Determine callee's hotness and adjust threshold based on that. NFC.

This uses the same criteria used in CFE's CodeGenPGO to identify hot and cold
callees and uses values of inlinehint-threshold and inlinecold-threshold
respectively as the thresholds for such callees.

Differential Revision: http://reviews.llvm.org/D15245

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@256222 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/IPO/Inliner.cpp b/lib/Transforms/IPO/Inliner.cpp
index 14b1767721d095e600dd4101f85fa787c7287647..545050171367fa0f9db0cf4e6c01206b994e1e54 100644 (file)
--- a/lib/Transforms/IPO/Inliner.cpp
+++ b/lib/Transforms/IPO/Inliner.cpp
@@ -288,18 +288,42 @@ unsigned Inliner::getInlineThreshold(CallSite CS) const {
       OptSizeThreshold < Threshold)
     Threshold = OptSizeThreshold;
 
-  // Listen to the inlinehint attribute when it would increase the threshold
-  // and the caller does not need to minimize its size.
   Function *Callee = CS.getCalledFunction();
-  bool InlineHint = Callee && !Callee->isDeclaration() &&
-                    Callee->hasFnAttribute(Attribute::InlineHint);
+  if (!Callee || Callee->isDeclaration())
+    return Threshold;
+
+  // If profile information is available, use that to adjust threshold of hot
+  // and cold functions.
+  // FIXME: The heuristic used below for determining hotness and coldness are
+  // based on preliminary SPEC tuning and may not be optimal. Replace this with
+  // a well-tuned heuristic based on *callsite* hotness and not callee hotness.
+  uint64_t FunctionCount = 0, MaxFunctionCount = 0;
+  bool HasPGOCounts = false;
+  if (Callee->getEntryCount() &&
+      Callee->getParent()->getMaximumFunctionCount()) {
+    HasPGOCounts = true;
+    FunctionCount = Callee->getEntryCount().getValue();
+    MaxFunctionCount =
+        Callee->getParent()->getMaximumFunctionCount().getValue();
+  }
+
+  // Listen to the inlinehint attribute or profile based hotness information
+  // when it would increase the threshold and the caller does not need to
+  // minimize its size.
+  bool InlineHint =
+      Callee->hasFnAttribute(Attribute::InlineHint) ||
+      (HasPGOCounts &&
+       FunctionCount >= (uint64_t)(0.3 * (double)MaxFunctionCount));
   if (InlineHint && HintThreshold > Threshold &&
       !Caller->hasFnAttribute(Attribute::MinSize))
     Threshold = HintThreshold;
 
-  // Listen to the cold attribute when it would decrease the threshold.
-  bool ColdCallee = Callee && !Callee->isDeclaration() &&
-                    Callee->hasFnAttribute(Attribute::Cold);
+  // Listen to the cold attribute or profile based coldness information
+  // when it would decrease the threshold.
+  bool ColdCallee =
+      Callee->hasFnAttribute(Attribute::Cold) ||
+      (HasPGOCounts &&
+       FunctionCount <= (uint64_t)(0.01 * (double)MaxFunctionCount));
   // Command line argument for InlineLimit will override the default
   // ColdThreshold. If we have -inline-threshold but no -inlinecold-threshold,
   // do not use the default cold threshold even if it is smaller.

diff --git a/test/Transforms/Inline/inline-cold-callee.ll b/test/Transforms/Inline/inline-cold-callee.ll
new file mode 100644 (file)
index 0000000..1fd9f10
--- /dev/null
+++ b/test/Transforms/Inline/inline-cold-callee.ll
@@ -0,0 +1,39 @@
+; RUN: opt < %s -inline  -inlinecold-threshold=0 -S | FileCheck %s
+
+; This tests that a cold callee gets the (lower) inlinecold-threshold even without
+; Cold hint and does not get inlined because the cost exceeds the inlinecold-threshold.
+; A callee with identical body does gets inlined because cost fits within the
+; inline-threshold
+
+define i32 @callee1(i32 %x) !prof !1 {
+  %x1 = add i32 %x, 1
+  %x2 = add i32 %x1, 1
+  %x3 = add i32 %x2, 1
+
+  ret i32 %x3
+}
+
+define i32 @callee2(i32 %x) !prof !2 {
+; CHECK-LABEL: @callee2(
+  %x1 = add i32 %x, 1
+  %x2 = add i32 %x1, 1
+  %x3 = add i32 %x2, 1
+
+  ret i32 %x3
+}
+
+define i32 @caller2(i32 %y1) !prof !2 {
+; CHECK-LABEL: @caller2(
+; CHECK: call i32 @callee2
+; CHECK-NOT: call i32 @callee1
+; CHECK: ret i32 %x3.i
+  %y2 = call i32 @callee2(i32 %y1)
+  %y3 = call i32 @callee1(i32 %y2)
+  ret i32 %y3
+}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"MaxFunctionCount", i32 1000}
+!1 = !{!"function_entry_count", i64 100}
+!2 = !{!"function_entry_count", i64 1}
+

diff --git a/test/Transforms/Inline/inline-hot-callee.ll b/test/Transforms/Inline/inline-hot-callee.ll
new file mode 100644 (file)
index 0000000..93ea9d4
--- /dev/null
+++ b/test/Transforms/Inline/inline-hot-callee.ll
@@ -0,0 +1,39 @@
+; RUN: opt < %s -inline -inline-threshold=0 -inlinehint-threshold=100 -S | FileCheck %s
+
+; This tests that a hot callee gets the (higher) inlinehint-threshold even without
+; inline hints and gets inlined because the cost is less than inlinehint-threshold.
+; A cold callee with identical body does not get inlined because cost exceeds the
+; inline-threshold
+
+define i32 @callee1(i32 %x) !prof !1 {
+  %x1 = add i32 %x, 1
+  %x2 = add i32 %x1, 1
+  %x3 = add i32 %x2, 1
+
+  ret i32 %x3
+}
+
+define i32 @callee2(i32 %x) !prof !2 {
+; CHECK-LABEL: @callee2(
+  %x1 = add i32 %x, 1
+  %x2 = add i32 %x1, 1
+  %x3 = add i32 %x2, 1
+
+  ret i32 %x3
+}
+
+define i32 @caller2(i32 %y1) !prof !2 {
+; CHECK-LABEL: @caller2(
+; CHECK: call i32 @callee2
+; CHECK-NOT: call i32 @callee1
+; CHECK: ret i32 %x3.i
+  %y2 = call i32 @callee2(i32 %y1)
+  %y3 = call i32 @callee1(i32 %y2)
+  ret i32 %y3
+}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"MaxFunctionCount", i32 10}
+!1 = !{!"function_entry_count", i64 10}
+!2 = !{!"function_entry_count", i64 1}
+