CHECK-NOT: call i32 @callee1
-; CHECK: ret i32 %x3.i
-  %i = call i32 @callee1(i32 %n)
-  ret i32 %i
-cond_false:
-; CHECK-LABEL: cond_false:
-; CHECK: call i32 @callee1
-; CHECK: ret i32 %j
-  %j = call i32 @callee1(i32 %n)
-  ret i32 %j
-}
 declare void @extern()
+declare i1 @ext(i32)
+
+; CHECK-LABEL: caller
+define i32 @caller(i32 %n) {
+entry:
+  %cmp4 = icmp sgt i32 %n, 0
+  br i1 %cmp4, label %for.body, label %for.cond.cleanup
+
+for.cond.cleanup:
+  ret i32 0
+
+for.body:
+  %i.05 = phi i32 [ %inc, %for.inc ], [ 0, %entry ]
+; CHECK: %call = tail call
+  %call = tail call zeroext i1 @ext(i32 %i.05)
+; CHECK-NOT: call void @callee
+; CHECK-NEXT: call void @extern
+  call void @callee()
+  br i1 %call, label %cold, label %for.inc, !prof !0
+
+cold:
+; CHECK: call void @callee
+  call void @callee()
+  br label %for.inc
+
+for.inc:
+  %inc = add nuw nsw i32 %i.05, 1
+  %exitcond = icmp eq i32 %inc, %n
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+}
+
 
-!0 = !{!"branch_weights", i32 200, i32 1}
-
-!llvm.module.flags = !{!1}
-!21 = !{!"function_entry_count", i64 200}
-!22 = !{!"function_entry_count", i64 200}
-
-!1 = !{i32 1, !"ProfileSummary", !2}
-!2 = !{!3, !4, !5, !6, !7, !8, !9, !10}
-!3 = !{!"ProfileFormat", !"InstrProf"}
-!4 = !{!"TotalCount", i64 10000}
-!5 = !{!"MaxCount", i64 1000}
-!6 = !{!"MaxInternalCount", i64 1}
-!7 = !{!"MaxFunctionCount", i64 1000}
-!8 = !{!"NumCounts", i64 3}
-!9 = !{!"NumFunctions", i64 3}
-!10 = !{!"DetailedSummary", !11}
-!11 = !{!12, !13, !14}
-!12 = !{i32 10000, i64 1000, i32 1}
-!13 = !{i32 999000, i64 1000, i32 1}
-!14 = !{i32 999999, i64 1, i32 2}
+!0 = !{!"branch_weights", i32 1, i32 2000}
diff --git a/test/Transforms/Inline/optimization-remarks-yaml.ll b/test/Transforms/Inline/optimization-remarks-yaml.ll
index 532e443e2170..16783634484f 100644
--- a/test/Transforms/Inline/optimization-remarks-yaml.ll
+++ b/test/Transforms/Inline/optimization-remarks-yaml.ll
@@ -1,8 +1,21 @@
-; RUN: opt < %s -S -inline -pass-remarks-missed=inline -pass-remarks-with-hotness \
+; RUN: opt < %s -S -inline -pass-remarks-missed=inline \
+; RUN:     -pass-remarks-with-hotness -pass-remarks-hotness-threshold 15 \
 ; RUN:     -pass-remarks-output=%t 2>&1 | FileCheck %s
 ; RUN: cat %t | FileCheck -check-prefix=YAML %s
 ; RUN: opt < %s -S -inline -pass-remarks-with-hotness -pass-remarks-output=%t
 ; RUN: cat %t | FileCheck -check-prefix=YAML %s
+;
+; Verify that remarks that don't meet the hotness threshold are not output.
+; RUN: opt < %s -S -inline -pass-remarks-missed=inline \
+; RUN:     -pass-remarks-with-hotness -pass-remarks-hotness-threshold 100 \
+; RUN:     -pass-remarks-output=%t.threshold 2>&1 | \
+; RUN:     FileCheck -check-prefix=THRESHOLD %s
+; RUN: test ! -s %t.threshold
+; RUN: opt < %s -S -inline \
+; RUN:     -pass-remarks-with-hotness -pass-remarks-hotness-threshold 100 \
+; RUN:     -pass-remarks-output=%t.threshold
+; The remarks output file should be empty.
+; RUN: test ! -s %t.threshold
 
 ; Check the YAML file generated for inliner remarks for this program:
 ;
@@ -43,6 +56,9 @@
 ; YAML-NEXT:   - String: ' because its definition is unavailable'
 ; YAML-NEXT: ...
 
+; No remarks should be output, since none meet the threshold.
+; THRESHOLD-NOT: remark
+
 ; ModuleID = '/tmp/s.c'
 source_filename = "/tmp/s.c"
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
diff --git a/test/Transforms/Inline/pr33637.ll b/test/Transforms/Inline/pr33637.ll
new file mode 100644
index 000000000000..315feca27bd9
--- /dev/null
+++ b/test/Transforms/Inline/pr33637.ll
@@ -0,0 +1,25 @@
+; RUN: opt -inline < %s
+
+define void @patatino() {
+for.cond:
+  br label %for.body
+
+for.body:
+  %tobool = icmp eq i32 5, 0
+  %sel = select i1 %tobool, i32 0, i32 2
+  br i1 undef, label %cleanup1.thread, label %cleanup1
+
+cleanup1.thread:
+  ret void
+
+cleanup1:
+  %cleanup.dest2 = phi i32 [ %sel, %for.body ]
+  %switch = icmp ult i32 %cleanup.dest2, 1
+  ret void
+}
+
+define void @main() {
+entry:
+  call void @patatino()
+  ret void
+}